feat(linkedin-thought-leadership): v1.1.0 — Q2 2026 feature release

9 improvements across 3 tracks:

Onboarding: /linkedin:onboarding wizard, README Quick Start rewrite
Content Quality: voice drift scoring, industry angle variants,
  /linkedin:carousel, /linkedin:react multi-URL comparison
Analytics: automated week-rollover, day-of-week heatmap,
  month-over-month reports

25→27 commands. All Q2 ROADMAP items completed.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

plugins/linkedin-thought-leadership/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "linkedin-thought-leadership",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "description": "Build LinkedIn thought leadership with algorithmic understanding, strategic consistency, and authentic engagement. Updated for the January 2026 360Brew algorithm change.",
   "author": {
     "name": "Kjell Tore Guttormsen"

plugins/linkedin-thought-leadership/CHANGELOG.md

@@ -5,6 +5,29 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.1.0] - 2026-04-08
+
+### Summary
+Q2 2026 feature release. 9 improvements across onboarding, content quality, and analytics pipeline.
+
+### Added
+- **`/linkedin:onboarding`** — multi-step onboarding wizard: profile → setup → first-post as one guided flow
+- **`/linkedin:carousel`** — structured multi-slide carousel generator with 5 templates and design specs
+- **Voice drift scoring** — 6-dimension rubric (sentence structure, word choice, openings, storytelling, tone, formatting) with AUTHENTIC/CAUTION/ALERT/REWRITE verdicts in voice-guardian hook
+- **Industry angle variants** — 48 concrete variants (6 industries × 8 angles) in thought-leadership-angles reference
+- **Multi-URL comparison** — `/linkedin:react` now supports 2-3 URL synthesis with contrarian and pattern analysis angles
+- **Day-of-week heatmap** — `heatmap` CLI command and `HeatmapReport` type in analytics pipeline
+- **Month-over-month reports** — `report --month YYYY-MM` CLI command with MoM deltas, weekly breakdown, top performers
+- **Automated week-rollover** — session-start hook now writes `posts_this_week: 0` and updates `current_week` on ISO week change
+- **Collected Post Samples** — Stop hook passively accumulates published posts in voice-samples file for drift scoring
+
+### Changed
+- **README Quick Start** — replaced 4-step manual flow with single `/linkedin:onboarding` entry point
+- **`/linkedin:report`** — Step 2 now offers report type choice (weekly/monthly/heatmap)
+- **`/linkedin:post`** — Step 2 shows industry-specific angles when user-profile has industry set; Step 3 redirects to carousel when appropriate
+- **`/linkedin` router** — added onboarding and carousel to menus and direct routing
+- **Command count** — 25 → 27 (onboarding, carousel)
+
 ## [1.0.0] - 2026-04-07
 
 ### Summary

plugins/linkedin-thought-leadership/CLAUDE.md

@@ -1,4 +1,4 @@
-# LinkedIn Thought Leadership Plugin (v1.0.0)
+# LinkedIn Thought Leadership Plugin (v1.1.0)
 
 Build LinkedIn thought leadership with algorithmic understanding, strategic consistency, and authentic engagement. January 2026 360Brew algorithm update integrated.
 
@@ -27,11 +27,12 @@ Build LinkedIn thought leadership with algorithmic understanding, strategic cons
 
 **Hook editing:** Edit `hooks/hooks.template.json` + `hooks/prompts/*.md`, then run `python3 hooks/scripts/compile-hooks.py`. Do not edit `hooks.json` directly. Prompts are loaded at runtime by gatekeeper scripts; the compile step is only needed when adding `type: prompt` hooks.
 
-## Commands (25)
+## Commands (27)
 
 | Command | Purpose |
 |---------|---------|
 | `/linkedin` | Router — status line + command menu |
+| `/linkedin:onboarding` | Multi-step onboarding wizard (profile → setup → first-post) |
 | `/linkedin:first-post` | First-post accelerator (10 min) |
 | `/linkedin:setup` | Guided personalization setup |
 | `/linkedin:react` | URL-to-post pipeline |
@@ -42,6 +43,7 @@ Build LinkedIn thought leadership with algorithmic understanding, strategic cons
 | `/linkedin:batch` | Create a full week of content |
 | `/linkedin:calendar` | View/manage post scheduling queue |
 | `/linkedin:publish` | Mark scheduled posts as published |
+| `/linkedin:carousel` | Structured multi-slide carousel generator |
 | `/linkedin:video` | Video script generator (30s-2min) |
 | `/linkedin:multiplatform` | Adapt content for other platforms |
 | `/linkedin:analyze` | Content/performance analysis |

plugins/linkedin-thought-leadership/README.md

@@ -4,15 +4,15 @@
 
 *Built for my own Claude Code workflow and shared openly for anyone who finds it useful. This is a solo project — bug reports and feature requests are welcome, but pull requests are not accepted.*
 
-![Version](https://img.shields.io/badge/version-1.0.0-blue)
+![Version](https://img.shields.io/badge/version-1.1.0-blue)
 ![Platform](https://img.shields.io/badge/platform-Claude_Code_Plugin-purple)
-![Commands](https://img.shields.io/badge/commands-25-green)
+![Commands](https://img.shields.io/badge/commands-27-green)
 ![Agents](https://img.shields.io/badge/agents-16-orange)
 ![Hooks](https://img.shields.io/badge/hooks-9-red)
 ![Reference Docs](https://img.shields.io/badge/reference_docs-24-teal)
 ![License](https://img.shields.io/badge/license-MIT-lightgrey)
 
-A comprehensive Claude Code plugin that turns LinkedIn from a chore into a system. It covers the full content lifecycle — from ideation and drafting through publishing, analytics, and growth strategy — with 25 slash commands, 16 specialized agents, 9 automated hooks, and a 24-document knowledge base grounded in LinkedIn's actual algorithm signals. Updated for the January 2026 **360Brew** algorithm change, where LinkedIn now validates your profile before distributing content.
+A comprehensive Claude Code plugin that turns LinkedIn from a chore into a system. It covers the full content lifecycle — from ideation and drafting through publishing, analytics, and growth strategy — with 27 slash commands, 16 specialized agents, 9 automated hooks, and a 24-document knowledge base grounded in LinkedIn's actual algorithm signals. Updated for the January 2026 **360Brew** algorithm change, where LinkedIn now validates your profile before distributing content.
 
 ---
 
@@ -82,55 +82,39 @@ Or add to your `~/.claude/settings.json`:
 }
 ```
 
-### First Conversation
+### Get Started (5 minutes)
 
-#### 1. Optimize Your Profile (Critical)
+Run the onboarding wizard — it walks you through profile, setup, and your first post in one flow:
-
-With the 360Brew update, profile optimization is no longer optional — LinkedIn validates your profile before distributing content:
 
 ```
-/linkedin:profile
+/linkedin:onboarding
 ```
 
-#### 2. Personalize the Plugin
+The wizard handles everything: 360Brew profile checklist, voice and user profile setup, and a guided first post.
 
-```bash
+### Already Set Up?
-cp config/user-profile.template.md config/user-profile.local.md
-# Edit with your name, expertise, audience, voice, and goals
-```
 
-Then run the guided setup to populate all asset templates:
+| Goal | Command |
-
+|------|---------|
-```
+| Write a post | `/linkedin:post` |
-/linkedin:setup
+| Quick 5-min post | `/linkedin:quick` |
-```
+| React to an article | `/linkedin:react` |
-
+| View your stats | `/linkedin:report` |
-#### 3. Create Your First Post
+| See all commands | `/linkedin` |
-
-```
-/linkedin:post
-> I want to write about how AI is changing public sector procurement
-```
-
-For a faster start, try the 5-minute quick post:
-
-```
-/linkedin:quick
-```
-
-#### 4. Explore All Commands
-
-```
-/linkedin
-```
-
-The router shows your current posting status (streak, weekly progress) and lists all available commands.
 
 ---
 
 ## Commands
 
-All 25 commands use colon notation: `/linkedin:post`, `/linkedin:quick`, etc.
+All 26 commands use colon notation: `/linkedin:post`, `/linkedin:quick`, etc.
+
+### Onboarding
+
+| Command | Description |
+|---------|-------------|
+| `/linkedin:onboarding` | Multi-step onboarding wizard — guides you through profile optimization, plugin personalization, and your first post in one flow. |
+| `/linkedin:first-post` | First-post accelerator — zero to published in 10 minutes with guided hand-holding. |
+| `/linkedin:setup` | Guided setup to populate empty asset templates with your real voice, case studies, and audience data. |
 
 ### Content Creation
 
@@ -146,7 +130,6 @@ All 25 commands use colon notation: `/linkedin:post`, `/linkedin:quick`, etc.
 | `/linkedin:video` | Video script generator for 30s, 60s, 90s, or 2-minute LinkedIn videos with pacing and visual cues. |
 | `/linkedin:multiplatform` | Adapt LinkedIn content for Twitter/X threads, newsletter sections, blog posts, presentation slides, and YouTube scripts. |
 | `/linkedin:react` | URL-to-post pipeline — paste an article, research paper, or news link and generate a reaction post. |
-| `/linkedin:first-post` | First-post accelerator — zero to published in 10 minutes with guided hand-holding. |
 
 ### Analytics
 
@@ -518,6 +501,7 @@ Scheduled posts are tracked in `assets/drafts/queue.json`:
 
 | Version | Date | Highlights |
 |---------|------|-----------|
+| **1.1.0** | 2026-04-08 | Q2 feature release. 27 commands (+onboarding, +carousel). Week-rollover automation, voice drift scoring, industry content matrix, multi-URL react, day-of-week heatmap, month-over-month reports. |
 | **1.0.0** | 2026-04-07 | Public release. 25 commands, 16 agents, 9 hooks, 6 skills, 24 reference docs. Agent model tiering (Sonnet/Haiku), all scripts Node.js, comprehensive documentation. |
 | **0.6.0** | 2026-02-07 | First formal version. 20 commands, 15 agents, 8 hooks, analytics system, 360Brew profile optimization, content matrix system, personalization engine, 20 reference documents. |
 

plugins/linkedin-thought-leadership/ROADMAP.md

@@ -1,6 +1,6 @@
 # LinkedIn Thought Leadership Plugin — Roadmap
 
-**Current version:** v1.0.0 (April 2026)
+**Current version:** v1.1.0 (April 2026)
 **Scope:** Planned improvements through Q4 2026
 
 Items organized by quarter and track. Priority = Impact / Effort (High/Medium/Low). Items within each quarter ordered by priority.
@@ -16,23 +16,23 @@ Items organized by quarter and track. Priority = Impact / Effort (High/Medium/Lo
 - [x] Condensed getting-started menu for zero-post users in `/linkedin` router
 - [x] Readiness check in `/linkedin:post` and `/linkedin:quick` for unpersonalized state
 - [x] Inline 5x5x5 engagement ritual explanation
-- [ ] `/linkedin:onboarding` — dedicated multi-step onboarding command that guides profile → setup → first-post as one flow
+- [x] `/linkedin:onboarding` — dedicated multi-step onboarding command that guides profile → setup → first-post as one flow
-- [ ] README Quick Start refinement — 5-minute getting-started path with screenshots
+- [x] README Quick Start refinement — 5-minute getting-started path with single `/linkedin:onboarding` entry point
 
 ### Content Quality
 **Priority: High** | **Effort: Medium**
 
-- [ ] Enhanced voice-trainer agent: automatic drift scoring on every post draft (compare against voice samples)
+- [x] Enhanced voice-trainer agent: automatic drift scoring on every post draft (compare against voice samples)
-- [ ] Content Matrix improvements: add industry-specific angle variants
+- [x] Content Matrix improvements: add industry-specific angle variants
-- [ ] Carousel post support: structured multi-slide content generation with visual layout guidance
+- [x] Carousel post support: structured multi-slide content generation with visual layout guidance
-- [ ] `/linkedin:react` enhancement: multi-URL comparison posts (compare 2-3 articles)
+- [x] `/linkedin:react` enhancement: multi-URL comparison posts (compare 2-3 articles)
 
 ### Analytics Pipeline
 **Priority: Medium** | **Effort: Medium**
 
-- [ ] Automated week-rollover: session-start hook resets `posts_this_week` and updates `current_week` on week change (currently warn-only)
+- [x] Automated week-rollover: session-start hook resets `posts_this_week` and updates `current_week` on week change
-- [ ] Post-level heatmap generation: day-of-week x time-of-day performance matrix from imported CSV data
+- [x] Post-level heatmap generation: day-of-week performance matrix from imported CSV data (time-of-day not available in CSV export)
-- [ ] `/linkedin:report` month-over-month comparison view
+- [x] `/linkedin:report` month-over-month comparison view
 
 ---
 

plugins/linkedin-thought-leadership/agents/content-planner.md

@@ -183,7 +183,7 @@ APRIL
 
 MAY
   - Microsoft Build (typically May) → AI announcements
-  - [National/regional holiday] → Cultural content
+  - 17. mai (Norwegian National Day) → Cultural content
   - End of spring conference season wrap-ups
 
 JUNE

plugins/linkedin-thought-leadership/agents/network-builder.md

@@ -5,7 +5,7 @@ description: |
   who to engage with, tracks engagement history, and guides the 5x5x5 method with
   specific people and posts to target. Includes connection request templates (300-char limit),
   collaboration pitch templates, follow-up sequences (day 1-30), and connection scoring
-  criteria.
+  criteria. Inherits DM template functionality from cancelled UPYOU-2078.
 
   Use when the user says:
   - "who should I connect with", "networking strategy", "build my network"

plugins/linkedin-thought-leadership/agents/trend-spotter.md

@@ -52,7 +52,7 @@ Before scanning, load the user's content pillars and expertise areas:
 ### Tier 1: Breaking News (daily, respond within 24-48h)
 
 - **OpenAI**, **Anthropic**, **Microsoft AI**, **Google AI** -- blog posts and announcements
-- **EU/[your region's] government** AI regulatory decisions
+- **EU/Norwegian government** AI regulatory decisions
 
 ### Tier 2: Analysis & Research (2-3x/week, post within a week)
 

plugins/linkedin-thought-leadership/assets/examples/high-engagement-posts.md

@@ -14,58 +14,145 @@ Claude will study these to understand your successful patterns and apply them to
 
 ---
 
-<!-- Add your posts here using this format:
+## Post 1: Ralph Wiggum / Vibe Coding (BASELINE)
 
-## Post 1: [Title/Topic]
+**Posted:** 2026-01-23, 23:13 CET (suboptimal timing)
-
+**Engagement:** Likes: 19 | Comments: 6 | Shares: 0
-**Posted:** [Date, time, timezone]
+**Reach:** 502 impressions
-**Engagement:** Likes: [N] | Comments: [N] | Shares: [N]
+**Engagement Rate:** 4.98%
-**Reach:** [N] impressions
+**Your Follower Count:** ~1,000
-**Engagement Rate:** [N]%
-**Your Follower Count:** ~[N]
 
 **The Post:**
 ```
-[Paste your full post text here]
+𝗘𝗻 𝗱𝗮𝗴. 𝟭𝟬 𝟬𝟬𝟬 𝗹𝗶𝗻𝗷𝗲𝗿. 𝗨𝘁𝗲𝗻 å 𝘃æ𝗿𝗲 𝘂𝘁𝘃𝗶𝗸𝗹𝗲𝗿.
+
+Jeg er ikke utvikler. Jeg er KI-rådgiver. Jeg kan ikke skrive kode fra bunnen av.
+
+Men jeg kan kommunisere med Claude Code. Og det viser seg at det er nok.
+
+𝗛𝘃𝗼𝗿𝗱𝗮𝗻 𝗱𝗲𝘁 𝘀𝘁𝗮𝗿𝘁𝗲𝘁
+
+Denne uken var jeg på Claude Code Meetup i Oslo. 250+ deltakere. Arrangert av Aleksander Stensby og Mesh Oslo.
+
+Aleksander nevnte "Ralph Wiggum-teknikken" som er en metode for å la AI bygge applikasjoner helt på egen hånd.
+
+På spørsmål om hvem som faktisk hadde fullført en hel slik prosess, rakk én person opp hånden. Av 250.
+
+Den kvelden bestemte jeg meg: I morgen tester jeg dette.
+
+𝗞𝗼𝗻𝘀𝗲𝗽𝘁𝗲𝘁
+
+Du blir intervjuet og ender opp med en liste med oppgaver. Starter en prosess. Går og lager kaffe, eller sover.
+
+Når du kommer tilbake er applikasjonen bygget.
+
+𝗠𝗶𝗻 𝗱𝗮𝗴
+
+Klokken 08:00 fant jeg et enkelt Ralph Wiggum script på 100 linjer. Klokken 23:00 hadde jeg 10 000 linjer og et komplett rammeverk.
+
+Ikke ved å skrive kode selv — men ved å forklare hva jeg ville ha:
+
+"Claude, stopp etter fem feil på rad."
+"Claude, send meg Slack-melding når du er ferdig."
+"Claude, lag en AI som vurderer om ting ser bra ut visuelt."
+
+Claude foreslo løsninger. Jeg sa ja. Ferdig.
+
+𝗙ø𝗹𝗲𝗹𝘀𝗲𝗻
+
+Starte prosessen med 30 oppgaver. Gjør noe annet. Komme tilbake og se oppgavene tikke av. Én etter én.
+
+Å våkne til en Slack-melding: "🎉 Ferdig. Alle 30 oppgaver fullført."
+
+Å åpne mappen og se en fungerende app. Som jeg ikke skrev. Men som jeg 𝘥𝘦𝘧𝘪𝘯𝘦𝘳𝘵𝘦.
+
+𝗥𝗲𝘀𝘂𝗹𝘁𝗮𝘁
+
+Tre prototyper i dag; booking-app, dashbord, skjemaverktøy. Hver tok én time. Null linjer kode. Bare beskrivelser.
+
+𝗗𝗲𝗻 æ𝗿𝗹𝗶𝗴𝗲 𝗱𝗲𝗹𝗲𝗻
+
+Alt dette tok én dag. Og jeg skraper bare i overflaten.
+
+Det ryktes at Anthropic bygde Claude Cowork, et helt produkt, med fire personer på ti dager. Vi er i starten av noe stort.
+
+De som eksperimenterer nå kommer til å ha et forsprang. Det er ikke lenger AI som er begrensningen, det er deg og meg.
+
+𝗦å 𝗷𝗮. 𝗥𝗮𝗹𝗽𝗵 𝗪𝗶𝗴𝗴𝘂𝗺.
+
+Oppkalt etter Simpsons-karakteren som sier: "I'm learnding!"
+
+Det føles passende :-)
+
+—
+
+Jeg jobber i KI-seksjonen i Statens vegvesen. Mer om dette og andre eksperimenter i kommende innlegg.
+
+𝗧𝗶𝗽𝘀: Claude Code Meetup i Oslo arrangeres jevnlig, sjekk [lenke]
+
+#AI #ClaudeCode #VibeCoding #StatensVegvesen #Innovasjon
 ```
 
-**Why It Worked:**
+**Why It Worked (Despite Mistakes):**
-- **Hook:** [What made people stop scrolling?]
+- **Hook:** Strong - "En dag. 10 000 linjer. Uten å være utvikler." Creates immediate curiosity gap with specific numbers and contrast
-- **Angle:** [What framing did you use?]
+- **Angle:** Personal Lesson + Discovery narrative - "I tried this, here's what happened"
-- **Timing:** [Was the timing good/bad?]
+- **Timing:** FAILED - Posted 23:13, missed Golden Hour entirely
-- **CTA:** [Did you include a call-to-action?]
+- **CTA:** MISSING - No engagement prompt at end
+- **Key insight:** Concrete numbers (10,000 lines, 250 people, 1 person raised hand) create credibility
+
+**Mistakes Made:**
+1. Posted at 23:13 (should be 08:00)
+2. Link in post body (should be in first comment)
+3. 5 hashtags (should be 3-4)
+4. No CTA (should ask question or invite discussion)
+5. Em dash used (should avoid)
+6. Post was in Norwegian (strategy says English)
 
 **Pattern to Replicate:**
-- [What can you reuse in future posts?]
+- Hook with specific numbers + contrast works well
+- "I'm not X, but I did Y" framing creates relatability
+- Concrete timeline (08:00 to 23:00) adds credibility
+- "Følelsen" section (emotional payoff) resonates
+- Bold-formatted section headers improve readability
 
 **Audience Response Themes:**
-- [What did people comment about?]
+- Interest in the technical process
+- Questions about Ralph Wiggum technique
+- Recognition from Claude Code community
+
+**What to Test Next:**
+- Same quality content, but posted at 08:00
+- With proper CTA
+- Without link in body
+- In English
 
 ---
 
--->
-
 ## Patterns Across All High-Performing Posts
 
 **Common Elements:**
-- [ ] Specific numbers in hook
+- [x] Specific numbers in hook (10,000 lines, 250 people)
-- [ ] Personal story structure (I did X, here's what happened)
+- [x] Personal story structure (I did X, here's what happened)
-- [ ] Concrete timeline and details
+- [x] Concrete timeline and details
-- [ ] Strong CTA
+- [ ] Strong CTA (not yet tested)
-- [ ] Optimal timing
+- [ ] Optimal timing (not yet tested)
 
 **Audience Preferences (What YOUR Audience Responds To):**
-- Format: [Discover from your data]
+- Format: Story-based posts with concrete details
-- Length: [Your typical length]
+- Length: ~2,100 characters (slightly over optimal 1,800)
-- Tone: [Your tone pattern]
+- Tone: Professional but personal, showing vulnerability ("I'm not a developer")
-- CTAs: [What works for your audience?]
+- CTAs: Unknown - need to test
 
 **Topics That Resonate:**
-1. [Add after 3+ posts]
+1. AI-assisted coding / Vibe coding
 2. [More data needed]
 3. [More data needed]
 
 **Best Posting Times (Based on YOUR Data):**
-- Primary: [Test and record]
+- Primary: Unknown - need to test 08:00 CET
-- Secondary: [Test and record]
+- Secondary: Unknown - need to test
-- **Avoid:** [Based on your data]
+- **Avoid:** After 21:00 (confirmed by Ralph Wiggum failure)
+
+## Update Log
+
+- 2026-01-24: Added Ralph Wiggum post as baseline reference. Note: Post had good engagement rate (4.98%) despite multiple mistakes, suggesting content quality is strong. Focus on fixing timing, CTA, and link placement for next posts.

plugins/linkedin-thought-leadership/assets/voice-samples/authentic-voice-samples.md

@@ -1,71 +1,100 @@
-# Authentic Voice Samples - [Your Name]
+# Authentic Voice Samples - Kjell Tore Guttormsen
 
-These guidelines help Claude understand and replicate [Your Name]'s natural writing style for LinkedIn content.
+These guidelines help Claude understand and replicate Kjell Tore's natural writing style for LinkedIn content.
 
 ## Voice Profile Summary
 
-Fill in this section with your own writing characteristics. Run `/linkedin:setup` to build your voice profile interactively, or edit this file directly.
+Kjell Tore does not have traditional writing samples to share. Instead, his voice is defined by the following characteristics which Claude should internalize and apply consistently.
 
 ---
 
 ## Core Voice Characteristics
 
-<!-- Replace these with your own voice traits. The examples below are common defaults - keep what fits, remove what doesn't, add your own. -->
+### 1. Solution-Oriented Mindset
+- Every problem is presented as an opportunity
+- Never complains without offering a path forward
+- Focuses on "what can be done" rather than "what went wrong"
+- Sees challenges as interesting puzzles to solve
 
-### 1. [Your Primary Trait]
+### 2. Factual Grounding
-- [Describe how this trait shows up in your writing]
+- Statements are based on facts, not assumptions
-- [What makes your approach distinctive?]
+- If uncertain, acknowledges uncertainty openly
+- Prefers data and evidence over opinions
+- Avoids speculation presented as fact
 
-### 2. [Your Secondary Trait]
+### 3. Non-Judgmental Tone
-- [Describe how this trait shows up in your writing]
+- Observes and explains without criticizing others
+- Builds up, never tears down
+- Avoids negative commentary about people, companies, or decisions
+- When discussing alternatives, frames as "different approaches" not "better/worse"
 
-### 3. [Your Third Trait]
+### 4. Curiosity and Openness
-- [Describe how this trait shows up in your writing]
+- Genuinely interested in learning new things
+- Open to new ideas and approaches
+- Asks questions to understand, not to challenge
+- Embraces "I don't know" as a starting point for exploration
 
-<!-- Add more traits as needed. Most voice profiles have 4-6 core characteristics. -->
+### 5. Storytelling Approach
+- Uses narrative techniques to make points memorable
+- Varies storytelling patterns based on content:
+  - Hero's journey (transformation stories)
+  - Problem-solution (practical content)
+  - Before-after (showing change/improvement)
+  - Discovery narrative (learning something new)
+  - Day-in-the-life (practical application)
+- Shows rather than tells
+
+### 6. Actionable Conclusions
+- Ends with something the reader can do
+- The more actionable, the better
+- If no clear action, provides a clear summary/takeaway
+- Never ends on a vague note
 
 ---
 
 ## Cross-Sample Analysis
 
-### Do's (Things that sound like [Your Name])
+### Do's (Things that sound like Kjell Tore)
 
-<!-- Replace these with patterns from YOUR best-performing posts. Run /linkedin:setup to analyze your writing samples. The items below are common best practices you can keep as defaults. -->
+- ✅ Start with stories or concrete examples before explaining concepts
+- ✅ Use clear, accessible language even for technical topics
+- ✅ Explain technical concepts thoroughly - assume intelligence, not knowledge
+- ✅ Show rather than tell - demonstrate with examples
+- ✅ End with actionable takeaways - what can the reader do NOW?
+- ✅ Vary storytelling techniques based on the content
+- ✅ Be genuinely helpful and supportive
+- ✅ Acknowledge complexity before simplifying
+- ✅ Use transitions like "What I've learned is..." to share insights
+- ✅ Frame discoveries as shared learning, not lecturing
+- ✅ Keep posts concise - short to medium length (800-1500 characters)
 
-- Start with stories or concrete examples before explaining concepts
+### Don'ts (Things Kjell Tore would NEVER say)
-- Use clear, accessible language even for technical topics
-- Explain technical concepts thoroughly - assume intelligence, not knowledge
-- Show rather than tell - demonstrate with examples
-- End with actionable takeaways - what can the reader do NOW?
-- Vary storytelling techniques based on the content
-- Be genuinely helpful and supportive
-- Acknowledge complexity before simplifying
-- Frame discoveries as shared learning, not lecturing
-- Keep posts concise - short to medium length (800-1500 characters)
 
-### Don'ts (Things [Your Name] would NEVER say)
+- ❌ Don't use buzzwords: "game-changer", "leverage", "synergy", "disrupt", "revolutionize"
-
+- ❌ Don't criticize people, companies, or decisions
-<!-- Replace these with your personal anti-patterns. The items below are universal LinkedIn best practices. -->
+- ❌ Don't use self-deprecating humor
-
+- ❌ Don't make assumptions without facts
-- Don't use buzzwords: "game-changer", "leverage", "synergy", "disrupt", "revolutionize"
+- ❌ Don't write overly long posts (stay under 1500 characters for posts)
-- Don't criticize people, companies, or decisions
+- ❌ Don't use more than 1-2 emojis per post
-- Don't make assumptions without facts
+- ❌ Don't discuss politics, religion, or personal matters
-- Don't write overly long posts (stay under 1500 characters for posts)
+- ❌ Don't use em dashes (—) - use hyphens or alternatives instead
-- Don't use more than 1-2 emojis per post
+- ❌ Don't start with "Let's dive deep into..."
-- Don't start with "Let's dive deep into..."
+- ❌ Don't use excessive exclamation marks!!!
-- Don't use excessive exclamation marks
+- ❌ Don't use generic motivational phrases
-- Don't use generic motivational phrases
+- ❌ Don't be preachy or lecture the reader
-- Don't be preachy or lecture the reader
+- ❌ Don't use "we" when you mean "I" (be direct about personal experience)
 
 ---
 
 ## Signature Phrases
 
-<!-- Add 3-5 phrases that are distinctly yours. These help Claude maintain your voice. -->
+Use these naturally when appropriate - don't force them:
 
-- "[Your phrase 1]"
+- "Let me show you..."
-- "[Your phrase 2]"
+- "What I've learned is..."
-- "[Your phrase 3]"
+- "Here is the secret to..."
+
+These phrases signal a transition to insight or demonstration. Use them to introduce key points or revelations.
 
 ---
 
@@ -73,11 +102,11 @@ Fill in this section with your own writing characteristics. Run `/linkedin:setup
 
 ### Technical Terms - How to Handle
 
-<!-- Replace with your domain-specific terms. Examples: -->
+- **RAG (Retrieval-Augmented Generation):** Always explain on first use
-
+- **MCP (Model Context Protocol):** Explain what it enables, not just the acronym
-- **[Term 1]:** [How to explain/use it]
+- **Copilot Studio:** Can assume some familiarity with Microsoft ecosystem
-- **[Term 2]:** [How to explain/use it]
+- **Skills (Claude):** Explain as "reusable instruction sets" or similar
-- **[Term 3]:** [How to explain/use it]
+- **Low-code:** Generally understood, but clarify scope if needed
 
 **Principle:** Assume intelligence, not knowledge. Explain jargon without being condescending.
 
@@ -100,10 +129,10 @@ Fill in this section with your own writing characteristics. Run `/linkedin:setup
 
 ## Humor and Personality
 
-- **Humor style:** [Describe your humor approach - absent, dry, observational, etc.]
+- **Humor style:** Mostly absent in professional content. If humor appears, it's observational and gentle - never at anyone's expense
-- **Self-deprecation:** [Your preference]
+- **Self-deprecation:** Never. Don't undermine your own credibility.
-- **Cultural references:** [Your approach]
+- **Cultural references:** Avoid pop culture references. Stick to professional/work context.
-- **Analogies:** [What kind of analogies work for your audience?]
+- **Analogies:** Use when helpful for explanation. Prefer technical or universal analogies over sports/culture-specific ones.
 
 ---
 
@@ -136,14 +165,14 @@ Match technical depth to the target audience:
 - ROI and outcomes
 - Avoid implementation details
 
-### For Practitioners
+### For Low-Code Developers
 - Practical tips and patterns
 - Step-by-step guidance
 - Tool-specific insights
 - Common pitfalls and solutions
 - Can include some technical detail
 
-### For Technical Experts
+### For AI Architects
 - Technical depth welcome
 - Architecture patterns
 - Integration approaches
@@ -163,24 +192,36 @@ Match technical depth to the target audience:
 
 ## Language Guidelines
 
-- Choose ONE language for all LinkedIn content and stick with it
+- **Always English** for all LinkedIn content
 - Clear, international English accessible to non-native speakers
 - Avoid idioms that don't translate well internationally
 - Prefer simple sentence structures for complex ideas
+- Never use em dashes (—) - use hyphens, commas, or separate sentences instead
 
 ---
 
 ## Instructions for Claude
 
-When generating LinkedIn content for [Your Name]:
+When generating LinkedIn content for Kjell Tore:
 
-1. **Start with the voice profile** (from this document)
+1. **Start with his voice profile** (from this document)
 2. **Check the content pillar** - which audience is this for?
 3. **Choose appropriate storytelling technique** for the content type
 4. **Ensure actionable conclusion** - what can the reader DO?
 5. **Verify against Don'ts list** - no buzzwords, no criticism, no assumptions
 6. **Keep length in check** - 800-1500 characters for posts
 
-**Priority:** Sound like [Your Name] > Optimize for algorithm
+**Priority:** Sound like Kjell Tore > Optimize for algorithm
 
-**Exception:** If a phrase or approach would harm reach (external links, engagement bait), flag it but maintain the voice in everything else.
+**Exception:** If a phrase or approach would harm reach (external links, engagement bait), flag it but maintain his voice in everything else.
+
+---
+
+## Update Log
+
+- 2025-11-30: Initial voice profile created based on interview
+
+## Collected Post Samples
+
+<!-- Posts are saved here automatically by the Stop hook after each session where content is created. -->
+<!-- The voice-trainer agent uses these for 6-dimension drift scoring. Needs 5+ samples for reliable results. -->

plugins/linkedin-thought-leadership/commands/carousel.md

@@ -0,0 +1,138 @@
+---
+name: linkedin:carousel
+description: |
+  Create a LinkedIn carousel post with structured slide-by-slide content and visual layout guidance.
+  Carousels have the highest engagement rate (6.6%) on LinkedIn. Guides template selection,
+  topic definition, and generates copy for each slide plus caption.
+  Triggers on: "carousel", "slide deck", "pdf post", "swipe post", "multi-slide",
+  "linkedin carousel", "document post", "create slides".
+allowed-tools:
+  - Read
+  - AskUserQuestion
+---
+
+# Carousel Post Generator
+
+You are a LinkedIn carousel content specialist. Create high-engagement carousel posts with structured slide content and visual layout guidance.
+
+## Step 0: Load Context
+
+- Read `~/.claude/linkedin-thought-leadership.local.md` for posting state and expertise areas
+- Read `assets/voice-samples/authentic-voice-samples.md` for voice profile
+- Check recent posts to avoid topic repetition
+
+## Step 1: Choose Template
+
+Read `assets/templates/carousel-templates.md` for the 5 templates.
+
+Present the options:
+
+```
+LinkedIn carousels get 6.6% average engagement — highest of all formats.
+
+Choose a template:
+
+1. How-To Guide — Teach a process step-by-step (8-10 slides)
+2. Listicle / Top N — Curated list of tips, tools, or lessons (8-12 slides)
+3. Story / Before-After — Personal narrative with transformation (8-10 slides)
+4. Comparison / vs. — Side-by-side analysis of two approaches (8-10 slides)
+5. Framework / Mental Model — Present an original framework (8-10 slides)
+```
+
+Use AskUserQuestion for selection.
+
+## Step 2: Define Topic and Audience
+
+Ask:
+1. "What's the core topic or insight for this carousel?"
+2. "Who is the primary audience? (e.g., developers, managers, executives)"
+
+If the user's expertise areas are set in the state file, suggest topics aligned with their pillars.
+
+## Step 3: Generate Slide Content
+
+Using the selected template structure from `carousel-templates.md`, generate content for each slide.
+
+**Output format for each slide:**
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+SLIDE [N] of [TOTAL] — [Purpose from template]
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+HEADER:
+[Bold headline text — max 8 words]
+
+BODY:
+[Line 1 — max 50 chars]
+[Line 2 — max 50 chars]
+[Line 3 — max 50 chars]
+[Line 4 — max 50 chars (optional)]
+[Line 5 — max 50 chars (optional)]
+
+VISUAL NOTE:
+[Layout suggestion: e.g., "Icon: lightbulb left of header",
+"Before/After split layout", "Numbered list with accent color",
+"Summary table with checkmarks"]
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+**Slide content rules:**
+- Max 5-7 lines of body text per slide (mobile readability)
+- One idea per slide — if it needs two points, it needs two slides
+- Use the template's formula for each slide type (cover, step, item, CTA, etc.)
+- Headlines in sentence case, not ALL CAPS
+- Include the template-specific patterns (Pro tip, Before/After, Winner, etc.)
+
+## Step 4: Generate Caption
+
+Generate a caption following the carousel caption structure from the template file:
+
+1. **Hook** (first line): Question, bold claim, or surprising stat — 110-140 chars
+2. **Context** (1-2 lines): Why this matters to the audience
+3. **Swipe prompt**: Reference a specific slide to create curiosity
+4. **Engagement CTA**: Question that invites comments
+5. **Hashtags**: 3-4 maximum
+
+Target: 300-500 characters total.
+
+Match the user's voice profile — check against avoid-list and tone markers.
+
+## Step 5: Quality Check
+
+Run against the Carousel Quality Checklist from `carousel-templates.md`:
+
+- [ ] Cover slide has a clear promise or question
+- [ ] Each slide has one point (not multiple ideas)
+- [ ] Text is readable on mobile (keep lines short)
+- [ ] 8-10 slides total
+- [ ] Last slide has a clear CTA
+- [ ] Caption hooks attention and prompts swipe
+- [ ] Consistent structure across all slides
+
+If any item fails, fix before presenting.
+
+## Step 6: Present Complete Deck
+
+Show all slides in order, then the caption, then design guidance:
+
+```
+DESIGN GUIDE
+━━━━━━━━━━━━
+Dimensions:  1080 × 1350 px (4:5 portrait)
+Font:        Sans-serif, 24pt+ body, 36pt+ headlines
+Colors:      Pick 3 — background, text, accent
+Export:      PDF format, under 100 MB
+Tools:       Canva, PowerPoint, Figma, or Keynote
+
+Create one slide per page using the content above.
+Export as PDF and upload directly to LinkedIn.
+```
+
+Use AskUserQuestion: "Want to refine any slides, or is this ready for design?"
+
+## Step 7: State Update
+
+If the user confirms the carousel is ready:
+- Note in state file: topic, format=carousel, slide count
+- Suggest: "After publishing, run the 5x5x5 engagement method for maximum reach."

plugins/linkedin-thought-leadership/commands/linkedin.md

@@ -27,23 +27,6 @@ The follower segment only appears if `follower_count > 0` in the state file.
 
 If the state file doesn't exist, show: "No LinkedIn state tracked yet. State tracking starts when you create your first post."
 
-## New User Detection
-
-After reading the state file, check if `first_post_date` is null/empty AND `posts_this_week` is 0. If so, this is a new user. Show a condensed getting-started menu INSTEAD of the full command list:
-
-**You haven't posted yet! Here's where to start:**
-
-| # | Action | Time |
-|---|--------|------|
-| 0 | **Profile audit** — optimize for 360Brew algorithm | 10 min |
-| 1 | **Personalize** — set up your voice, audience, and goals | 15 min |
-| 2 | **First post** — guided creation with hand-holding | 10 min |
-| 3 | **Show all commands** — I know what I'm doing |
-
-Use AskUserQuestion with these 4 options. Route 0 → `/linkedin:profile`, 1 → `/linkedin:setup`, 2 → `/linkedin:first-post`, 3 → continue to the full command list below.
-
-**Skip this section entirely if `first_post_date` is set or `posts_this_week` > 0.** Proceed to Upcoming Posts and the full command list.
-
 ## Upcoming Posts
 
 After the status line, show upcoming scheduled posts from the queue:
@@ -81,6 +64,7 @@ Present these options to the user:
 
 | Command | Purpose |
 |---------|---------|
+| `/linkedin:onboarding` | Full onboarding wizard — profile, setup, and first post in one flow |
 | `/linkedin:first-post` | First-post accelerator — zero to published in under 10 minutes |
 | `/linkedin:setup` | Guided setup to populate empty asset templates with your real voice, case studies, and audience data |
 
@@ -93,6 +77,7 @@ Present these options to the user:
 | `/linkedin:quick` | Fast 5-minute post using the 3-line formula |
 | `/linkedin:templates` | Browse and apply proven post templates |
 | `/linkedin:pipeline` | Full end-to-end workflow from idea to post-publish analysis |
+| `/linkedin:carousel` | Create structured multi-slide carousel with visual layout guidance |
 | `/linkedin:video` | Create video scripts with hook, body, CTA, captions, and thumbnail suggestions |
 | `/linkedin:batch` | Create a full week of content in one session |
 | `/linkedin:calendar` | View and manage your post scheduling queue |
@@ -133,7 +118,7 @@ Use AskUserQuestion to ask:
 
 **What would you like to do?**
 
-0. **First post** — Never posted? Start here (10 min)
+0. **Onboarding wizard** — Just installed? Full guided flow: profile → setup → first post
 1. **Setup & personalize** — Guided setup to populate voice, case studies, frameworks, and audience data
 2. **Create a post** — Full post workflow with angle selection
 3. **React to a URL** — Turn an article/news into a post
@@ -170,6 +155,7 @@ If the user already has content they want to turn into a post:
 ## Direct Routing
 
 If the user's intent is clear from context:
+- Mentions "onboarding" or "just installed" or "walk me through" or "setup wizard" or "start from scratch" → Route to `/linkedin:onboarding`
 - Mentions "first post" or "never posted" or "get started" or "new to linkedin" or "help me start" → Route to `/linkedin:first-post`
 - Mentions "setup" or "personalize" or "templates empty" or "score" or "fill in assets" or "configure plugin" → Route to `/linkedin:setup`
 - Mentions "react" or "this article" or "this url" or "turn this into" or "share this news" → Route to `/linkedin:react`
@@ -182,6 +168,7 @@ If the user's intent is clear from context:
 - Mentions "profile" or "360Brew" → Route to `/linkedin:profile`
 - Mentions "not working" or "low reach" → Route to `/linkedin:analyze`
 - Mentions "strategy" or "growth plan" → Route to `/linkedin:strategy`
+- Mentions "carousel" or "slides" or "slide deck" or "pdf post" or "swipe" or "document post" → Route to `/linkedin:carousel`
 - Mentions "template" → Route to `/linkedin:templates`
 - Mentions "audit" or "review strategy" → Route to `/linkedin:audit`
 - Mentions "authority" or "signature content" → Route to `/linkedin:authority`

plugins/linkedin-thought-leadership/commands/onboarding.md

@@ -0,0 +1,182 @@
+---
+name: linkedin:onboarding
+description: |
+  Multi-step onboarding wizard that guides new users through profile → setup → first-post
+  as one cohesive flow. Designed for users who have just installed the plugin and want a
+  single guided path instead of navigating 25 commands on their own.
+  Triggers on: "onboarding", "get started", "new user", "setup wizard", "start from scratch",
+  "just installed", "how do I start", "walk me through", "linkedin onboarding".
+allowed-tools:
+  - Read
+  - Bash
+  - AskUserQuestion
+---
+
+# LinkedIn Onboarding Wizard
+
+You are a LinkedIn thought leadership onboarding guide. Walk the user through profile optimization, plugin personalization, and their first post — all in one session.
+
+## Step 0: Load Context and Check State
+
+Read `~/.claude/linkedin-thought-leadership.local.md` for current state.
+
+**Already onboarded check:** If `first_post_date` is set (not null) AND personalization score > 50:
+- Show: "You've already completed onboarding (first post: [date], personalization: [score]%)."
+- Use AskUserQuestion: "Would you like to re-run a specific phase?"
+  1. Re-optimize profile (360Brew) → jump to Phase 1
+  2. Improve personalization → jump to Phase 2
+  3. Create another post → suggest `/linkedin:post` or `/linkedin:quick`
+  4. Exit
+
+If not already onboarded, continue to Phase 1.
+
+## Phase 1: Profile Optimization (360Brew)
+
+```
+╔═══════════════════════════════════════╗
+║  ONBOARDING — Phase 1 of 3: Profile  ║
+╚═══════════════════════════════════════╝
+```
+
+Explain briefly:
+- LinkedIn's 360Brew algorithm (January 2026) validates your profile BEFORE distributing your content
+- A weak profile means even great posts get suppressed
+- This takes 5 minutes and has outsized impact on everything else
+
+Use AskUserQuestion:
+1. **Guide me through profile optimization** — I want the full 360Brew checklist
+2. **Already optimized** — I've already done this, skip ahead
+3. **Do it later** — Skip for now, I'll run `/linkedin:profile` later
+
+**If option 1:** Walk through the core 360Brew checklist (condensed from `/linkedin:profile`):
+- [ ] Professional headshot (face visible, good lighting)
+- [ ] Headline with expertise + value prop (not just job title)
+- [ ] About section with story arc + CTA (not a resume)
+- [ ] Banner image related to expertise
+- [ ] Featured section with best content or lead magnet
+- [ ] Creator mode ON (if available)
+
+After each item, ask if done or needs to skip. Don't block — mark skipped items as "recommended later."
+
+**If option 2 or 3:** Move to Phase 2.
+
+## Phase 2: Plugin Personalization
+
+```
+╔═════════════════════════════════════════════╗
+║  ONBOARDING — Phase 2 of 3: Personalization ║
+╚═════════════════════════════════════════════╝
+```
+
+Calculate personalization score:
+```bash
+node --input-type=module -e "
+import { calculateScore } from '${CLAUDE_PLUGIN_ROOT}/hooks/scripts/personalization-score.mjs';
+const result = calculateScore('${CLAUDE_PLUGIN_ROOT}');
+console.log(JSON.stringify(result));
+"
+```
+
+Show the score dashboard:
+```
+Personalization Score: [XX]%
+
+Category          Weight  Status
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+Voice samples       25    [✓ Done / ○ Empty]
+User profile        20    [✓ Done / ○ Empty]
+Case studies        15    [✓ Done / ○ Empty]
+Frameworks          10    [✓ Done / ○ Empty]
+High-eng. posts     10    [✓ Done / ○ Empty]
+Demographics         8    [✓ Done / ○ Empty]
+Engagement patterns  7    [✓ Done / ○ Empty]
+Post templates       5    [✓ Done / ○ Empty]
+```
+
+Identify the **top 2 incomplete categories by weight** and guide through those:
+
+**Priority setup (2 categories only — keep it focused):**
+
+Use AskUserQuestion:
+1. **Set up voice profile** (weight: 25) — 5 questions about your writing style, or paste 3 examples
+2. **Set up user profile** (weight: 20) — Your name, industry, expertise areas, audience
+3. **Both** — Do voice + user profile now
+4. **Skip for now** — I'll run `/linkedin:setup` later for the full setup
+
+**If voice selected:** Run a quick 5-question voice interview:
+1. "How would you describe your communication style in one sentence?"
+2. "What words or phrases do you naturally use?" (give examples)
+3. "What tone turns you off in LinkedIn content?"
+4. "Paste a paragraph you've written that sounds like YOU (email, doc, anything)"
+5. "Any words or phrases you'd NEVER use?"
+
+Save responses to `assets/voice-samples/authentic-voice-samples.md` under a new section `## Quick Voice Interview` (append, don't overwrite existing content).
+
+**If user profile selected:** Ask for:
+1. Full name
+2. Industry
+3. Job title / role
+4. 3-5 expertise areas (these become your content pillars)
+5. Target audience description
+
+Save to `config/user-profile.local.md`.
+
+After setup, recalculate and show updated score.
+
+## Phase 3: First Post
+
+```
+╔═══════════════════════════════════════════╗
+║  ONBOARDING — Phase 3 of 3: First Post   ║
+╚═══════════════════════════════════════════╝
+```
+
+Check `first_post_date` in state file:
+
+**If null (no first post yet):**
+- "You're ready to create your first post! This is the most important step — your first post doesn't need to be perfect, it needs to EXIST."
+- Use AskUserQuestion:
+  1. **Guided first post** (10 min) — Maximum hand-holding, simple format → routes to `/linkedin:first-post` workflow
+  2. **Quick post** (5 min) — You already know what to say → routes to `/linkedin:quick` workflow
+  3. **Not now** — I'll post later
+
+**If first_post_date is set:**
+- "You already have your first post (published [date]). Ready to create your next one?"
+- Use AskUserQuestion:
+  1. **Create a new post** → suggest `/linkedin:post`
+  2. **Quick post** → suggest `/linkedin:quick`
+  3. **Exit onboarding**
+
+**If user chooses to post (option 1 or 2):** Don't invoke the sub-command directly — instead, tell them:
+"Run `/linkedin:first-post` to start the guided first-post flow."
+or
+"Run `/linkedin:quick` to create a quick post."
+
+This keeps the onboarding context clean and lets the post commands manage their own workflow.
+
+## Phase 4: Summary and Next Steps
+
+```
+╔═══════════════════════════════════════════╗
+║  ONBOARDING COMPLETE                      ║
+╚═══════════════════════════════════════════╝
+```
+
+Show final status:
+```
+Profile:          [Optimized / Skipped — run /linkedin:profile later]
+Personalization:  [XX]% [↑ from YY% if improved]
+First post:       [Published DATE / Pending — run /linkedin:first-post]
+```
+
+**What's next — your first week:**
+1. Create 2-3 posts this week (`/linkedin:post` or `/linkedin:quick`)
+2. Engage with 5 posts in your niche before and after publishing (5x5x5 method)
+3. Import your first analytics data after 7 days (`/linkedin:import`)
+4. Run `/linkedin:report` after your first week to see what's working
+
+**Power commands to explore:**
+- `/linkedin:batch` — Plan a full week of content in one session
+- `/linkedin:react` — Turn articles and news into posts
+- `/linkedin:strategy` — Growth strategy tailored to your follower level
+- `/linkedin` — See all 25 commands anytime

plugins/linkedin-thought-leadership/commands/post.md

@@ -23,16 +23,6 @@ You are a LinkedIn thought leadership content creator. Guide the user through cr
 First, load persistent state and personalization:
 - Read `~/.claude/linkedin-thought-leadership.local.md` for posting state (streak, weekly progress, recent topics)
 - Read `skills/linkedin-thought-leadership/SKILL.md` for user profile, voice settings, and preferences
-- Read `config/user-profile.local.md` (if it exists) for expertise areas and audience
-
-### Readiness Check
-
-If `config/user-profile.local.md` doesn't exist OR `assets/voice-samples/authentic-voice-samples.md` contains `[Your Name]` in the title line, show this non-blocking notice:
-
-> This plugin isn't personalized yet. Content will use generic best practices.
-> Run `/linkedin:setup` after this session to unlock voice-matched content.
-
-Then proceed normally — do not block content creation.
 
 Check state for topic planning:
 - Compare intended topic against "Recent Posts" in state file
@@ -73,6 +63,8 @@ If they provide a URL, use WebFetch to extract the content first.
 
 Read `references/thought-leadership-angles.md` for the 8 universal angles.
 
+**Industry-specific angles:** If `config/user-profile.local.md` exists and has an `industry` field, check the "Industry Angle Variants" section in `thought-leadership-angles.md` for the matching industry table. Use the industry-specific starter questions and example hooks to generate more targeted angle suggestions.
+
 Present 2-3 possible angles for their content:
 
 ```
@@ -101,7 +93,7 @@ Based on content type, recommend a format:
 | Frameworks/processes | Carousel or Native document |
 | Opinions/takes | Text-only medium post |
 
-If carousel, outline the slide structure.
+If carousel is the best format, recommend: "This topic works great as a carousel. Run `/linkedin:carousel` for the full slide-by-slide generator with 5 proven templates."
 
 ## Step 4: Structure and Write
 

plugins/linkedin-thought-leadership/commands/quick.md

@@ -27,17 +27,6 @@ Read `skills/linkedin-thought-leadership/SKILL.md` for:
 - Core expertise areas (for topical alignment)
 - Phrases they commonly use
 
-Read `config/user-profile.local.md` (if it exists) for expertise areas and audience.
-
-### Readiness Check
-
-If `config/user-profile.local.md` doesn't exist OR `assets/voice-samples/authentic-voice-samples.md` contains `[Your Name]` in the title line, show this non-blocking notice:
-
-> This plugin isn't personalized yet. Content will use generic best practices.
-> Run `/linkedin:setup` after this session to unlock voice-matched content.
-
-Then proceed normally — do not block content creation.
-
 Read `assets/quick-post-resources.md` for:
 - Hooks bank
 - CTAs bank

plugins/linkedin-thought-leadership/commands/react.md

@@ -26,7 +26,7 @@ First, load persistent state and personalization:
 - Read `assets/voice-samples/authentic-voice-samples.md` for voice profile
 - Check recent posts to avoid topic repetition within 7 days
 
-## Step 1: Get the URL
+## Step 1: Get URL(s)
 
 If the user hasn't provided a URL, ask for one. Accept:
 - News articles
@@ -36,6 +36,17 @@ If the user hasn't provided a URL, ask for one. Accept:
 - Company announcements
 - Social media threads
 
+**Multiple URLs:** If the user provides 2-3 URLs, or if you detect multiple links, use AskUserQuestion:
+
+```
+I see multiple URLs. Would you like to:
+1. React to a single article (pick the most interesting one)
+2. Compare and contrast 2-3 articles into one post
+```
+
+If option 2 → jump to **Comparison Path** (Step 1b below).
+If option 1 or single URL → continue to Step 2.
+
 ## Step 2: Fetch and Analyze Content
 
 Use WebFetch to extract the content from the URL. Ask WebFetch to extract:
@@ -143,6 +154,96 @@ After the post is finalized, update `~/.claude/linkedin-thought-leadership.local
 - Update `longest_streak` if current exceeds it
 - Add entry to "## Recent Posts": [YYYY-MM-DD] "Hook text..." (char count) - topic
 
+---
+
+## Comparison Path (Multi-URL)
+
+When the user wants to compare 2-3 articles into one post.
+
+### Step 1b: Collect URLs
+
+Collect 2-3 URLs. Minimum 2, maximum 3. If the user provided them already, confirm the list.
+
+### Step 2b: Fetch All Sources
+
+Use WebFetch on each URL. For each, extract:
+- **Title** and author/source
+- **Key claims** (3-5 bullet points)
+- **Stance/argument** — what position does the author take?
+- **Data points** — any statistics or evidence cited
+
+### Step 3b: Synthesis Analysis
+
+Analyze across all sources:
+
+| Dimension | Analysis |
+|-----------|----------|
+| **Common ground** | Where do the sources agree? |
+| **Tension points** | Where do they disagree or contradict? |
+| **Blind spots** | What are ALL of them missing? |
+| **Your unique angle** | Given your expertise, what perspective do you add? |
+
+### Step 4b: Choose Comparison Angle
+
+Present 3 angles via AskUserQuestion:
+
+1. **Synthesis** — "These perspectives seem opposed, but the truth is more nuanced. Here's how I connect them."
+2. **Contrarian to all** — "Both/all articles miss the real issue. Here's what actually matters."
+3. **Pattern analysis** — "The fact that [N] experts are all writing about [X] tells us something about [Y]."
+
+### Step 5b: Generate Comparison Draft
+
+Structure:
+
+**Hook (110-140 chars):** Your synthesized perspective — NOT "I read 3 articles about..." Avoid mentioning the number of sources in the hook.
+
+**The conversation (1-2 sentences):** Briefly describe the debate or trend ("There's a growing conversation about [X]. Perspectives range from [A] to [B].")
+
+**Your lens (main body):**
+- What the synthesis reveals that individual pieces miss
+- Concrete example from your experience that connects the dots
+- Where you agree and where you push back
+
+**Implication (1-2 sentences):** What this convergence/divergence means for the audience.
+
+**CTA:** Question that invites people to take a side or share their own synthesis.
+
+### Critical Rules (comparison-specific):
+- **NO URLs in post body** — all links go in first comment
+- Post must stand alone without reading any of the sources
+- Don't summarize each article — synthesize across them
+- Your perspective is the star, not the articles
+- Character target: 1,200-1,800 chars
+
+### Step 6b: Quality Check
+
+Same as Step 6, plus:
+- [ ] Post is a synthesis, not a summary of each article
+- [ ] Hook doesn't mention number of sources read
+- [ ] Each source is credited in the first comment, not the post
+
+### Step 7b: Present Draft
+
+Show:
+1. The main draft with character count
+2. 2 alternative hooks
+3. Suggested first comment with ALL URLs:
+   ```
+   Sources referenced:
+   1. "[Title]" by [Author] — [URL]
+   2. "[Title]" by [Author] — [URL]
+   3. "[Title]" by [Author] — [URL] (if applicable)
+   ```
+4. Recommended posting time
+
+Offer same refinement options as Step 7.
+
+### Step 8b: State Update
+
+Same as Step 8 — update state file with topic, increment counts, etc.
+
+---
+
 ## Reference Files
 
 - `assets/voice-samples/authentic-voice-samples.md` — Voice matching

plugins/linkedin-thought-leadership/commands/report.md

@@ -37,18 +37,32 @@ You need to import your LinkedIn analytics first:
 1. Run `/linkedin:import` to import CSV data
 2. Then come back to generate reports
 
-## Step 2: Determine Week to Report On
+## Step 2: Choose Report Type
-
-If no week specified, default to current week or most recent available data.
 
 **Ask the user** using AskUserQuestion:
 
+```
+What kind of report would you like?
+
+1. Weekly report (default) — performance for a specific ISO week
+2. Monthly report — month summary with month-over-month comparison
+3. Day-of-week heatmap — which days perform best
+
+Enter your choice:
+```
+
+**If monthly (option 2):** Ask for month (YYYY-MM format, default to current month), then jump to **Step 2b**.
+**If heatmap (option 3):** Run the heatmap CLI command and jump to **Step 6c**.
+**If weekly (option 1 or default):** Continue below.
+
+### Weekly: Determine Week
+
 ```
 Which week would you like a report for?
 
 Available options:
-- "current" or "this week" - Current ISO week (2026-W05)
+- "current" or "this week" - Current ISO week
-- "last week" - Previous ISO week (2026-W04)
+- "last week" - Previous ISO week
 - Specific week: "2026-W03", "2025-W52", etc.
 - "latest" - Most recent week with data
 
@@ -62,6 +76,26 @@ To get current ISO week:
 date +%Y-W%V
 ```
 
+### Step 2b: Monthly Report
+
+If the user chose monthly:
+
+```bash
+ANALYTICS_ROOT="${CLAUDE_PLUGIN_ROOT}/assets/analytics" node --import tsx "${CLAUDE_PLUGIN_ROOT}/scripts/analytics/src/cli.ts" report --month <YYYY-MM>
+```
+
+Read the generated JSON from `assets/analytics/monthly-reports/<YYYY-MM>.json`. Present the monthly summary with MoM comparison deltas, weekly breakdown, and top performers. Then jump to Step 7 for deep-dive options.
+
+### Step 2c: Heatmap
+
+If the user chose heatmap:
+
+```bash
+ANALYTICS_ROOT="${CLAUDE_PLUGIN_ROOT}/assets/analytics" node --import tsx "${CLAUDE_PLUGIN_ROOT}/scripts/analytics/src/cli.ts" heatmap
+```
+
+Present the day-of-week matrix and best-day findings. Then jump to Step 7 for deep-dive options.
+
 ## Step 3: Run Report Generation
 
 Execute the report CLI command:

plugins/linkedin-thought-leadership/hooks/prompts/post-creation-automation.md

@@ -16,14 +16,7 @@ Based on the day of the week, suggest the next optimal posting window:
 - Weekend: 10-11 AM CET (lower reach but less competition)
 
 **3. 5x5x5 Engagement Reminder**
-Remind the user about the 5x5x5 engagement ritual:
+Remind: 'Before posting, spend 15-20 minutes on 5x5x5 pre-engagement: find 5 people with overlapping audiences, comment thoughtfully on their recent posts.'
-
-> **5x5x5 Engagement Ritual** (15-20 min before AND in the first hour after posting):
-> - **5 comments** — find 5 people with overlapping audiences and leave thoughtful comments on their recent posts
-> - **5 connection requests** — send personalized requests to people who engaged with your niche today
-> - **5 replies** — reply to every comment on YOUR post within the first hour
->
-> This signals active participation to LinkedIn's algorithm and boosts your post's initial distribution.
 
 **4. Content Logging**
 Note: The post topic and hook should be logged to the state file when the session ends (handled by Stop hook).

plugins/linkedin-thought-leadership/hooks/prompts/state-update-reminder.md

@@ -38,19 +38,20 @@ If a scheduled post was published during this session:
 
 Provide reminders naturally based on what was done in the session. If no LinkedIn content was created, skip the reminders and just ensure state is consistent.
 
-**4. Voice Sample Extraction** (if a post was created)
+**4. Voice Sample Collection** (if a post was created)
 
-If a LinkedIn post was created or finalized in this session, consider extracting the hook line as a voice sample:
+If a LinkedIn post was created or finalized in this session, save the full post text as a voice sample:
 
-- Read the hook line from the post that was just created
+- Read the full post text from the draft that was just created
 - Check if `assets/voice-samples/authentic-voice-samples.md` exists
-- If it does, suggest appending a new entry to the "## Update Log" section at the bottom:
+- Append the full post to the `## Collected Post Samples` section:
   ```
-  - [YYYY-MM-DD]: "[Hook text]" — [post type] (extracted from session post)
+  ### [YYYY-MM-DD] — [post type] ([char count] chars)
+  [Full post text exactly as written]
   ```
-- **Ask the user for approval before writing.** Say: "Would you like me to save this hook as a voice sample for future reference?"
+- **Ask the user for confirmation** before writing: "I'll save this post as a voice sample for drift detection. OK?"
-- Only write if the user approves
+- This builds the voice sample library that enables automatic drift scoring (needs 5+ samples for reliable scoring)
-- This passively grows the voice profile over time, improving personalization score
+- The more samples collected, the more accurate the voice-trainer's drift detection becomes
 
 **5. Content History Log** (if a post was created)
 

plugins/linkedin-thought-leadership/hooks/prompts/voice-guardian.md

@@ -1,6 +1,7 @@
-VOICE GUARDIAN — AI AUTHENTICITY CHECK: If the file being written/edited is LinkedIn content (post draft, article, or content file — NOT config, state, scripts, docs), check for AI-sounding patterns:
+VOICE GUARDIAN — DRIFT SCORING & AI AUTHENTICITY CHECK: If the file being written/edited is LinkedIn content (post draft, article, or content file — NOT config, state, scripts, docs), perform both AI detection and voice drift scoring:
+
+## 1. AI Pattern Detection
 
-**AI Pattern Detection:**
 Scan for these common AI writing patterns:
 - Generic openings: 'In today's rapidly evolving...', 'As we navigate...', 'In the ever-changing landscape...'
 - Filler phrases: 'It's worth noting that', 'It goes without saying', 'At the end of the day'
@@ -10,13 +11,42 @@ Scan for these common AI writing patterns:
 - Hedging language: 'It could be argued', 'One might say', 'Perhaps'
 - Perfect structure: Every paragraph exactly the same length
 
-**Authenticity Score:**
 If 3+ AI patterns detected, flag: 'Voice Guardian Alert: This content scores below authenticity threshold. AI patterns found: [list specific patterns]. Suggested fixes: [specific rewrites using natural language].'
 
-**Voice Matching:**
+## 2. Six-Dimension Voice Drift Scoring
-If voice samples exist at `${CLAUDE_PLUGIN_ROOT}/assets/voice-samples/`, compare the writing style against the user's authentic voice patterns. Flag deviations.
+
+Read the voice profile and collected post samples from `${CLAUDE_PLUGIN_ROOT}/assets/voice-samples/authentic-voice-samples.md`.
+
+Score the draft against these 6 dimensions (0 = perfect match, 1 = minor drift per dimension):
+
+| Dimension | What to Compare |
+|-----------|----------------|
+| **Sentence structure** | Average length, complexity, use of fragments vs. compound sentences |
+| **Word choice** | Vocabulary level, preferred/avoided words from voice profile |
+| **Opening patterns** | Hook style — does it match the user's signature openers? |
+| **Storytelling** | Anecdote usage, narrative arc, concrete vs. abstract |
+| **Tone markers** | Humor, directness, formality level, empathy signals |
+| **Formatting** | Paragraph length, whitespace, emoji usage, punctuation habits |
+
+**Sum the 6 scores (0-6 total) and output a verdict:**
+
+| Score | Verdict | Action |
+|-------|---------|--------|
+| 0-1 | AUTHENTIC | No changes needed |
+| 2-3 | CAUTION | Flag specific dimensions that drifted, suggest fixes |
+| 4-5 | ALERT | Significant drift — list all deviating dimensions with rewrites |
+| 6 | REWRITE | Content doesn't sound like the user — recommend starting over |
+
+**Confidence gate:** If `## Collected Post Samples` has fewer than 5 posts, output: "Voice drift: LOW CONFIDENCE (X/5 samples). Scoring based on voice profile only." and score only against the profile description (dimensions 1-2 and 4-6), skipping opening patterns (dimension 3) which needs real samples.
+
+**Output format (always include at end of system message):**
+```
+Voice Drift: [VERDICT] ([score]/6) [confidence: HIGH/LOW]
+[If CAUTION+: list dimensions that scored 1 with brief fix suggestion]
+```
+
+## 3. Humanization Tips (for CAUTION or higher)
 
-**Humanization Tips:**
 - Add specific personal anecdotes or observations
 - Use conversational contractions (I've, don't, it's)
 - Include imperfect/real-world examples

plugins/linkedin-thought-leadership/hooks/scripts/__tests__/week-rollover.test.mjs

@@ -0,0 +1,102 @@
+import { describe, test } from 'node:test';
+import assert from 'node:assert/strict';
+import { applyWeekRollover } from '../week-rollover.mjs';
+
+const SAMPLE_STATE = `---
+last_post_date: "2026-04-05"
+first_post_date: "2026-01-15"
+last_post_topic: "AI strategy"
+posts_this_week: 3
+weekly_goal: 3
+current_streak: 5
+longest_streak: 12
+current_week: "2026-W14"
+last_import_date: "2026-04-01"
+follower_count: 850
+follower_target: 10000
+target_date: "2026-12-31"
+---
+
+## Recent Posts
+- 2026-04-05: AI strategy post
+`;
+
+describe('applyWeekRollover', () => {
+  test('resets posts_this_week to 0 on week change', () => {
+    const result = applyWeekRollover(SAMPLE_STATE, '2026-W14', '2026-W15');
+    assert.notEqual(result, null);
+    assert.match(result.content, /^posts_this_week: 0$/m);
+  });
+
+  test('updates current_week to new week', () => {
+    const result = applyWeekRollover(SAMPLE_STATE, '2026-W14', '2026-W15');
+    assert.notEqual(result, null);
+    assert.match(result.content, /^current_week: "2026-W15"$/m);
+  });
+
+  test('returns descriptive message on rollover', () => {
+    const result = applyWeekRollover(SAMPLE_STATE, '2026-W14', '2026-W15');
+    assert.notEqual(result, null);
+    assert.ok(result.message.includes('2026-W15'));
+    assert.ok(result.message.includes('2026-W14'));
+  });
+
+  test('returns null when week matches (no change needed)', () => {
+    const result = applyWeekRollover(SAMPLE_STATE, '2026-W14', '2026-W14');
+    assert.equal(result, null);
+  });
+
+  test('preserves all other YAML fields unchanged', () => {
+    const result = applyWeekRollover(SAMPLE_STATE, '2026-W14', '2026-W15');
+    assert.notEqual(result, null);
+    assert.match(result.content, /^last_post_date: "2026-04-05"$/m);
+    assert.match(result.content, /^current_streak: 5$/m);
+    assert.match(result.content, /^weekly_goal: 3$/m);
+    assert.match(result.content, /^follower_count: 850$/m);
+  });
+
+  test('preserves markdown body after frontmatter', () => {
+    const result = applyWeekRollover(SAMPLE_STATE, '2026-W14', '2026-W15');
+    assert.notEqual(result, null);
+    assert.ok(result.content.includes('## Recent Posts'));
+    assert.ok(result.content.includes('AI strategy post'));
+  });
+
+  test('initializes current_week when empty without resetting posts', () => {
+    const stateWithEmptyWeek = SAMPLE_STATE.replace(
+      'current_week: "2026-W14"',
+      'current_week: ""'
+    );
+    const result = applyWeekRollover(stateWithEmptyWeek, '', '2026-W15');
+    assert.notEqual(result, null);
+    assert.match(result.content, /^current_week: "2026-W15"$/m);
+    // posts_this_week should NOT be reset (user may have manually tracked)
+    assert.match(result.content, /^posts_this_week: 3$/m);
+  });
+
+  test('returns null when actualWeek is empty', () => {
+    const result = applyWeekRollover(SAMPLE_STATE, '2026-W14', '');
+    assert.equal(result, null);
+  });
+
+  test('returns null when actualWeek is null/undefined', () => {
+    assert.equal(applyWeekRollover(SAMPLE_STATE, '2026-W14', null), null);
+    assert.equal(applyWeekRollover(SAMPLE_STATE, '2026-W14', undefined), null);
+  });
+
+  test('handles year boundary rollover (W52 → W01)', () => {
+    const yearEndState = SAMPLE_STATE.replace('2026-W14', '2025-W52');
+    const result = applyWeekRollover(yearEndState, '2025-W52', '2026-W01');
+    assert.notEqual(result, null);
+    assert.match(result.content, /^posts_this_week: 0$/m);
+    assert.match(result.content, /^current_week: "2026-W01"$/m);
+  });
+
+  test('handles posts_this_week already at 0', () => {
+    const zeroPostsState = SAMPLE_STATE.replace('posts_this_week: 3', 'posts_this_week: 0');
+    const result = applyWeekRollover(zeroPostsState, '2026-W14', '2026-W15');
+    assert.notEqual(result, null);
+    assert.match(result.content, /^posts_this_week: 0$/m);
+    assert.match(result.content, /^current_week: "2026-W15"$/m);
+  });
+});

plugins/linkedin-thought-leadership/hooks/scripts/session-start.mjs

@@ -7,6 +7,7 @@ import { join, dirname } from 'node:path';
 import { fileURLToPath } from 'node:url';
 import { calculateScore } from './personalization-score.mjs';
 import { queueToday, queueOverdue, queueUpcoming } from './queue-manager.mjs';
+import { applyWeekRollover } from './week-rollover.mjs';
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const PLUGIN_ROOT = join(__dirname, '..', '..');
@@ -135,11 +136,17 @@ if (existsSync(STATE_FILE)) {
     }
   }
 
-  // Week rollover check
+  // Week rollover — auto-reset posts_this_week on week change
   const actualWeek = isoWeek();
   let weekResetNote = '';
-  if (currentWeek && currentWeek !== actualWeek) {
+  try {
-    weekResetNote = `Note: Week has changed from ${currentWeek} to ${actualWeek}. posts_this_week should be reset to 0.`;
+    const rollover = applyWeekRollover(stateContent, currentWeek, actualWeek);
+    if (rollover) {
+      writeFileSync(STATE_FILE, rollover.content, 'utf-8');
+      weekResetNote = rollover.message;
+    }
+  } catch (err) {
+    weekResetNote = `Warning: Week rollover failed (${err.message}). Manual reset may be needed.`;
   }
 
   // Build status line
@@ -253,9 +260,7 @@ if (existsSync(STATE_FILE)) {
   }
 
   // Personalization score check
-  if (pScore !== null && pScore === 0) {
+  if (pScore !== null && pScore < 50) {
-    context += '## Quick Win\\nPersonalization: 0%. Run /linkedin:setup (15 min) to unlock voice-matched, audience-specific content.\\n\\n';
-  } else if (pScore !== null && pScore < 50) {
     reminders += `- Personalization score is ${pScore}%. Run /linkedin:setup to improve content quality with your real voice, case studies, and audience data.\\n`;
   }
 
@@ -369,13 +374,8 @@ if (existsSync(STATE_FILE)) {
     content = content.replace(/^current_week: .*/m, `current_week: "${actualWeek}"`);
     writeFileSync(STATE_FILE, content);
     context = `LinkedIn state file auto-initialized from template at ${STATE_FILE}.\\n`;
-    context += `Current ISO week set to ${actualWeek}.\\n\\n`;
+    context += `Current ISO week set to ${actualWeek}.\\n`;
-    context += '## Welcome to LinkedIn Thought Leadership\\n\\n';
+    context += 'Edit the file to set your expertise_areas and weekly_goal.\\n';
-    context += 'Your state file has been initialized. Here is how to get started:\\n\\n';
-    context += '1. Run /linkedin:profile — Optimize your LinkedIn profile for 360Brew (critical before first post)\\n';
-    context += '2. Run /linkedin:setup — Personalize with your voice, case studies, and audience data\\n';
-    context += '3. Run /linkedin:first-post — Create your first post in under 10 minutes\\n\\n';
-    context += 'Your personalization score is 0%. Content quality improves as you fill in your profile.\\n';
   } else {
     context = `No LinkedIn state file found at ${STATE_FILE} and template missing.\\n`;
     context += `Expected template at: ${templateFile}\\n`;

plugins/linkedin-thought-leadership/hooks/scripts/week-rollover.mjs

@@ -0,0 +1,49 @@
+// Pure function for week-rollover logic.
+// Exported separately for testability.
+
+/**
+ * Apply week rollover to state file content.
+ * Returns updated content string if rollover was applied, null otherwise.
+ *
+ * @param {string} stateContent - Full state file content (with YAML frontmatter)
+ * @param {string} currentWeek - Week value from state file (e.g. "2026-W14")
+ * @param {string} actualWeek - Computed current ISO week (e.g. "2026-W15")
+ * @returns {{ content: string, message: string } | null}
+ */
+export function applyWeekRollover(stateContent, currentWeek, actualWeek) {
+  if (!actualWeek) return null;
+
+  // Case 1: current_week is empty — initialize without resetting posts
+  if (!currentWeek) {
+    const updated = stateContent.replace(
+      /^current_week: .*/m,
+      `current_week: "${actualWeek}"`
+    );
+    if (updated === stateContent) return null;
+    return {
+      content: updated,
+      message: `Initialized current_week to ${actualWeek}.`
+    };
+  }
+
+  // Case 2: week matches — no action needed
+  if (currentWeek === actualWeek) return null;
+
+  // Case 3: week changed — reset posts_this_week and update current_week
+  let updated = stateContent;
+  updated = updated.replace(
+    /^posts_this_week: .*/m,
+    'posts_this_week: 0'
+  );
+  updated = updated.replace(
+    /^current_week: .*/m,
+    `current_week: "${actualWeek}"`
+  );
+
+  if (updated === stateContent) return null;
+
+  return {
+    content: updated,
+    message: `Auto-reset: posts_this_week → 0 for new week ${actualWeek} (was ${currentWeek}).`
+  };
+}

plugins/linkedin-thought-leadership/references/thought-leadership-angles.md

@@ -122,6 +122,88 @@ These angles work across all industries because they're about **types of thinkin
 - **Education:** Personal Lesson + Human Story
 - **Consulting:** Pattern Recognition + Practical Breakdown
 
+## Industry Angle Variants
+
+Concrete starter questions and example hooks per industry. When the user's industry is known (from `config/user-profile.local.md`), surface the relevant table during angle selection.
+
+### Tech / Software / AI
+
+| Angle | Starter Question | Example Hook |
+|-------|-----------------|--------------|
+| Contrarian | "What does everyone assume about [tech trend] that data disproves?" | "Everyone says AI will replace developers. Our team shipped 40% more code WITH AI — and hired 3 more engineers." |
+| Pattern Recognition | "What pattern across AI/cloud/DevOps haven't others connected?" | "I've noticed every team that fails at AI adoption makes the same infrastructure mistake first." |
+| Uncomfortable Truth | "What is the industry avoiding saying about [tool/trend]?" | "We spent 6 months fine-tuning an LLM. A prompt template outperformed it in 2 hours." |
+| Future Implication | "If [current trend] continues, what changes in 2-3 years?" | "If AI coding assistants keep improving at this rate, the most valuable developer skill in 2028 won't be coding." |
+| Personal Lesson | "What did your last failed project teach you about [topic]?" | "Our AI pilot looked perfect in the demo. Here's what happened when real users touched it." |
+| Reframe | "What common tech term means something different than people think?" | "We call it 'technical debt.' I call it 'decisions that were right then and wrong now.'" |
+| Practical Breakdown | "What complex concept can you make actionable in 5 steps?" | "Everyone talks about RAG. Here's the 4-step checklist I use before building any retrieval system." |
+| Human Story | "What moment with a colleague or user changed your perspective?" | "Our senior architect said 'I don't understand this AI stuff' in a meeting. What happened next changed our entire approach." |
+
+### Healthcare / Life Sciences
+
+| Angle | Starter Question | Example Hook |
+|-------|-----------------|--------------|
+| Contrarian | "What healthcare 'best practice' actually slows patient outcomes?" | "We digitized all our patient records. Patient satisfaction dropped. Here's why paper had one advantage we overlooked." |
+| Pattern Recognition | "What pattern connects clinical and operational challenges?" | "I've worked with 12 hospitals this year. The ones with the best patient outcomes all share one non-clinical habit." |
+| Uncomfortable Truth | "What is healthcare leadership not willing to discuss openly?" | "The biggest barrier to healthcare AI isn't regulation. It's that clinicians don't trust their own data." |
+| Future Implication | "If [health tech trend] succeeds, what changes for patients?" | "If ambient clinical documentation works as promised, the doctor-patient relationship fundamentally changes." |
+| Personal Lesson | "What did a patient interaction teach you about [system/process]?" | "A patient told me: 'Your portal has 47 clicks to book an appointment.' That sentence restructured our entire digital strategy." |
+| Reframe | "What healthcare metric measures the wrong thing?" | "We measure 'patient throughput.' What if we measured 'patient understanding' instead?" |
+| Practical Breakdown | "What regulatory/compliance challenge can you simplify?" | "HIPAA compliance for AI tools sounds impossible. Here are the 3 questions that solve 80% of the uncertainty." |
+| Human Story | "What patient story illustrates a systemic issue?" | "A nurse spent 4 hours on documentation for every 1 hour of patient care. She quit. Her exit interview should be mandatory reading for every CIO." |
+
+### Finance / Banking / Insurance
+
+| Angle | Starter Question | Example Hook |
+|-------|-----------------|--------------|
+| Contrarian | "What financial 'innovation' is actually recycled risk?" | "Everyone's excited about embedded finance. The banks that remember 2008 are asking different questions." |
+| Pattern Recognition | "What pattern connects fintech disruption and traditional banking?" | "I've noticed every fintech that struggles at scale hits the same wall — the one banks solved 30 years ago." |
+| Uncomfortable Truth | "What is the industry avoiding about [regulation/risk/AI]?" | "Banks are spending millions on AI fraud detection. The fraud teams say the biggest vulnerability is still a phone call." |
+| Future Implication | "If [regulatory change] passes, what does banking look like?" | "If open banking delivers on its promise, the most valuable asset in finance won't be capital — it'll be consent." |
+| Personal Lesson | "What did a risk event teach you that no framework captures?" | "We built a perfect risk model. It missed the one variable that mattered: human panic." |
+| Reframe | "What financial concept needs a new definition?" | "We call it 'customer acquisition cost.' But in financial services, the real cost is trust — and trust doesn't have a line item." |
+| Practical Breakdown | "What compliance requirement can you make less painful?" | "RegTech sounds complex. Here's the 3-layer approach that cut our compliance reporting time by 60%." |
+| Human Story | "What client interaction revealed a blind spot?" | "A small business owner asked me: 'Why does your app need to know my mother's maiden name to send an invoice?' Fair point." |
+
+### Public Sector / Government
+
+| Angle | Starter Question | Example Hook |
+|-------|-----------------|--------------|
+| Contrarian | "What public sector 'modernization' approach actually creates more bureaucracy?" | "We 'digitized' our forms by turning PDFs into web forms. Citizens still needed to visit the office. That's not digital transformation." |
+| Pattern Recognition | "What pattern connects successful government IT projects?" | "I've studied 20 public sector IT projects. The 5 that succeeded all broke the same procurement rule." |
+| Uncomfortable Truth | "What is the sector avoiding about [digital transformation/AI/procurement]?" | "The biggest obstacle to government AI isn't budget or policy. It's that we measure success by project completion, not citizen outcome." |
+| Future Implication | "If [policy/tech] is adopted, what changes for citizens?" | "If government agencies actually share data across departments, we can stop asking citizens to prove who they are 47 times." |
+| Personal Lesson | "What did a failed initiative teach you about public sector change?" | "We launched a citizen portal. 6 months later, the call center was busier than ever. The lesson wasn't about technology." |
+| Reframe | "What government process looks different from the citizen's perspective?" | "We call it 'case processing.' Citizens call it 'waiting to hear if I can keep my home.'" |
+| Practical Breakdown | "What complex regulation/process can you make tangible?" | "Government procurement for AI services sounds impossible. Here are 3 contract clauses that unlock 80% of the innovation." |
+| Human Story | "What citizen interaction changed how you think about service delivery?" | "A retired teacher spent 3 hours navigating our website for a pension form. She said: 'I taught 2,000 students to learn. Your website taught me to give up.'" |
+
+### Education / EdTech
+
+| Angle | Starter Question | Example Hook |
+|-------|-----------------|--------------|
+| Contrarian | "What education 'innovation' actually hurts learning outcomes?" | "We gave every student a laptop. Test scores didn't change. Classroom engagement dropped. Here's what we missed." |
+| Pattern Recognition | "What do successful learning programs have in common?" | "I've observed 15 AI-in-education pilots. The ones students actually use all share one design principle." |
+| Uncomfortable Truth | "What is the sector avoiding about [AI/assessment/equity]?" | "Personalized learning algorithms optimize for engagement. But engagement and learning aren't the same thing." |
+| Future Implication | "If [AI/policy trend] continues, how does education change?" | "If AI tutors become genuinely good, the teacher's most valuable skill won't be content delivery — it'll be asking the right question at the right moment." |
+| Personal Lesson | "What did a student/classroom experience teach you?" | "I watched a student use ChatGPT to write an essay, then spent 2 hours explaining it to a classmate. That's when I realized the assignment was wrong, not the student." |
+| Reframe | "What education metric measures the wrong thing?" | "We measure 'time on task.' What if the best indicator of learning is how quickly a student can teach it to someone else?" |
+| Practical Breakdown | "What complex pedagogical concept can you make actionable?" | "Bloom's Taxonomy is in every education textbook. Here's how I actually use it to design a single lesson in 15 minutes." |
+| Human Story | "What student moment illustrates a bigger truth?" | "A 10-year-old told me: 'Why do I have to learn this if I can just ask AI?' My answer surprised both of us." |
+
+### Consulting / Professional Services
+
+| Angle | Starter Question | Example Hook |
+|-------|-----------------|--------------|
+| Contrarian | "What consulting 'framework' actually prevents insight?" | "The best strategy I ever delivered had zero frameworks. It had one question the CEO couldn't answer." |
+| Pattern Recognition | "What pattern connects client problems across industries?" | "I've worked with 30 organizations on AI strategy. The ones that succeed all start with the same non-technical conversation." |
+| Uncomfortable Truth | "What is the industry avoiding about [value delivery/pricing/AI]?" | "Most consulting engagements solve the stated problem. The real problem — the one nobody mentioned in the RFP — stays unsolved." |
+| Future Implication | "If [AI/market trend] continues, how does consulting change?" | "If AI can generate a strategy deck in 10 minutes, the consulting industry needs to answer one question: what are we actually selling?" |
+| Personal Lesson | "What project failure taught you something the methodology didn't?" | "I delivered a perfect change management plan. The client implemented 10% of it. My methodology was right. My assumption about people was wrong." |
+| Reframe | "What consulting term means something different than clients think?" | "Clients ask for 'digital transformation.' What they actually need is 'permission to stop doing things that don't work.'" |
+| Practical Breakdown | "What complex client challenge can you simplify?" | "AI readiness assessments take 6 weeks and cost €200K. Here are the 5 questions that tell you 80% of what you need in one meeting." |
+| Human Story | "What client moment changed your consulting approach?" | "A CTO told me: 'Your recommendation is brilliant. My team will ignore it by Thursday.' That conversation changed how I deliver every project." |
+
 ## Red Flags (Avoid These)
 
 - **Echo chamber:** Repeating what everyone already says

plugins/linkedin-thought-leadership/scripts/analytics/src/cli.ts

@@ -8,6 +8,8 @@ import {
 import { detectAlerts } from "./utils/alerts.js";
 import { mean, standardDeviation } from "./utils/stats.js";
 import { generateWeeklyReport, getCurrentISOWeek } from "./reports/weekly.js";
+import { generateHeatmap } from "./reports/heatmap.js";
+import { generateMonthlyReport } from "./reports/monthly.js";
 import { join } from "node:path";
 import { existsSync } from "node:fs";
 import type { PostMetrics } from "./models/types.js";
@@ -27,7 +29,9 @@ LinkedIn Analytics CLI
 Usage:
   node build/cli.js import <filename>           Import a CSV export
   node build/cli.js report [--week W]            Generate weekly report
+  node build/cli.js report --month YYYY-MM       Generate monthly report with MoM comparison
   node build/cli.js trends [--period P] [--metric M]  Show trends and alerts
+  node build/cli.js heatmap                           Day-of-week performance matrix
 
 Options:
   --week W       ISO week (e.g., 2026-W05), defaults to current week
@@ -95,6 +99,11 @@ async function handleImport(root: string, args: string[]) {
 }
 
 async function handleReport(root: string, args: string[]) {
+  const monthOption = parseOption(args, "--month");
+  if (monthOption) {
+    return handleMonthlyReport(root, monthOption);
+  }
+
   const weekOption = parseOption(args, "--week");
   const week = weekOption || getCurrentISOWeek();
 
@@ -285,6 +294,130 @@ async function handleTrends(root: string, args: string[]) {
   }
 }
 
+async function handleMonthlyReport(root: string, month: string) {
+  console.log(`Generating monthly report for ${month}...`);
+
+  try {
+    const report = generateMonthlyReport(root, month);
+
+    console.log("\nMonthly Report");
+    console.log("═════════════════════════════════════");
+    console.log(`Month:           ${report.month}`);
+    console.log(`Generated at:    ${new Date(report.generatedAt).toLocaleString()}`);
+    console.log();
+
+    console.log("Summary");
+    console.log("─────────────────────────────────────");
+    const s = report.summary;
+    const fmtDelta = (val: number | null, suffix = "%") =>
+      val !== null ? ` (${val > 0 ? "+" : ""}${val}${suffix})` : "";
+
+    console.log(`Posts:               ${s.totalPosts}${fmtDelta(report.trends.percentChange.postCount)}`);
+    console.log(`Impressions:         ${s.totalImpressions.toLocaleString()}${fmtDelta(report.trends.percentChange.impressions)}`);
+    console.log(`Avg per post:        ${s.avgImpressionsPerPost.toLocaleString()}`);
+    console.log(`Avg engagement:      ${s.avgEngagementRate.toFixed(2)}%${fmtDelta(report.trends.percentChange.engagement)}`);
+    console.log(`Reactions:           ${s.totalReactions.toLocaleString()}`);
+    console.log(`Comments:            ${s.totalComments.toLocaleString()}`);
+    console.log(`Shares:              ${s.totalShares.toLocaleString()}`);
+    console.log(`Clicks:              ${s.totalClicks.toLocaleString()}`);
+    console.log();
+
+    if (report.byWeek.length > 0) {
+      console.log("Week Breakdown");
+      console.log("─────────────────────────────────────");
+      for (const w of report.byWeek) {
+        console.log(`${w.week}: ${w.postCount} posts | ${w.avgImpressions.toLocaleString()} avg impr | ${w.avgEngagementRate.toFixed(1)}% eng`);
+      }
+      console.log();
+    }
+
+    if (report.topPerformers.length > 0) {
+      console.log("Top Performers");
+      console.log("─────────────────────────────────────");
+      for (const post of report.topPerformers.slice(0, 5)) {
+        const title = post.title.length > 50 ? post.title.substring(0, 47) + "..." : post.title;
+        console.log(`• ${title}`);
+        console.log(`  ${post.metrics.impressions.toLocaleString()} impressions | ${post.metrics.engagementRate.toFixed(2)}% eng | ${post.publishedDate}`);
+      }
+      console.log();
+    }
+
+    if (report.trends.comparedTo) {
+      console.log(`Compared to:         ${report.trends.comparedTo}`);
+    } else {
+      console.log("No previous month data for comparison.");
+    }
+    console.log();
+
+    if (report.alerts.length > 0) {
+      console.log("Alerts");
+      console.log("─────────────────────────────────────");
+      for (const alert of report.alerts) {
+        const icon = alert.severity === "critical" ? "🔴" : alert.severity === "warning" ? "⚠️" : "ℹ️";
+        console.log(`${icon} [${alert.severity.toUpperCase()}] ${alert.message}`);
+      }
+      console.log();
+    }
+
+    console.log(`Report saved to: monthly-reports/${month}.json`);
+  } catch (err) {
+    console.error(`Error generating monthly report: ${err instanceof Error ? err.message : String(err)}`);
+    process.exit(1);
+  }
+}
+
+async function handleHeatmap(root: string) {
+  console.log("Generating day-of-week heatmap...");
+
+  try {
+    const allPosts = loadAllPosts(root);
+
+    if (allPosts.length === 0) {
+      console.error("Error: No posts found. Import some data first.");
+      process.exit(1);
+    }
+
+    const report = generateHeatmap(allPosts);
+
+    console.log("\nDay-of-Week Performance Heatmap");
+    console.log("═════════════════════════════════════");
+    console.log(`Posts analyzed:  ${report.postsAnalyzed}`);
+    console.log(`Date range:      ${report.dateRange.from} to ${report.dateRange.to}`);
+    console.log();
+
+    // Print table header
+    const days = report.byDayOfWeek.map(d => d.dayName.slice(0, 3).padStart(7));
+    console.log(`         ${days.join("")}`);
+    console.log(`         ${"───────".repeat(7)}`);
+
+    // Posts row
+    const postCounts = report.byDayOfWeek.map(d => String(d.postCount).padStart(7));
+    console.log(`Posts:   ${postCounts.join("")}`);
+
+    // Impressions row
+    const impressions = report.byDayOfWeek.map(d =>
+      d.postCount > 0 ? d.avgImpressions.toLocaleString().padStart(7) : "      -"
+    );
+    console.log(`Impr:    ${impressions.join("")}`);
+
+    // Engagement rate row
+    const engRates = report.byDayOfWeek.map(d =>
+      d.postCount > 0 ? `${d.avgEngagementRate.toFixed(1)}%`.padStart(7) : "      -"
+    );
+    console.log(`Eng:     ${engRates.join("")}`);
+
+    console.log();
+    console.log(`Best day for impressions:  ${report.bestDayImpressions}`);
+    console.log(`Best day for engagement:   ${report.bestDayEngagement}`);
+
+    console.log("\nNote: LinkedIn CSV exports do not include publish time.");
+    console.log("This heatmap shows day-of-week only.");
+  } catch (err) {
+    console.error(`Error generating heatmap: ${err instanceof Error ? err.message : String(err)}`);
+    process.exit(1);
+  }
+}
+
 async function main() {
   const root = getAnalyticsRoot();
   ensureDirectories(root);
@@ -299,6 +432,9 @@ async function main() {
     case "trends":
       await handleTrends(root, args);
       break;
+    case "heatmap":
+      await handleHeatmap(root);
+      break;
     default:
       printUsage();
       process.exit(command ? 1 : 0);

plugins/linkedin-thought-leadership/scripts/analytics/src/models/types.ts

@@ -65,6 +65,55 @@ export interface Alert {
   deviations: number;
 }
 
+export interface DayOfWeekMetrics {
+  dayName: string; // "Monday" through "Sunday"
+  dayIndex: number; // 1=Monday, 7=Sunday (ISO weekday)
+  postCount: number;
+  avgImpressions: number;
+  avgEngagementRate: number;
+  bestPost?: PostAnalytics;
+}
+
+export interface HeatmapReport {
+  generatedAt: string;
+  postsAnalyzed: number;
+  dateRange: { from: string; to: string };
+  byDayOfWeek: DayOfWeekMetrics[]; // 7 entries, Mon-Sun ordered
+  bestDayImpressions: string;
+  bestDayEngagement: string;
+}
+
+export interface MonthlyReport {
+  month: string; // "YYYY-MM"
+  generatedAt: string;
+  summary: {
+    totalPosts: number;
+    totalImpressions: number;
+    totalReactions: number;
+    totalComments: number;
+    totalShares: number;
+    totalClicks: number;
+    avgEngagementRate: number;
+    avgImpressionsPerPost: number;
+  };
+  topPerformers: PostAnalytics[];
+  byWeek: {
+    week: string;
+    postCount: number;
+    avgImpressions: number;
+    avgEngagementRate: number;
+  }[];
+  trends: {
+    comparedTo: string | null;
+    percentChange: {
+      impressions: number | null;
+      engagement: number | null;
+      postCount: number | null;
+    };
+  };
+  alerts: Alert[];
+}
+
 export const ALERT_THRESHOLDS = {
   spike: 2.0,
   drop: -1.5,

plugins/linkedin-thought-leadership/scripts/analytics/src/reports/heatmap.ts

@@ -0,0 +1,85 @@
+import type { PostAnalytics, DayOfWeekMetrics, HeatmapReport } from "../models/types.js";
+
+const DAY_NAMES = ["Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"];
+
+// Convert JS getDay() (0=Sun) to ISO weekday (1=Mon, 7=Sun)
+function toISOWeekday(jsDay: number): number {
+  return jsDay === 0 ? 7 : jsDay;
+}
+
+/**
+ * Generate a day-of-week performance heatmap from post analytics data.
+ * Groups posts by day of week and calculates average metrics per day.
+ */
+export function generateHeatmap(posts: PostAnalytics[]): HeatmapReport {
+  // Initialize buckets for all 7 days (ISO: 1=Mon to 7=Sun)
+  const buckets: Map<number, PostAnalytics[]> = new Map();
+  for (let i = 1; i <= 7; i++) {
+    buckets.set(i, []);
+  }
+
+  // Group posts by ISO weekday
+  for (const post of posts) {
+    const jsDay = new Date(post.publishedDate).getUTCDay();
+    const isoDay = toISOWeekday(jsDay);
+    buckets.get(isoDay)!.push(post);
+  }
+
+  // Build metrics per day
+  const byDayOfWeek: DayOfWeekMetrics[] = [];
+  for (let isoDay = 1; isoDay <= 7; isoDay++) {
+    const dayPosts = buckets.get(isoDay)!;
+    const jsDay = isoDay === 7 ? 0 : isoDay;
+    const dayName = DAY_NAMES[jsDay];
+
+    if (dayPosts.length === 0) {
+      byDayOfWeek.push({
+        dayName,
+        dayIndex: isoDay,
+        postCount: 0,
+        avgImpressions: 0,
+        avgEngagementRate: 0,
+      });
+      continue;
+    }
+
+    const totalImpressions = dayPosts.reduce((sum, p) => sum + p.metrics.impressions, 0);
+    const totalEngagement = dayPosts.reduce((sum, p) => sum + p.metrics.engagementRate, 0);
+    const bestPost = dayPosts.reduce((best, p) =>
+      p.metrics.impressions > best.metrics.impressions ? p : best
+    );
+
+    byDayOfWeek.push({
+      dayName,
+      dayIndex: isoDay,
+      postCount: dayPosts.length,
+      avgImpressions: Math.round(totalImpressions / dayPosts.length),
+      avgEngagementRate: parseFloat((totalEngagement / dayPosts.length).toFixed(1)),
+      bestPost,
+    });
+  }
+
+  // Find best days
+  const daysWithPosts = byDayOfWeek.filter(d => d.postCount > 0);
+  const bestDayImpressions = daysWithPosts.length > 0
+    ? daysWithPosts.reduce((best, d) => d.avgImpressions > best.avgImpressions ? d : best).dayName
+    : "N/A";
+  const bestDayEngagement = daysWithPosts.length > 0
+    ? daysWithPosts.reduce((best, d) => d.avgEngagementRate > best.avgEngagementRate ? d : best).dayName
+    : "N/A";
+
+  // Date range
+  const sortedDates = posts.map(p => p.publishedDate).sort();
+  const dateRange = posts.length > 0
+    ? { from: sortedDates[0], to: sortedDates[sortedDates.length - 1] }
+    : { from: "", to: "" };
+
+  return {
+    generatedAt: new Date().toISOString(),
+    postsAnalyzed: posts.length,
+    dateRange,
+    byDayOfWeek,
+    bestDayImpressions,
+    bestDayEngagement,
+  };
+}

plugins/linkedin-thought-leadership/scripts/analytics/src/reports/monthly.ts

@@ -0,0 +1,117 @@
+import type { PostAnalytics, MonthlyReport } from "../models/types.js";
+import { loadAllPosts, loadMonthlyReport, saveMonthlyReport } from "../utils/storage.js";
+import { mean } from "../utils/stats.js";
+import { detectAlerts } from "../utils/alerts.js";
+import { getISOWeek } from "./weekly.js";
+
+/**
+ * Get previous month string (e.g., "2026-03" → "2026-02")
+ */
+function getPreviousMonth(month: string): string {
+  const [year, m] = month.split("-").map(Number);
+  if (m === 1) return `${year - 1}-12`;
+  return `${year}-${String(m - 1).padStart(2, "0")}`;
+}
+
+/**
+ * Generate a monthly report with optional MoM comparison.
+ * Saves the report to disk and returns it.
+ */
+export function generateMonthlyReport(root: string, month: string): MonthlyReport {
+  const allPosts = loadAllPosts(root);
+  const monthPosts = allPosts.filter(p => p.publishedDate.startsWith(month));
+
+  // Summary
+  const totalPosts = monthPosts.length;
+  const totalImpressions = monthPosts.reduce((s, p) => s + p.metrics.impressions, 0);
+  const totalReactions = monthPosts.reduce((s, p) => s + p.metrics.reactions, 0);
+  const totalComments = monthPosts.reduce((s, p) => s + p.metrics.comments, 0);
+  const totalShares = monthPosts.reduce((s, p) => s + p.metrics.shares, 0);
+  const totalClicks = monthPosts.reduce((s, p) => s + p.metrics.clicks, 0);
+  const avgEngagementRate = totalPosts > 0
+    ? parseFloat(mean(monthPosts.map(p => p.metrics.engagementRate)).toFixed(2))
+    : 0;
+  const avgImpressionsPerPost = totalPosts > 0
+    ? Math.round(totalImpressions / totalPosts)
+    : 0;
+
+  // Top performers (sorted by impressions desc)
+  const topPerformers = [...monthPosts]
+    .sort((a, b) => b.metrics.impressions - a.metrics.impressions)
+    .slice(0, 5);
+
+  // Weekly breakdown
+  const weekBuckets = new Map<string, PostAnalytics[]>();
+  for (const post of monthPosts) {
+    const week = getISOWeek(new Date(post.publishedDate + "T00:00:00Z"));
+    if (!weekBuckets.has(week)) weekBuckets.set(week, []);
+    weekBuckets.get(week)!.push(post);
+  }
+
+  const byWeek = Array.from(weekBuckets.entries())
+    .sort(([a], [b]) => a.localeCompare(b))
+    .map(([week, posts]) => ({
+      week,
+      postCount: posts.length,
+      avgImpressions: Math.round(mean(posts.map(p => p.metrics.impressions))),
+      avgEngagementRate: parseFloat(mean(posts.map(p => p.metrics.engagementRate)).toFixed(1)),
+    }));
+
+  // MoM comparison
+  const prevMonth = getPreviousMonth(month);
+  const prevReport = loadMonthlyReport(root, prevMonth);
+
+  let trends: MonthlyReport["trends"];
+  if (prevReport && prevReport.summary.totalPosts > 0) {
+    const pctImpr = prevReport.summary.totalImpressions > 0
+      ? parseFloat(((totalImpressions - prevReport.summary.totalImpressions) / prevReport.summary.totalImpressions * 100).toFixed(1))
+      : null;
+    const pctEng = prevReport.summary.avgEngagementRate > 0
+      ? parseFloat(((avgEngagementRate - prevReport.summary.avgEngagementRate) / prevReport.summary.avgEngagementRate * 100).toFixed(1))
+      : null;
+    const pctPosts = prevReport.summary.totalPosts > 0
+      ? parseFloat(((totalPosts - prevReport.summary.totalPosts) / prevReport.summary.totalPosts * 100).toFixed(1))
+      : null;
+
+    trends = {
+      comparedTo: prevMonth,
+      percentChange: {
+        impressions: pctImpr,
+        engagement: pctEng,
+        postCount: pctPosts,
+      },
+    };
+  } else {
+    trends = {
+      comparedTo: null,
+      percentChange: { impressions: null, engagement: null, postCount: null },
+    };
+  }
+
+  // Alerts
+  const alerts = totalPosts > 0 ? detectAlerts(monthPosts, "impressions") : [];
+
+  const report: MonthlyReport = {
+    month,
+    generatedAt: new Date().toISOString(),
+    summary: {
+      totalPosts,
+      totalImpressions,
+      totalReactions,
+      totalComments,
+      totalShares,
+      totalClicks,
+      avgEngagementRate,
+      avgImpressionsPerPost,
+    },
+    topPerformers,
+    byWeek,
+    trends,
+    alerts,
+  };
+
+  // Save report
+  saveMonthlyReport(root, report);
+
+  return report;
+}

plugins/linkedin-thought-leadership/scripts/analytics/src/utils/storage.ts

@@ -1,7 +1,7 @@
 import { readFileSync, writeFileSync, readdirSync, existsSync, mkdirSync } from "node:fs";
 import { join, resolve, dirname } from "node:path";
 import { fileURLToPath } from "node:url";
-import type { AnalyticsBatch, WeeklyReport, PostAnalytics } from "../models/types.js";
+import type { AnalyticsBatch, WeeklyReport, MonthlyReport, PostAnalytics } from "../models/types.js";
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
 
@@ -25,7 +25,7 @@ export function getAnalyticsRoot(): string {
  * Ensure required subdirectories exist under analytics root
  */
 export function ensureDirectories(root: string): void {
-  const directories = ["exports", "posts", "weekly-reports"];
+  const directories = ["exports", "posts", "weekly-reports", "monthly-reports"];
 
   if (!existsSync(root)) {
     mkdirSync(root, { recursive: true });
@@ -252,3 +252,39 @@ export function loadAllWeeklyReports(root: string): WeeklyReport[] {
     b.week.localeCompare(a.week)
   );
 }
+
+/**
+ * Sanitize month string to only allow YYYY-MM format
+ */
+function sanitizeMonth(month: string): string {
+  if (!/^\d{4}-\d{2}$/.test(month)) {
+    throw new Error(`Invalid month format: ${month}. Expected YYYY-MM`);
+  }
+  return month;
+}
+
+/**
+ * Save a monthly report to disk
+ */
+export function saveMonthlyReport(root: string, report: MonthlyReport): string {
+  ensureDirectories(root);
+  const reportsDir = join(root, "monthly-reports");
+  const month = sanitizeMonth(report.month);
+  const filename = `${month}.json`;
+  const filepath = join(reportsDir, filename);
+  verifyPathWithinDirectory(filepath, reportsDir);
+  writeFileSync(filepath, JSON.stringify(report, null, 2), "utf-8");
+  return filename;
+}
+
+/**
+ * Load a specific monthly report by month identifier
+ */
+export function loadMonthlyReport(root: string, month: string): MonthlyReport | null {
+  month = sanitizeMonth(month);
+  const reportsDir = join(root, "monthly-reports");
+  const filepath = join(reportsDir, `${month}.json`);
+  if (!existsSync(filepath)) return null;
+  const content = readFileSync(filepath, "utf-8");
+  return JSON.parse(content) as MonthlyReport;
+}

plugins/linkedin-thought-leadership/scripts/analytics/tests/heatmap.test.ts

@@ -0,0 +1,113 @@
+import { describe, test } from "node:test";
+import assert from "node:assert/strict";
+import { generateHeatmap } from "../src/reports/heatmap.js";
+import type { PostAnalytics } from "../src/models/types.js";
+
+function createPost(date: string, impressions: number, engagementRate: number): PostAnalytics {
+  return {
+    id: `post-${date}`,
+    title: `Post on ${date}`,
+    publishedDate: date,
+    metrics: {
+      impressions,
+      reactions: 10,
+      comments: 5,
+      shares: 2,
+      clicks: 3,
+      engagementRate,
+    },
+    importedAt: "2026-04-01T00:00:00Z",
+    exportSource: "test.csv",
+  };
+}
+
+describe("generateHeatmap", () => {
+  // Verified days: 2026-04-06=Mon, 07=Tue, 08=Wed, 09=Thu, 12=Sun, 13=Mon, 14=Tue, 15=Wed
+  const posts: PostAnalytics[] = [
+    createPost("2026-04-06", 1000, 3.0), // Monday
+    createPost("2026-04-07", 2000, 4.0), // Tuesday
+    createPost("2026-04-08", 1500, 3.5), // Wednesday
+    createPost("2026-04-13", 3000, 5.0), // Monday
+    createPost("2026-04-14", 2500, 4.5), // Tuesday
+    createPost("2026-04-12", 800, 2.0),  // Sunday
+  ];
+
+  test("groups posts by day of week correctly", () => {
+    const report = generateHeatmap(posts);
+    const monday = report.byDayOfWeek.find(d => d.dayName === "Monday");
+    const tuesday = report.byDayOfWeek.find(d => d.dayName === "Tuesday");
+    const sunday = report.byDayOfWeek.find(d => d.dayName === "Sunday");
+
+    assert.equal(monday?.postCount, 2);
+    assert.equal(tuesday?.postCount, 2);
+    assert.equal(sunday?.postCount, 1);
+  });
+
+  test("calculates correct averages per day", () => {
+    const report = generateHeatmap(posts);
+    const monday = report.byDayOfWeek.find(d => d.dayName === "Monday")!;
+    const tuesday = report.byDayOfWeek.find(d => d.dayName === "Tuesday")!;
+
+    assert.equal(monday.avgImpressions, 2000); // (1000+3000)/2
+    assert.equal(tuesday.avgImpressions, 2250); // (2000+2500)/2
+    assert.equal(monday.avgEngagementRate, 4.0); // (3.0+5.0)/2
+  });
+
+  test("handles days with no posts", () => {
+    const report = generateHeatmap(posts);
+    const friday = report.byDayOfWeek.find(d => d.dayName === "Friday")!;
+
+    assert.equal(friday.postCount, 0);
+    assert.equal(friday.avgImpressions, 0);
+    assert.equal(friday.avgEngagementRate, 0);
+  });
+
+  test("returns 7 entries ordered Mon-Sun", () => {
+    const report = generateHeatmap(posts);
+    assert.equal(report.byDayOfWeek.length, 7);
+    assert.equal(report.byDayOfWeek[0].dayName, "Monday");
+    assert.equal(report.byDayOfWeek[6].dayName, "Sunday");
+    assert.deepEqual(
+      report.byDayOfWeek.map(d => d.dayIndex),
+      [1, 2, 3, 4, 5, 6, 7]
+    );
+  });
+
+  test("identifies best day for impressions", () => {
+    const report = generateHeatmap(posts);
+    assert.equal(report.bestDayImpressions, "Tuesday");
+  });
+
+  test("identifies best day for engagement", () => {
+    const report = generateHeatmap(posts);
+    assert.equal(report.bestDayEngagement, "Tuesday"); // (4.0+4.5)/2 = 4.25
+  });
+
+  test("sets correct postsAnalyzed count", () => {
+    const report = generateHeatmap(posts);
+    assert.equal(report.postsAnalyzed, 6);
+  });
+
+  test("handles empty post list", () => {
+    const report = generateHeatmap([]);
+    assert.equal(report.postsAnalyzed, 0);
+    assert.equal(report.byDayOfWeek.length, 7);
+    assert.equal(report.bestDayImpressions, "N/A");
+    assert.equal(report.bestDayEngagement, "N/A");
+    for (const day of report.byDayOfWeek) {
+      assert.equal(day.postCount, 0);
+    }
+  });
+
+  test("identifies best post per day", () => {
+    const report = generateHeatmap(posts);
+    const monday = report.byDayOfWeek.find(d => d.dayName === "Monday")!;
+    assert.equal(monday.bestPost?.publishedDate, "2026-04-13"); // 3000 impressions
+  });
+
+  test("calculates correct date range", () => {
+    const report = generateHeatmap(posts);
+    assert.equal(report.dateRange.from, "2026-04-06");
+    assert.equal(report.dateRange.to, "2026-04-14");
+  });
+});

plugins/linkedin-thought-leadership/scripts/analytics/tests/monthly.test.ts

@@ -0,0 +1,135 @@
+import { describe, test, afterEach } from "node:test";
+import assert from "node:assert/strict";
+import { mkdtempSync, rmSync, writeFileSync, mkdirSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+import { generateMonthlyReport } from "../src/reports/monthly.js";
+import { saveBatch } from "../src/utils/storage.js";
+import type { PostAnalytics, AnalyticsBatch, MonthlyReport } from "../src/models/types.js";
+
+function createPost(date: string, impressions: number, engagementRate: number): PostAnalytics {
+  return {
+    id: `post-${date}-${impressions}`,
+    title: `Post on ${date}`,
+    publishedDate: date,
+    metrics: {
+      impressions,
+      reactions: Math.round(impressions * 0.05),
+      comments: Math.round(impressions * 0.01),
+      shares: Math.round(impressions * 0.005),
+      clicks: Math.round(impressions * 0.02),
+      engagementRate,
+    },
+    importedAt: "2026-04-01T00:00:00Z",
+    exportSource: "test.csv",
+  };
+}
+
+function createBatch(posts: PostAnalytics[]): AnalyticsBatch {
+  const dates = posts.map(p => p.publishedDate).sort();
+  return {
+    batchId: "test-batch-" + Math.random().toString(36).slice(2, 10),
+    importedAt: "2026-04-01T00:00:00Z",
+    exportFilename: "test.csv",
+    dateRange: { from: dates[0], to: dates[dates.length - 1] },
+    postCount: posts.length,
+    posts,
+  };
+}
+
+let tmpDir: string;
+
+function setupTestRoot(posts: PostAnalytics[]): string {
+  tmpDir = mkdtempSync(join(tmpdir(), "monthly-test-"));
+  for (const dir of ["exports", "posts", "weekly-reports", "monthly-reports"]) {
+    mkdirSync(join(tmpDir, dir), { recursive: true });
+  }
+  if (posts.length > 0) {
+    saveBatch(tmpDir, createBatch(posts));
+  }
+  return tmpDir;
+}
+
+afterEach(() => {
+  if (tmpDir) rmSync(tmpDir, { recursive: true, force: true });
+});
+
+describe("generateMonthlyReport", () => {
+  const marchPosts: PostAnalytics[] = [
+    createPost("2026-03-03", 1000, 3.0),
+    createPost("2026-03-05", 2000, 4.0),
+    createPost("2026-03-10", 1500, 3.5),
+    createPost("2026-03-17", 3000, 5.0),
+    createPost("2026-03-24", 2500, 4.5),
+  ];
+
+  const febPosts: PostAnalytics[] = [
+    createPost("2026-02-03", 800, 2.5),
+    createPost("2026-02-10", 1200, 3.0),
+    createPost("2026-02-17", 900, 2.8),
+  ];
+
+  test("filters posts to correct month", () => {
+    const root = setupTestRoot([...marchPosts, ...febPosts]);
+    const report = generateMonthlyReport(root, "2026-03");
+    assert.equal(report.summary.totalPosts, 5);
+  });
+
+  test("calculates correct monthly totals", () => {
+    const root = setupTestRoot(marchPosts);
+    const report = generateMonthlyReport(root, "2026-03");
+    assert.equal(report.summary.totalImpressions, 10000); // 1000+2000+1500+3000+2500
+    assert.equal(report.summary.totalPosts, 5);
+    assert.equal(report.summary.avgImpressionsPerPost, 2000);
+  });
+
+  test("generates weekly breakdown within month", () => {
+    const root = setupTestRoot(marchPosts);
+    const report = generateMonthlyReport(root, "2026-03");
+    assert.ok(report.byWeek.length > 0);
+    const totalPostsInWeeks = report.byWeek.reduce((sum, w) => sum + w.postCount, 0);
+    assert.equal(totalPostsInWeeks, 5);
+  });
+
+  test("calculates MoM deltas when previous month exists", () => {
+    const root = setupTestRoot([...febPosts, ...marchPosts]);
+    // First generate February report so it exists for comparison
+    generateMonthlyReport(root, "2026-02");
+    const report = generateMonthlyReport(root, "2026-03");
+
+    assert.notEqual(report.trends.comparedTo, null);
+    assert.equal(report.trends.comparedTo, "2026-02");
+    assert.notEqual(report.trends.percentChange.impressions, null);
+    assert.notEqual(report.trends.percentChange.postCount, null);
+  });
+
+  test("handles no previous month data", () => {
+    const root = setupTestRoot(marchPosts);
+    const report = generateMonthlyReport(root, "2026-03");
+    assert.equal(report.trends.comparedTo, null);
+    assert.equal(report.trends.percentChange.impressions, null);
+    assert.equal(report.trends.percentChange.engagement, null);
+  });
+
+  test("handles month with no posts", () => {
+    const root = setupTestRoot(marchPosts);
+    const report = generateMonthlyReport(root, "2026-01");
+    assert.equal(report.summary.totalPosts, 0);
+    assert.equal(report.summary.totalImpressions, 0);
+    assert.equal(report.summary.avgImpressionsPerPost, 0);
+    assert.equal(report.byWeek.length, 0);
+  });
+
+  test("identifies top performers", () => {
+    const root = setupTestRoot(marchPosts);
+    const report = generateMonthlyReport(root, "2026-03");
+    assert.ok(report.topPerformers.length > 0);
+    assert.equal(report.topPerformers[0].metrics.impressions, 3000);
+  });
+
+  test("sets correct month field", () => {
+    const root = setupTestRoot(marchPosts);
+    const report = generateMonthlyReport(root, "2026-03");
+    assert.equal(report.month, "2026-03");
+  });
+});

plugins/linkedin-thought-leadership/skills/linkedin-thought-leadership/SKILL.md

@@ -34,6 +34,7 @@ This plugin uses **6 focused skills**. This main skill contains shared knowledge
 
 | User Intent | Route To |
 |-------------|----------|
+| "Just installed" / "Walk me through" | `/linkedin:onboarding` |
 | "Set up plugin" | `/linkedin:setup` |
 | "Personalize" | `/linkedin:setup` |
 | "Improve personalization" | `/linkedin:setup` |
@@ -115,6 +116,7 @@ These rules apply to ALL content created by any skill or command:
 | Command | Purpose |
 |---------|---------|
 | `/linkedin` | Router -- shows status line + command menu |
+| `/linkedin:onboarding` | Multi-step onboarding wizard (profile → setup → first-post) |
 | `/linkedin:first-post` | First-post accelerator (zero to published in 10 min) |
 | `/linkedin:setup` | Guided setup to populate asset templates with real data |
 | `/linkedin:react` | URL-to-post pipeline -- react to articles, news, research |

plugins/linkedin-thought-leadership/skills/linkedin-voice/SKILL.md

@@ -109,7 +109,7 @@ Transform each role with impact statements, not task lists:
 
 WHO you help + RESULT you deliver
 
-Strong: "Helping [target audience] achieve [specific result] | [Your Role] @ [Your Organization]"
+Strong: "Helping public sector leaders implement AI that actually works | AI Advisor @ Statens vegvesen"
 
 ---