open/ktg-plugin-marketplace
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions

fix(linkedin-studio): propagate reconciled algorithm numbers, cite-not-restate

Browse source 
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-05-29 20:32:17 +02:00
commit 4700248cc4
32 changed files with 133 additions and 113 deletions
Download patch file Download diff file Expand all files Collapse all files

8
plugins/linkedin-studio/CLAUDE.md
View file

@ -1,6 +1,6 @@
# LinkedIn Studio Plugin (v3.1.0)
Full-spectrum LinkedIn content engine — short-form feed posts, carousels, video scripts, and long-form newsletter editions — with the January 2026 360Brew algorithm baked in. v2.0.0 consolidated the surface (27 commands → 24, 16 agents → 14) while adding the long-form `/linkedin:newsletter` orchestrator + two longform-quality gate agents (`fact-checker`, `persona-reviewer`). v2.1.0 added two gates BEFORE prose (Step 2.5 skeleton + Step 3a spine prose) + a third `persona-reviewer` mode (`skjelett`). v2.2.0 hardened the longform gates with the lessons from the second production run (Seres-serien): blocking persona hard-fails, a post-cutoff fact-check mandate, a `voice-scrubber` agent, render+annotate operator gates, and STATE.md-reconciled edition state. v2.3.0 made **visual assets an explicit pipeline phase** — Step 7.5 (visual-assets) between annotation (Step 7) and lock (Step 8): cover (+ optional inline figures) or a carousel deck, generated (default `mcp-image`, external `cover-raw.png` accepted) and operator-gated BEFORE lock so `render/build-linkedin.mjs` picks up `cover.png` at lock without a post-lock re-render. **v2.4.0** makes an **editor's craft gate an explicit pipeline phase** — new **Step 5.5 (editorial-review)** between fact-check (Step 5) and the persona sweep (Step 6): a new **`editorial-reviewer` agent** (Opus) judges **craft** (prosa-håndverk + narrativ-arkitektur), not reader-response, returning ≤10 flags (BLOCK/REWORK/NICE) as direction, **operator-gated via `SendUserFile` BEFORE the persona sweep** so the personas measure resonance instead of stumbling on craft noise. Motivated by Del 4: every persona reported PASS, yet the editor found 8 fresh points on first reading, ~6/8 of them craft/architecture blind spots no agent measured. Mirrors the Maskinrommet writing-contract §C2. Pipeline 14 → 15 phases; agents 15 → 16; additive `editorialReview` state. Doc/orchestration-only for the wiring (the new agent + its fasit fixture + lint test are the only new files); commands unchanged (24). **v3.1.0 (Endring 9)** adds an **adversarial review package** run COLD on a frozen draft — new **Step 6.5 (headless-review)** between the persona sweep (Step 6) and lock, plus a standalone **`/linkedin:headless-review`** command (run in a fresh session for maximum isolation): three new headless archetypes — **`content-reviewer`** (argument integrity), **`language-reviewer`** (Norwegian language), **`fact-reviewer`** (cold re-verification incl. claims a late pivot bolted on) — plus `persona-reviewer` in resonance + conversion modes, all with NO drafting-session context (the independence layer the in-session gates structurally cannot be). v3.1.0 also adds **`/linkedin:pivot`** (re-opens cleared gates after a late change + a >20 %/>2-section pivot-detection gate at lock) and **per-artifact personas** (`articles.NN.personas` — one or more readers configurable per edition, resolved edition-state → series file → plugin library → interactive). Pipeline 15 → 16 phases; agents 16 → 19; commands 24 → 26; additive `personas` / `pivots` / `headlessReview` state. Motivated by Del 4: the in-session editor + persona sweep shared the drafting session's framing-bias, so the version that shipped was never independently re-reviewed.
Full-spectrum LinkedIn content engine — short-form feed posts, carousels, video scripts, and long-form newsletter editions — with the 2026 relevance-ranking model baked in. v2.0.0 consolidated the surface (27 commands → 24, 16 agents → 14) while adding the long-form `/linkedin:newsletter` orchestrator + two longform-quality gate agents (`fact-checker`, `persona-reviewer`). v2.1.0 added two gates BEFORE prose (Step 2.5 skeleton + Step 3a spine prose) + a third `persona-reviewer` mode (`skjelett`). v2.2.0 hardened the longform gates with the lessons from the second production run (Seres-serien): blocking persona hard-fails, a post-cutoff fact-check mandate, a `voice-scrubber` agent, render+annotate operator gates, and STATE.md-reconciled edition state. v2.3.0 made **visual assets an explicit pipeline phase** — Step 7.5 (visual-assets) between annotation (Step 7) and lock (Step 8): cover (+ optional inline figures) or a carousel deck, generated (default `mcp-image`, external `cover-raw.png` accepted) and operator-gated BEFORE lock so `render/build-linkedin.mjs` picks up `cover.png` at lock without a post-lock re-render. **v2.4.0** makes an **editor's craft gate an explicit pipeline phase** — new **Step 5.5 (editorial-review)** between fact-check (Step 5) and the persona sweep (Step 6): a new **`editorial-reviewer` agent** (Opus) judges **craft** (prosa-håndverk + narrativ-arkitektur), not reader-response, returning ≤10 flags (BLOCK/REWORK/NICE) as direction, **operator-gated via `SendUserFile` BEFORE the persona sweep** so the personas measure resonance instead of stumbling on craft noise. Motivated by Del 4: every persona reported PASS, yet the editor found 8 fresh points on first reading, ~6/8 of them craft/architecture blind spots no agent measured. Mirrors the Maskinrommet writing-contract §C2. Pipeline 14 → 15 phases; agents 15 → 16; additive `editorialReview` state. Doc/orchestration-only for the wiring (the new agent + its fasit fixture + lint test are the only new files); commands unchanged (24). **v3.1.0 (Endring 9)** adds an **adversarial review package** run COLD on a frozen draft — new **Step 6.5 (headless-review)** between the persona sweep (Step 6) and lock, plus a standalone **`/linkedin:headless-review`** command (run in a fresh session for maximum isolation): three new headless archetypes — **`content-reviewer`** (argument integrity), **`language-reviewer`** (Norwegian language), **`fact-reviewer`** (cold re-verification incl. claims a late pivot bolted on) — plus `persona-reviewer` in resonance + conversion modes, all with NO drafting-session context (the independence layer the in-session gates structurally cannot be). v3.1.0 also adds **`/linkedin:pivot`** (re-opens cleared gates after a late change + a >20 %/>2-section pivot-detection gate at lock) and **per-artifact personas** (`articles.NN.personas` — one or more readers configurable per edition, resolved edition-state → series file → plugin library → interactive). Pipeline 15 → 16 phases; agents 16 → 19; commands 24 → 26; additive `personas` / `pivots` / `headlessReview` state. Motivated by Del 4: the in-session editor + persona sweep shared the drafting session's framing-bias, so the version that shipped was never independently re-reviewed.
## Architecture
@ -63,7 +63,7 @@ All content commands (post, quick, react, pipeline, first-post, video, multiplat
| `/linkedin:competitive` | Competitive analysis of niche |
| `/linkedin:monetize` | Monetization strategy and funnels (unlocks at ~1K followers) |
| `/linkedin:outreach` | Outreach orchestrator — collaborations + speaking opportunities (unlocks at ~1K followers) |
| `/linkedin:profile` | 360Brew profile optimization |
| `/linkedin:profile` | profile/topic-relevance optimization |
## Agents (19)
@ -104,8 +104,8 @@ invokable until the session reloads. After adding an agent, reload before invoki
1. Hook: 110-140 characters (mobile cutoff)
2. Post length: 1,200-1,800 chars (standard), 150-500 chars (quick)
3. No external links in post body (40-50% reach suppression)
3. No external links in post body (correlate with lower reach; see `references/algorithm-signals-reference.md`)
4. No corporate buzzwords: leverage, synergy, paradigm shift, thought leader, disruptive, value proposition, ecosystem, holistic approach
5. Topic must align with user's 5 core expertise areas (360Brew signal)
5. Topic must align with user's 5 core expertise areas (topic-relevance signal)
6. Topic rotation: no back-to-back same pillar, no pillar >50% in 14 days (warn-only)
7. Progressive onboarding: personalization score hidden until 3+ posts; voice guardian suppressed until 5+ voice samples

22
plugins/linkedin-studio/README.md
View file

@ -14,7 +14,7 @@
![Reference Docs](https://img.shields.io/badge/reference_docs-24-teal)
![License](https://img.shields.io/badge/license-MIT-lightgrey)
Most experts know they *should* post on LinkedIn — and quietly don't. The blank editor wins. LinkedIn Studio turns that chore into a system: structured workflows that take you from idea to published, in your own voice, calibrated to how LinkedIn's **360Brew** ranking model (January 2026) actually distributes content. Two engines under one surface — a **feed engine** for short-form posts, carousels, and video scripts, and a **long-form engine** that runs newsletter editions and essays through a serious editorial pipeline before they ever lock. 26 commands, 19 specialized agents, 9 automated quality hooks, and a 24-document knowledge base grounded in the algorithm's real signals.
Most experts know they *should* post on LinkedIn — and quietly don't. The blank editor wins. LinkedIn Studio turns that chore into a system: structured workflows that take you from idea to published, in your own voice, calibrated to how LinkedIn's **topic-relevance** ranking model (2026) actually distributes content. Two engines under one surface — a **feed engine** for short-form posts, carousels, and video scripts, and a **long-form engine** that runs newsletter editions and essays through a serious editorial pipeline before they ever lock. 26 commands, 19 specialized agents, 9 automated quality hooks, and a 24-document knowledge base grounded in the algorithm's real signals.
This is not a shortcut. Hand the wheel to the AI and you land where everyone who did the same lands — the forgettable middle. The plugin removes the friction; the judgment, the genuine engagement, and the effort that make content worth reading remain entirely yours.
@ -52,7 +52,7 @@ For most professionals, the hard part of LinkedIn isn't writing — it's everyth
- **You post in bursts, then go quiet.** Three posts one week, nothing for a month. The algorithm reads inconsistency as "not a creator" and quietly throttles you.
- **You can't see why anything works.** One post reaches 12,000 people; the next, near-identical one, reaches 200. With no model of the ranking signals, every post is a coin flip.
- **Generic AI output sounds like generic AI.** It doesn't sound like you, it leans on buzzwords, and LinkedIn's classifiers increasingly suppress exactly that register. "AI-assisted" only helps if it protects your voice.
- **The ground moved in January 2026.** LinkedIn's **360Brew** model now validates your *profile* before distributing your *content* — an off-topic post or an unoptimized profile caps reach regardless of how good the writing is. Most "LinkedIn tips" predate this and are now actively misleading.
- **The ground moved in 2026.** LinkedIn's **topic-relevance** model now validates your *profile* before distributing your *content* — an off-topic post or an unoptimized profile caps reach regardless of how good the writing is. Most "LinkedIn tips" predate this and are now actively misleading.
**What the plugin does about it:**
@ -60,9 +60,9 @@ For most professionals, the hard part of LinkedIn isn't writing — it's everyth
|----------|---------------------|
| Blank-page paralysis | Guided workflows — from a 5-minute `/linkedin:quick` to a full `/linkedin:pipeline` — so you start from structure, not a void |
| Inconsistency | A scheduling queue, streak tracking, batch creation, and proactive posting reminders that keep cadence visible |
| Algorithm opacity | Every command is calibrated to documented 360Brew signals; hooks gate hook-length, link-suppression, buzzwords, and topic rotation *before* you publish |
| Algorithm opacity | Every command is calibrated to documented topic-relevance signals; hooks gate hook-length, link-suppression, buzzwords, and topic rotation *before* you publish |
| Generic slop | Voice training learns your authentic style and flags drift; a voice-guardian hook catches AI register on the way out |
| The 360Brew shift | `/linkedin:profile` aligns your profile to the new model first, because content distribution now depends on it |
| The topic-relevance shift | `/linkedin:profile` aligns your profile to the new model first, because content distribution now depends on it |
The result is not "AI writes your posts." It's a system that holds the structure, the discipline, and the algorithmic knowledge so you can focus on the one thing only you can supply — the expertise.
@ -77,7 +77,7 @@ LinkedIn Studio is a complete LinkedIn content engine inside Claude Code. Instea
Key capabilities:
- **360Brew profile optimization** aligned with LinkedIn's AI-first content distribution (January 2026 update)
- **profile/topic-relevance optimization** aligned with LinkedIn's AI-first content distribution (2026 update)
- **Content angle system** that generates post ideas from a single topic using 8 universal thought-leadership angles
- **Full content pipeline** from ideation through post-publish 48-hour monitoring
- **Long-form editorial pipeline** — newsletter editions and essays run through skeleton, voice, fact-check, craft, resonance, and cold adversarial review gates *before* they lock
@ -166,7 +166,7 @@ Run the onboarding wizard — it walks you through profile, setup, and your firs
/linkedin:onboarding
```
The wizard handles everything: 360Brew profile checklist, voice and user profile setup, and a guided first post.
The wizard handles everything: topic-relevance profile checklist, voice and user profile setup, and a guided first post.
### Already Set Up?
@ -225,7 +225,7 @@ All 26 commands use colon notation: `/linkedin:post`, `/linkedin:quick`, etc.
| Command | Description |
|---------|-------------|
| `/linkedin:strategy` | Growth strategy + authority building. Phase-specific guidance from foundation (0-1K) through authority establishment (10K+), trajectory-aware adjustments, and signature-content compounding for Phase 2+. The single growth/authority entry point — `/linkedin:profile` owns 360Brew alignment. |
| `/linkedin:strategy` | Growth strategy + authority building. Phase-specific guidance from foundation (0-1K) through authority establishment (10K+), trajectory-aware adjustments, and signature-content compounding for Phase 2+. The single growth/authority entry point — `/linkedin:profile` owns topic-relevance alignment. |
| `/linkedin:monetize` | Monetization strategy with scored readiness assessment, stage-specific action plans, lead magnet blueprints, DM conversion workflows, and revenue dashboards. |
| `/linkedin:outreach` | Outreach orchestrator covering both collaborations and speaking opportunities under one paradigm: readiness assessment (collab thresholds + 100-pt speaker scorecard), partner scoring (25-pt rubric), event/CFP search with Nordic/European conference calendar, 12 collaboration formats across 4 maturity tiers, 4 talk abstract templates, speaker bio variants, co-creation production workflow, unified pipeline tracker, and quarterly results dashboard. |
@ -233,7 +233,7 @@ All 26 commands use colon notation: `/linkedin:post`, `/linkedin:quick`, etc.
| Command | Description |
|---------|-------------|
| `/linkedin:profile` | 360Brew profile optimization checklist. Audits About section, Experience, Headline, content history alignment, and network patterns. |
| `/linkedin:profile` | profile/topic-relevance optimization checklist. Audits About section, Experience, Headline, content history alignment, and network patterns. |
| `/linkedin:setup` | Guided setup to populate asset templates with real data. 6 sub-workflows: voice samples, case studies, frameworks, post analysis, demographics, user profile. Calculates personalization score. |
| `/linkedin` | Main router. Shows posting status (streak, weekly progress) and lists all available commands with contextual guidance. |
@ -535,9 +535,9 @@ The plugin enforces quality standards through hooks and agent behavior:
| Hook length | 110-140 characters | PreToolUse quality gate |
| Post length (standard) | 1,200-1,800 characters | PreToolUse quality gate |
| Post length (quick) | 150-500 characters | PreToolUse quality gate |
| No external links in body | 0 links | PreToolUse quality gate (40-50% reach suppression) |
| No external links in body | 0 links | PreToolUse quality gate (body links correlate with lower reach) |
| No corporate buzzwords | Blocklist: leverage, synergy, paradigm shift, thought leader, disruptive, value proposition, ecosystem, holistic approach | PreToolUse quality gate |
| Topic alignment | Must align with 5 core expertise areas | 360Brew signal check |
| Topic alignment | Must align with 5 core expertise areas | topic-relevance signal check |
| Topic rotation | No back-to-back same pillar; no pillar >50% in 14 days | Topic rotation gate (warn-only) |
| Voice consistency | AI authenticity check + voice matching | Voice guardian hook |
@ -612,7 +612,7 @@ Scheduled posts are tracked in `assets/drafts/queue.json`:
| **1.2.0** | 2026-04-11 | Friction reduction release. Auto-clipboard on all content commands, reduced interactive steps (max 2 per post), deterministic state management (`state-updater.mjs`), MCP image carousel pipeline, progressive onboarding, iCal calendar integration for batch scheduling, auto-prune content history (90 days). |
| **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. |
| **0.6.0** | 2026-02-07 | First formal version. 20 commands, 15 agents, 8 hooks, analytics system, profile/topic-relevance optimization, content matrix system, personalization engine, 20 reference documents. |
See [CHANGELOG.md](CHANGELOG.md) for full details and known gaps.

12
plugins/linkedin-studio/agents/content-optimizer.md
View file

@ -2,7 +2,7 @@
name: content-optimizer
description: |
Optimize existing LinkedIn content for better performance. Analyzes hooks, structure, CTAs, and
format against January 2026 algorithm signals. Provides specific, actionable improvements.
format against 2026 algorithm signals. Provides specific, actionable improvements.
Use when the user says:
- "optimize this post", "make this better", "improve engagement"
@ -19,7 +19,7 @@ tools: ["Read", "Glob"]
# Content Optimizer Agent
You are a LinkedIn content optimization specialist with deep knowledge of the January 2026 algorithm changes, including the 360Brew profile validation system.
You are a LinkedIn content optimization specialist with deep knowledge of the 2026 algorithm changes, including the topic-relevance profile validation system.
## Your Mission
@ -78,7 +78,7 @@ When you receive content to optimize, analyze it through these lenses:
**Penalties to avoid:**
- 5+ hashtags (-68%)
- External links in body (-25-40%)
- External links in body (correlate with lower reach — see `references/algorithm-signals-reference.md`)
- Engagement bait phrases (-30-50%)
- Posts under 1,000 chars (-25%)
- Posts over 2,500 chars (-32%)
@ -99,12 +99,12 @@ When you receive content to optimize, analyze it through these lenses:
- Match the tone of the post
- Create optionality for engagement
### 5. 360Brew Alignment Check
### 5. topic-relevance Alignment Check
**Critical for January 2026:**
**Critical for 2026:**
- Does this content align with the creator's stated expertise?
- Would their profile validate authority on this topic?
- If posting off-topic: flag the risk (-40-60% reach)
- If posting off-topic: flag the risk (weak profile/topic alignment lowers reach — see `references/algorithm-signals-reference.md`)
## Output Format

4
plugins/linkedin-studio/agents/engagement-coach.md
View file

@ -45,7 +45,7 @@ Help creators:
## The Engagement Multiplier
**The math that most creators ignore:**
- Comments are worth 15x more reach than likes
- Comments rank above likes in the engagement order (see `references/algorithm-signals-reference.md`)
- Comments drive 5x more reach than reshares
- Posts with 15+ engagements in first hour unlock 2nd/3rd degree distribution
- Your comments on others' posts expose you to their audience
@ -441,7 +441,7 @@ Why this works: [Brief explanation]
7. **Conversations beat drive-bys** — Return to threads, continue dialogues
8. **The audience is watching** — Comment for the readers, not just the author
9. **Consistency compounds** — 15 daily comments for 90 days > 50 comments for a week then stopping
10. **Comment first, like second** — Always prioritize comments over reactions (15x more reach)
10. **Comment first, like second** — Always prioritize comments over reactions (higher in the engagement order; see `references/algorithm-signals-reference.md`)
11. **Quality has a floor** — Never post a comment you wouldn't want on your own profile
## Anti-Patterns (What NOT to Do)

4
plugins/linkedin-studio/agents/post-feedback-monitor.md
View file

@ -139,7 +139,7 @@ Check for these six anomaly patterns:
### 4. Ghost Impressions
**Detection:** Impressions growing steadily but near-zero engagement (engagement rate <0.5%)
**Likely cause:** Algorithm is testing the post with broader audience but nobody is engaging. Content may be off-topic for the audience receiving it (360Brew mismatch).
**Likely cause:** Algorithm is testing the post with broader audience but nobody is engaging. Content may be off-topic for the audience receiving it (profile/topic mismatch).
**Intervention:** Check if post topic aligns with profile expertise. If mismatched, note for future posts. Add a self-comment to prime engagement. This pattern often means the content needs to be more opinion-driven.
### 5. Delayed Spike
@ -321,7 +321,7 @@ If the post is performing well (>75th percentile):
## Handling Common Questions
### "My post got zero engagement in the first 30 minutes"
Check: Did you post at an optimal time? Is the hook strong? Does the topic match your profile expertise (360Brew)? Sometimes the answer is simply timing — not every audience is online when you post. Add a strategic first comment and give it another 30 minutes before drawing conclusions.
Check: Did you post at an optimal time? Is the hook strong? Does the topic match your profile expertise (topic-relevance)? Sometimes the answer is simply timing — not every audience is online when you post. Add a strategic first comment and give it another 30 minutes before drawing conclusions.
### "Should I delete and repost?"
Almost never. Deleting and reposting is detected by the algorithm and can result in reduced distribution. The exception: if you spot a major factual error in the first 5 minutes and have <10 impressions.

4
plugins/linkedin-studio/agents/strategy-advisor.md
View file

@ -23,7 +23,7 @@ tools: ["Read", "Glob"]
# Strategy Advisor Agent
You are a LinkedIn growth strategist with expertise in the January 2026 algorithm landscape. You help creators identify their current phase, understand their constraints, and focus on the highest-impact actions for their situation.
You are a LinkedIn growth strategist with expertise in the 2026 algorithm landscape. You help creators identify their current phase, understand their constraints, and focus on the highest-impact actions for their situation.
## Your Mission
@ -431,7 +431,7 @@ Time: [time]
## Common Situations and Responses
### "I'm not getting engagement"
- Check profile-content alignment (360Brew)
- Check profile-content alignment (topic-relevance)
- Audit hook quality
- Verify posting times
- Review first-hour engagement strategy

6
plugins/linkedin-studio/agents/trend-spotter.md
View file

@ -335,7 +335,7 @@ Search 6: "[AI debate OR controversy OR opinion] LinkedIn [this week]"
3. **Audience fit over virality.** A trend your specific audience cares about at score 6.0 beats a viral topic at score 4.0. Relevance compounds; virality fades.
4. **Credibility is non-negotiable.** Never recommend posting on a topic where the creator has no authority. The 360Brew algorithm will penalize off-topic content regardless of how trending it is.
4. **Credibility is non-negotiable.** Never recommend posting on a topic where the creator has no authority. The topic-relevance ranking will penalize off-topic content regardless of how trending it is.
5. **Saturation awareness saves reputation.** Posting the 15th take on a topic makes you look like a follower, not a leader. Better to skip than to add noise.
@ -350,7 +350,7 @@ Search 6: "[AI debate OR controversy OR opinion] LinkedIn [this week]"
| Anti-Pattern | Why It Fails | Instead |
|--------------|--------------|---------|
| Reporting news without perspective | No differentiation, looks like a news feed | Add "So what?" and "Now what?" to every trend |
| Recommending off-topic trends | 360Brew penalty, damages authority | Always check pillar fit and authority score |
| Recommending off-topic trends | topic-relevance penalty, damages authority | Always check pillar fit and authority score |
| Chasing every trend | Dilutes positioning, exhausts creator | Max 2-3 trend posts per week, rest is evergreen |
| Ignoring saturation | Late takes look derivative | Check saturation before recommending timing |
| Same angle every time | Predictable, audience tunes out | Rotate across 8 angles, track recently used |
@ -364,4 +364,4 @@ Read these files for detailed methodology:
- `${CLAUDE_PLUGIN_ROOT}/references/thought-leadership-angles.md` - 8 universal angles, selection framework, combination patterns
- `${CLAUDE_PLUGIN_ROOT}/references/ai-content-framework.md` - Content pillars, trigger framework, source tiers, seasonal calendar
- `${CLAUDE_PLUGIN_ROOT}/references/linkedin-growth-playbook-2025-2026.md` - Trend Translator tactic, first-mover advantage
- `${CLAUDE_PLUGIN_ROOT}/references/algorithm-signals-reference.md` - Engagement signals and 360Brew validation
- `${CLAUDE_PLUGIN_ROOT}/references/algorithm-signals-reference.md` - Engagement signals and profile/topic-relevance validation

6
plugins/linkedin-studio/commands/analyze.md
View file

@ -179,11 +179,11 @@ Based on how much reach dropped:
Based on diagnosis, provide specific action plan.
### If Profile-Content Mismatch (360Brew Failure)
### If Profile-Content Mismatch (topic-relevance Failure)
**Days 1-3: Profile Audit**
`/linkedin:profile` is the canonical 360Brew audit — headline scoring, About section structure, Experience impact statements, Featured curation, Skills alignment, content history check, and network signals. Run it for the per-section checklist and the remediation flow.
`/linkedin:profile` is the canonical topic-relevance audit — headline scoring, About section structure, Experience impact statements, Featured curation, Skills alignment, content history check, and network signals. Run it for the per-section checklist and the remediation flow.
Quick triage if a full audit can wait:
- Headline contains 3-4 topic keywords matching content pillars
@ -224,7 +224,7 @@ Set realistic expectations:
| Suppression Level | Initial Improvement | Baseline Recovery | Full Restoration |
|-------------------|---------------------|-------------------|------------------|
| Mild (25-40% drop) | 7-10 days | 14-21 days | 3-4 weeks |
| Moderate (link / off-topic) | 7-10 days | 14-21 days | 3-4 weeks |
| Moderate (50-70% drop) | 2-3 weeks | 4-6 weeks | 2-3 months |
| Severe (75%+ drop) | 4-6 weeks | 3-6 months | May not be possible |

4
plugins/linkedin-studio/commands/audit.md
View file

@ -58,7 +58,7 @@ For each top-performing post, analyze:
Same analysis for bottom performers:
- What went wrong?
- Common factors in low-performing posts?
- Were any off-topic (360Brew penalty)?
- Were any off-topic (topic-relevance penalty)?
- External links in body?
- Poor timing?
@ -148,7 +148,7 @@ Audit's job here is to name the gap; strategy prescribes the fix. Surface the sc
## Step 6: Profile Alignment Check
`/linkedin:profile` is the canonical 360Brew audit (Headline, About, Experience, Featured, Skills, content history, network signals). Audit's job is to confirm the user's *actual* posting topics align with the profile's *stated* expertise — full per-section checklist and remediation flow lives in `/linkedin:profile`.
`/linkedin:profile` is the canonical topic-relevance audit (Headline, About, Experience, Featured, Skills, content history, network signals). Audit's job is to confirm the user's *actual* posting topics align with the profile's *stated* expertise — full per-section checklist and remediation flow lives in `/linkedin:profile`.
Surface in this audit:
- Whether topics from Step 3 (Topic Distribution) match the profile's stated expertise

4
plugins/linkedin-studio/commands/carousel.md
View file

@ -2,7 +2,7 @@
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,
Carousels/documents are the top-performing organic format on LinkedIn. Guides template selection,
topic definition, and generates copy for each slide plus caption.
Optionally generates slide images via mcp-image (Nano Banana Pro).
Triggers on: "carousel", "slide deck", "pdf post", "swipe post", "multi-slide",
@ -33,7 +33,7 @@ Read `assets/templates/carousel-templates.md` for the 5 templates.
Present the options:
```
LinkedIn carousels get 6.6% average engagement — highest of all formats.
LinkedIn carousels/documents are the top-performing organic format (~7%; see `references/algorithm-signals-reference.md`).
Choose a template:

6
plugins/linkedin-studio/commands/linkedin.md
View file

@ -87,7 +87,7 @@ Present these options to the user:
| Command | Purpose |
|---------|---------|
| `/linkedin:strategy` | Growth strategy + authority building (phase-specific guidance, trajectory adjustments, signature content for Phase 2+) |
| `/linkedin:profile` | 360Brew profile optimization checklist |
| `/linkedin:profile` | profile/topic-relevance optimization checklist |
| `/linkedin:analyze` | Analyze content performance or troubleshoot issues |
| `/linkedin:ab-test` | Design and manage A/B tests for content optimization |
| `/linkedin:audit` | Quarterly content strategy audit |
@ -133,7 +133,7 @@ Use AskUserQuestion to ask:
8. **View calendar** — See scheduled posts and manage queue
9. **Plan content** — Weekly/monthly content planning
10. **Growth strategy & authority** — Plan growth, build signature content, compound authority
11. **Optimize profile** — 360Brew profile audit
11. **Optimize profile** — topic-relevance profile audit
12. **Audit content** — Review what's working and what's not
13. **Competitive analysis** — Learn from other thought leaders
14. **Monetize** — Revenue strategies for thought leadership
@ -168,7 +168,7 @@ If the user's intent is clear from context:
- Mentions "calendar" or "schedule" or "queue" or "upcoming posts" or "what's scheduled" → Route to `/linkedin:calendar`
- Mentions "publish" or "mark as published" or "posted today" or "just published" or "post is live" → Route to `/linkedin:calendar` (publish action)
- Mentions "plan" → Suggest `content-planner` agent
- Mentions "profile" or "360Brew" → Route to `/linkedin:profile`
- Mentions "profile" or "topic-relevance" → Route to `/linkedin:profile`
- Mentions "not working" or "low reach" → Route to `/linkedin:analyze`
- Mentions "strategy" or "growth plan" or "authority" or "build authority" or "signature content" or "greatest hits" or "my best content" → Route to `/linkedin:strategy`
- Mentions "carousel" or "slides" or "slide deck" or "pdf post" or "swipe" or "document post" → Route to `/linkedin:carousel`

4
plugins/linkedin-studio/commands/monetize.md
View file

@ -341,7 +341,7 @@ DM Conversion Framework:
- Not ready: "No rush — follow along and reach out when timing is right"
Response time matters:
- Same day: 40-50% conversion to next step
- Same day: roughly half convert to the next step
- Next day: 20-30% conversion
- 3+ days: <10% conversion
```
@ -492,7 +492,7 @@ ACTIONS FOR NEXT MONTH:
❌ Selling too early (before 1K followers with engagement)
→ Build trust with 8+ weeks of consistent value first
❌ External links in posts (kills reach by 25-40%)
❌ External links in posts (correlate with lower reach — see `references/algorithm-signals-reference.md`)
→ Use first comment for links, or bio link
❌ Generic CTAs ("check out my service")

10
plugins/linkedin-studio/commands/onboarding.md
View file

@ -38,14 +38,14 @@ Read `~/.claude/linkedin-studio.local.md` for current state.
Post templates 5 [✓ Done / ○ Empty]
```
- Use AskUserQuestion: "Would you like to re-run a specific phase?"
1. Re-optimize profile (360Brew) → jump to Phase 1
1. Re-optimize profile (topic-relevance) → 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)
## Phase 1: Profile Optimization (topic-relevance)
```
╔═══════════════════════════════════════╗
@ -54,16 +54,16 @@ If not already onboarded, continue to Phase 1.
```
Explain briefly:
- LinkedIn's 360Brew algorithm (January 2026) validates your profile BEFORE distributing your content
- LinkedIn's topic-relevance ranking (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
1. **Guide me through profile optimization** — I want the full profile/topic-relevance 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`):
**If option 1:** Walk through the core profile/topic-relevance 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)

30
plugins/linkedin-studio/commands/profile.md
View file

@ -1,32 +1,32 @@
---
name: linkedin:profile
description: |
360Brew profile optimization checklist for LinkedIn's January 2026 algorithm update.
profile/topic-relevance optimization checklist for LinkedIn's 2026 algorithm update.
LinkedIn now validates your profile BEFORE distributing content. This command audits
and optimizes your profile for maximum reach. Use when the user mentions "profile",
"360Brew", "profile optimization", "why is my reach low", or wants to improve their
LinkedIn presence. Triggers on: "optimize profile", "360Brew check", "profile audit",
"topic-relevance", "profile optimization", "why is my reach low", or wants to improve their
LinkedIn presence. Triggers on: "optimize profile", "profile/topic-relevance check", "profile audit",
"linkedin profile help", "fix my profile".
allowed-tools:
- Read
- AskUserQuestion
---
# LinkedIn Profile Optimization (360Brew Audit)
# LinkedIn Profile Optimization (Profile/Topic Audit)
You are a LinkedIn profile optimization specialist. Help the user optimize their profile for the 360Brew algorithm that validates profiles BEFORE distributing content.
You are a LinkedIn profile optimization specialist. Help the user optimize their profile for the topic-relevance ranking — profile/topic alignment is a real input into how widely content is distributed.
## Critical Context: 360Brew (January 2026)
## Critical Context: Profile/Topic Relevance
Read `references/algorithm-signals-reference.md` for algorithm mechanics.
**The Fundamental Shift:**
- **Before January 2026:** Post something -> Goes to 10% of audience -> Algorithm tracks engagement
- **After January 2026:** LinkedIn auditions you FIRST. Before your post goes anywhere, the algorithm scans your profile to determine if you're qualified to talk about the topic.
- **In the older feed model:** Post something -> Goes to 10% of audience -> Algorithm tracks engagement
- **In the 2026 relevance model:** profile/topic relevance is weighed alongside engagement — content matched to your demonstrated expertise is distributed more widely (including beyond your network), so an off-topic post from a misaligned profile tends to underperform.
**If profile doesn't match post topic = -40-60% reach before anyone sees it.**
**Profile/topic alignment is a real ranking input — content matched to your demonstrated expertise is distributed more widely (see `references/algorithm-signals-reference.md`).**
## The 360Brew Scoring System
## The Profile/Topic Relevance Factors
LinkedIn's 150B parameter foundation model evaluates five criteria:
@ -62,7 +62,7 @@ Guide the user through each section using AskUserQuestion for interactive feedba
### Section 2: About Section (2,600 characters max)
**Critical:** This is the first signal telling 360Brew what you're qualified to discuss.
**Critical:** This is the first signal telling topic-relevance what you're qualified to discuss.
**Structure:**
@ -124,7 +124,7 @@ Guide the user through each section using AskUserQuestion for interactive feedba
### Section 5: Skills Section
**Critical for 360Brew validation.**
**Critical for profile/topic-relevance validation.**
**Ask the user:** What skills are listed on your profile?
@ -136,7 +136,7 @@ Guide the user through each section using AskUserQuestion for interactive feedba
### Section 6: Network Quality
**360Brew checks if you're connected to professionals in your expertise area.**
**profile/topic-relevance checks if you're connected to professionals in your expertise area.**
**Ask the user:** Who are you primarily connected with? (peers, clients, random connections?)
@ -189,7 +189,7 @@ Based on the audit, provide a prioritized action list:
- Connect with domain experts
- Maintain consistency between profile and content
## The 360Brew Validation Test
## The Profile/Topic Alignment Test
Before posting, the user should ask themselves:
@ -199,6 +199,6 @@ If the answer is no, fix the profile FIRST before posting.
## Reference Files
- `references/algorithm-signals-reference.md` - 360Brew mechanics and signals
- `references/algorithm-signals-reference.md` - relevance-model mechanics and signals
- `references/troubleshooting-guide.md` - Recovery if reach is already down
- `skills/linkedin-studio/SKILL.md` - User's expertise areas and topics

2
plugins/linkedin-studio/commands/react.md
View file

@ -109,7 +109,7 @@ Structure the post:
**CTA:** Engagement question related to the topic.
### Critical Rules:
- **NEVER put the URL in the post body** — LinkedIn suppresses reach 40-50% for external links
- **NEVER put the URL in the post body** — external links correlate with lower reach (see `references/algorithm-signals-reference.md`); use the first comment and lead with value
- Mention the URL should go in the first comment
- The post should stand alone without needing to read the source
- Focus on YOUR perspective, not a summary of the article

10
plugins/linkedin-studio/commands/strategy.md
View file

@ -84,7 +84,7 @@ Based on follower count, place user in the right phase:
- Learning what works
**Focus areas:**
- Profile optimization (360Brew critical)
- Profile optimization (topic-relevance critical)
- Finding your voice
- Establishing consistency
- Building initial engagement habits
@ -171,7 +171,7 @@ Based on their phase, provide detailed guidance.
|----------|-----------|---------|
| Core expertise posts | 3-5x/week | Algorithm learning |
| Strategic commenting | Daily 20 min | Network expansion |
| Profile optimization | Monthly review | 360Brew validation |
| Profile optimization | Monthly review | profile/topic-relevance validation |
| Content experimentation | Ongoing | Finding what works |
**Milestone Markers to Track:**
@ -289,7 +289,7 @@ Once the user is in Phase 2 (3,000+) the growth lever shifts from finding-what-w
**Skip this section in Phase 0–1.** The signal there is consistency + voice discovery, not compounding. Reference it once they cross 3K.
For the canonical profile-alignment audit (headline/About/Experience/Featured/Skills against post topics), run `/linkedin:profile` — the 360Brew checker is the single source. This section covers the content + network side of authority.
For the canonical profile-alignment audit (headline/About/Experience/Featured/Skills against post topics), run `/linkedin:profile` — the profile/topic-relevance checker is the single source. This section covers the content + network side of authority.
### Identify Signature Content
@ -357,7 +357,7 @@ Use AskUserQuestion to pick which derivatives to create.
### Authority Signals Audit (Content + Network)
**Profile signals:** delegated to `/linkedin:profile` (canonical 360Brew audit).
**Profile signals:** delegated to `/linkedin:profile` (canonical topic-relevance audit).
**Content authority:**
- [ ] Consistent posting in expertise areas
@ -516,7 +516,7 @@ Remind them of the long-term view:
- `references/growth-roadmaps.md` - Detailed phase roadmaps
- `references/linkedin-growth-playbook-2025-2026.md` - Comprehensive tactics
- `references/trajectory-strategy-adjustments.md` - Trajectory-based strategy adjustments
- `references/algorithm-signals-reference.md` - 360Brew signals (authority audit)
- `references/algorithm-signals-reference.md` - topic-relevance signals (authority audit)
- `references/collaborations-guide.md` - Partnership strategies
- `references/opportunity-generation.md` - Business development
- `references/newsletter-strategy-guide.md` - For 5K+ followers

2
plugins/linkedin-studio/hooks/prompts/content-quality-gate.md
View file

@ -6,7 +6,7 @@ LINKEDIN CONTENT QUALITY GATE: If the file being written/edited is LinkedIn cont
- If under 110: wasting prime real estate. Expand it.
**Link Check:**
- NO external links (http/https URLs) in the post body. LinkedIn suppresses reach by 40-50% for posts with links.
- NO external links (http/https URLs) in the post body. Body links correlate with lower reach — use the first comment and lead with value (see `references/algorithm-signals-reference.md`).
- If a link is needed, instruct the user to put it in the FIRST COMMENT after posting.
**Tone Check:**

2
plugins/linkedin-studio/hooks/prompts/topic-rotation-gate.md
View file

@ -23,7 +23,7 @@ Count posts per pillar from the `## Recent Posts` section (last 14 days only). I
**Check 3 — Off-topic:**
If the current post does not match ANY of the 5 expertise_areas, flag:
> "OFF-TOPIC WARNING: This post doesn't align with any of your 5 expertise areas. Off-pillar posts weaken your 360Brew topical authority signal. Consider reframing to connect with [closest pillar]."
> "OFF-TOPIC WARNING: This post doesn't align with any of your 5 expertise areas. Off-pillar posts weaken your topic-relevance topical authority signal. Consider reframing to connect with [closest pillar]."
**Step 4: Suggest Alternatives**
If any check flagged, suggest 2-3 underrepresented pillars with context:

2
plugins/linkedin-studio/references/ab-testing-framework.md
View file

@ -211,6 +211,6 @@ Use this template to record completed tests:
---
*Last updated: January 2026*
*Last updated: 2026*
*Methodology adapted from growth marketing A/B testing principles, applied to LinkedIn's sequential posting model with adjustments for platform-specific confounders.*

2
plugins/linkedin-studio/references/first-comment-strategy.md
View file

@ -4,7 +4,7 @@ Your first comment is a strategic tool, not an afterthought. Used correctly, it
## Why First Comments Matter
LinkedIn's 360Brew algorithm penalizes external links in post bodies by 25-40% reach suppression. The first comment is the accepted workaround — but it's much more than a link dump.
External links in the post body correlate with lower reach (correlational, ~38% in 2026; LinkedIn denies an intentional penalty — see `references/algorithm-signals-reference.md`). A first comment is a common hedge — but lead with standalone value either way; it's much more than a link dump.
**First comment benefits:**
- Avoids link penalty while still providing resources

15
plugins/linkedin-studio/references/glossary.md
View file

@ -6,7 +6,7 @@ Alphabetical glossary of specialized terminology used across the plugin. Each te
## 3
### 360Brew
### Profile/topic relevance
LinkedIn's 150-parameter foundation model that validates creator profiles before distributing content. Checks expertise alignment across About section, Experience, content history, network quality, and engagement patterns. Content from unvalidated profiles receives limited distribution.
**Used in:** `references/algorithm-signals-reference.md`, `skills/linkedin-studio/SKILL.md`, `agents/content-optimizer.md`
@ -21,7 +21,7 @@ Engagement priming technique performed 15-20 minutes before posting: identify 5
## A
### Algorithm Penalty
Negative signal triggers that reduce post reach. Known penalties: 5+ hashtags (-68%), external links in body (-25-40%), off-topic posts (-40-60%), engagement bait phrases (-30-50%).
Signal triggers that correlate with lower reach: excessive hashtags, external links in the post body, off-topic posts (weak profile/topic alignment), and engagement-bait phrases. Magnitudes are directional — see `references/algorithm-signals-reference.md`.
**Used in:** `references/algorithm-signals-reference.md`, `references/linkedin-formats.md`
@ -31,7 +31,7 @@ Systematic application of 8 universal thought leadership angles across the same
**Used in:** `references/thought-leadership-angles.md`, `agents/content-planner.md`, `agents/trend-spotter.md`
### Authority Score
Composite metric measuring a creator's established expertise on a topic, derived from posting consistency, engagement quality, profile alignment (360Brew), and network validation. Higher authority unlocks broader distribution.
Composite metric measuring a creator's established expertise on a topic, derived from posting consistency, engagement quality, profile alignment (topic-relevance), and network validation. Higher authority unlocks broader distribution.
**Used in:** `commands/strategy.md` (authority building absorbed in v2.0.0), `references/algorithm-signals-reference.md`
@ -65,7 +65,7 @@ Optimal content type distribution: 70% Educational (teach, frameworks, how-to),
**Used in:** `skills/linkedin-studio/SKILL.md`, `agents/content-planner.md`, `references/linkedin-growth-playbook-2025-2026.md`
### Content Pillars
3-5 core expertise areas that define your LinkedIn focus. Used for topic consistency validation, gap analysis in content planning, and 360Brew alignment checks. Example for AI content: News, Implementation, Strategy, Tools.
3-5 core expertise areas that define your LinkedIn focus. Used for topic consistency validation, gap analysis in content planning, and topic-relevance alignment checks. Example for AI content: News, Implementation, Strategy, Tools.
**Used in:** `agents/content-planner.md`, `references/ai-content-framework.md`, `skills/linkedin-studio/SKILL.md`
@ -113,7 +113,7 @@ Posts maintaining relevance and engagement potential beyond the initial publicat
**Used in:** `agents/content-repurposer.md`, `references/articles-strategy-guide.md`
### Expertise Verification System
LinkedIn's mechanism for validating creator authority: professional history, posting consistency on specific topics, relevant engagement, domain vocabulary usage, and performance track record. Feeds into 360Brew.
LinkedIn's mechanism for validating creator authority: professional history, posting consistency on specific topics, relevant engagement, domain vocabulary usage, and performance track record. Feeds into topic-relevance.
**Used in:** `references/linkedin-growth-playbook-2025-2026.md`
@ -127,7 +127,7 @@ Critical window (0-60 minutes post-publication) determining ~70% of a post's tot
**Used in:** `skills/linkedin-studio/SKILL.md`, `references/linkedin-formats.md`, `agents/engagement-coach.md`
### Four-Stage Distribution Model
Sequential post distribution: Stage 1 (0-30s: Quality classifier + 360Brew validation) → Stage 2 (0-90min: Test to 6-10% of connections) → Stage 3 (1-24h: Extended if velocity good) → Stage 4 (24-72h+: Evergreen circulation).
Sequential post distribution: Stage 1 (0-30s: Quality classifier + profile/topic-relevance validation) → Stage 2 (0-90min: Test to 6-10% of connections) → Stage 3 (1-24h: Extended if velocity good) → Stage 4 (24-72h+: Evergreen circulation).
**Used in:** `references/algorithm-signals-reference.md`
@ -168,7 +168,7 @@ LinkedIn's feature (2025-2026) measuring user interest in specific topics indepe
## L
### Link Penalty
Algorithm penalty of -25-40% reach for external links placed in the post body. LinkedIn prioritizes keeping users on-platform. Workaround: place links in the first comment instead, or use native document format.
External links in the post body correlate with lower reach (correlational, ~38% in 2026; LinkedIn denies an intentional penalty — see `references/algorithm-signals-reference.md`). Lead with standalone value; a first comment is a hedge, not a fix, and native document format is the durable answer.
**Used in:** `references/algorithm-signals-reference.md`, `references/first-comment-strategy.md`
@ -249,3 +249,4 @@ Deviation from established personal voice profile. Measured across 6 dimensions:
Quantified signature of a creator's unique writing style across sentence structure, vocabulary, hook preferences, storytelling approach, tone, and formatting. Updated quarterly. Identity-level traits (avoided words, tone, humor) are protected from automatic modification.
**Used in:** `agents/voice-trainer.md`, `assets/voice-samples/authentic-voice-samples.md`

2
plugins/linkedin-studio/references/growth-roadmaps.md
View file

@ -143,7 +143,7 @@ The 90-day system covers 0-2K followers. This section provides the roadmap from
|----------|-----------|---------|
| Core expertise posts | 3-5x/week | Algorithm learning |
| Strategic commenting | Daily 20 min | Network expansion |
| Profile optimization | Monthly review | 360Brew validation |
| Profile optimization | Monthly review | profile/topic-relevance validation |
| Content experimentation | Ongoing | Finding what works |
**Growth Levers:**

10
plugins/linkedin-studio/references/linkedin-formats.md
View file

@ -7,7 +7,7 @@
- Top 1% of creators: content rose from 15% to 31% of all feeds
- Algorithm now prioritizes topical authority over everything else
- Dwell time became the golden metric
- External links penalized 25-40%
- External links in the body correlate with lower reach (see `references/algorithm-signals-reference.md`)
- Hashtags died as discovery mechanism (late 2024)
**What This Means for Format Selection:**
@ -47,7 +47,7 @@ Choosing the right format isn't just about engagement rates—it's about underst
- Best for: Frameworks, step-by-step guides, data visualization
**2. Native documents (PDFs): High engagement (historically 24.42%, likely inflated)**
- Note: The 24.42% figure is from 2025 studies that conflated PDF documents with multi-image carousels. Current carousel-specific data shows 1.92% engagement rate (still highest of all formats). PDF documents may still perform higher due to download value.
- Note: documents/carousels are the top organic format (~7%; see `references/algorithm-signals-reference.md`). Cross-study rates (7% / 21.8% / 49.5%) differ by denominator/methodology, not by which format wins — do not treat any single figure as the carousel rate.
- Great for frameworks, step-by-step content, detailed insights
- Keeps users on platform (no external link penalty)
- Downloadable = high perceived value
@ -87,7 +87,7 @@ Choosing the right format isn't just about engagement rates—it's about underst
- Best for: Audience research, engagement spikes, starting conversations
**7. Link posts: AVOID or use strategically**
- External links reduce reach by 25-40%
- External links in the body correlate with lower reach (see `references/algorithm-signals-reference.md`)
- 4.9% more impressions than no-link posts (OLD DATA - now penalized)
- Platform wants to keep users on LinkedIn
- If must link: Use native LinkedIn article or wait until second-tier comment
@ -194,7 +194,7 @@ Algorithm prioritizes content that keeps users on platform longer.
### The External Link Penalty
**Critical reality:**
- External links reduce reach by 25-40%
- External links in the body correlate with lower reach (see `references/algorithm-signals-reference.md`)
- Links in post body get penalized most heavily
- First comment links are tracked but acceptable as workaround when necessary
- Old strategy of "drive traffic to website" is now algorithmically punished
@ -263,7 +263,7 @@ Immediate engagement in first hour is critical for triggering subsequent waves.
- Strong first-hour engagement velocity
**What the algorithm penalizes:**
- External links (25-40% reach reduction)
- External links (correlate with lower reach — see `references/algorithm-signals-reference.md`)
- Engagement bait phrases
- AI-generated generic comments
- Topic inconsistency (confuses your expertise)

6
plugins/linkedin-studio/references/linkedin-growth-playbook-2025-2026.md
View file

@ -41,7 +41,7 @@ Complete reference guide for growing from hundreds to thousands of engaged follo
### Engagement Quality Hierarchy
**Comment Value:**
- Comments: **15x more reach** than likes
- Comments rank above likes in the engagement order (saves > shares > quality comments > reactions; see `references/algorithm-signals-reference.md`)
- Comments: **5x more effective** than reshares
- Comments over 15 words: **2x impact** vs shorter ones
- Comments from relevant professionals: Significantly higher weight than generic responses
@ -91,7 +91,7 @@ LinkedIn doesn't formally boost new creators, but multiple mechanisms create a d
**Why New Creators Get Natural Advantages:**
1. **Clean Algorithmic Slate:** No negative history, no low-performing posts dragging down distribution. The algorithm evaluates new creators purely on current content quality.
2. **Interest-Based Distribution via 360Brew:** The 2025-2026 interest graph actively seeks diverse voices for each topic. New creators with clear expertise signals get surfaced to relevant audiences immediately.
2. **Interest-Based Distribution via topic-relevance:** The 2025-2026 interest graph actively seeks diverse voices for each topic. New creators with clear expertise signals get surfaced to relevant audiences immediately.
3. **Feed Diversification:** LinkedIn explicitly increased content from outside users' networks by 40%. New creators benefit disproportionately — they ARE the fresh voices the algorithm seeks.
4. **Faster Relative Growth Rates:** Buffer's 2025 data shows accounts with 1K-5K followers grow 40%+ YoY faster than large accounts (100K+). Small accounts compound faster when they post consistently.
5. **No Audience Fatigue:** Established creators face diminishing returns with existing followers. New creators present novel perspectives to every viewer.
@ -102,7 +102,7 @@ The advantage isn't a formal "boost" with a cliff — it's a window where consis
**Days 1-30: Signal Establishment**
- Algorithm is mapping your expertise areas from profile + content
- Every post teaches 360Brew what topics you cover
- Every post teaches topic-relevance what topics you cover
- Format experiments have low cost (small audience, no expectations)
- Priority: Post 4-5x/week to give the algorithm enough data points
- Focus: Topical consistency within your 5 expertise areas

2
plugins/linkedin-studio/references/linkedin-monetization-strategies.md
View file

@ -642,7 +642,7 @@ This isn't vanity metrics—it's market perception of your expertise.
**The error:** Constantly driving traffic away from LinkedIn
**Why it fails:**
- 25-40% reach reduction for external links
- External links in the body correlate with lower reach (see `references/algorithm-signals-reference.md`)
- Algorithm wants users on platform
- Looks desperate for traffic
- Breaks the value-first approach

2
plugins/linkedin-studio/references/linkedin-visual-style.md
View file

@ -92,7 +92,7 @@ LinkedIn users scroll fast. Your visual has 1-2 seconds to communicate its value
### Carousel (PDF Document)
**Best for:** Frameworks, how-to guides, listicles, comparisons, stories
**Engagement pattern:** Highest overall engagement rate (6.6%), excellent dwell time
**Engagement pattern:** Top-performing organic format (~7%; see `references/algorithm-signals-reference.md`), excellent dwell time
**Use when:** Content has 5+ distinct points that benefit from visual separation
**Design pattern per slide:**

4
plugins/linkedin-studio/references/trajectory-strategy-adjustments.md
View file

@ -26,7 +26,7 @@ Before adjusting tactics, identify root causes:
1. **Consistency gap:** Actual posts/week < weekly goal for 3+ consecutive weeks
2. **Topic scatter:** Posts span 6+ topics with no clear pillar dominance
3. **Profile-content mismatch:** 360Brew misalignment between headline/about and post topics
3. **Profile-content mismatch:** profile/topic misalignment between headline/about and post topics
4. **Engagement vacuum:** Average comments < 5 per post, no regular commenters
5. **Format stagnation:** 90%+ text-only posts, no carousels/documents
6. **Network isolation:** No collaborations in last 60 days, commenting on < 5 creators/day
@ -60,7 +60,7 @@ Before adjusting tactics, identify root causes:
- `/linkedin:audit` -- full strategy review with trajectory overlay
- `/linkedin:strategy` -- recalibrate growth plan
- `/linkedin:pipeline` -- activate full content pipeline for volume increase
- `/linkedin:profile` -- 360Brew profile optimization
- `/linkedin:profile` -- profile/topic-relevance optimization
---

8
plugins/linkedin-studio/references/troubleshooting-guide.md
View file

@ -121,7 +121,7 @@ Understanding how to recover from algorithmic suppression is critical for long-t
- Profile views declining despite posting
**Common causes:**
1. **Profile-content mismatch (360Brew failure)** - Algorithm validates profile before distributing content
1. **Profile-content mismatch (profile/topic mismatch)** - Algorithm validates profile before distributing content
2. **Topic inconsistency** - Confused algorithm about your expertise
3. **Engagement pod detection** - Artificial engagement patterns flagged
4. **External link overuse** - LinkedIn penalizes directing traffic away
@ -137,7 +137,7 @@ Understanding how to recover from algorithmic suppression is critical for long-t
- [ ] Update headline with 3-4 topic keywords matching your content
- [ ] Rewrite About section with clear expertise areas
- [ ] Remove or update irrelevant Featured content
- [ ] Check Skills section matches post topics (critical for 360Brew)
- [ ] Check Skills section matches post topics (critical for topic-relevance)
- [ ] Request 2-3 skill endorsements from connections in your content areas
- [ ] Review Experience descriptions for topic alignment
@ -171,7 +171,7 @@ Understanding how to recover from algorithmic suppression is critical for long-t
## Timeline Expectations
### Mild Suppression (25-40% reach drop)
### Moderate Suppression (link / off-topic)
- Initial improvement: 7-10 days
- Recovery to baseline: 14-21 days
@ -218,7 +218,7 @@ Maintain these practices to avoid future suppression:
- [ ] Avoid engagement pods entirely (easily detected)
- [ ] Limit external links to 1x per week maximum
- [ ] Monitor reach weekly for early warning signs
- [ ] Keep profile and content aligned (360Brew validation)
- [ ] Keep profile and content aligned (profile/topic-relevance validation)
- [ ] Respond to all comments within first hour
- [ ] Engage with others' content daily (10+ substantive comments)
- [ ] Use native formats primarily (text, carousels, LinkedIn video)

19
plugins/linkedin-studio/scripts/test-runner.sh
View file

@ -179,6 +179,25 @@ fi
echo ""
# --- Section 8: Algorithm-Stat Consistency ---
echo "--- Algorithm-Stat Consistency ---"
# The single source of truth for algorithm magnitudes is
# references/algorithm-signals-reference.md. After the Phase-0 reconciliation,
# stale/competing magnitudes — and the unpublishable model brand/date — must not
# reappear anywhere else (cite the reference, do not restate). This enforces
# "one value per effect" by forbidding the known competing values from returning.
STALE_STATS='40-50%|25-40%|6\.6%|1\.92%|15x more reach|-40-60%|360Brew|January 2026'
STAT_HITS=$(grep -rnE "$STALE_STATS" references/ commands/ skills/ hooks/prompts/ CLAUDE.md README.md 2>/dev/null | grep -v 'algorithm-signals-reference' || true)
if [ -z "$STAT_HITS" ]; then
pass "no stale algorithm magnitudes / model brand outside the canonical reference"
else
fail "stale algorithm stat(s) reintroduced — cite algorithm-signals-reference.md instead:"
echo "$STAT_HITS"
fi
echo ""
# --- Summary ---
echo "================================================"
echo "RESULTS"

4
plugins/linkedin-studio/skills/linkedin-analytics/SKILL.md
View file

@ -106,8 +106,8 @@ Is your reach down?
### Common Causes
1. **360Brew profile mismatch** -- Topic doesn't align with profile (see `references/algorithm-signals-reference.md`)
2. **External link penalty** -- Link in post body causes 40-50% reach suppression
1. **topic-relevance profile mismatch** -- Topic doesn't align with profile (see `references/algorithm-signals-reference.md`)
2. **External link reach effect** -- Links in the post body correlate with lower reach (see `references/algorithm-signals-reference.md`)
3. **Engagement drop** -- Not doing pre-post engagement (5x5x5 method)
4. **Topic inconsistency** -- Posting outside your established expertise areas
5. **Format fatigue** -- Same format every post, audience stops engaging

10
plugins/linkedin-studio/skills/linkedin-studio/SKILL.md
View file

@ -62,9 +62,9 @@ This plugin uses **6 focused skills**. This main skill contains shared knowledge
---
### Algorithm Context (360Brew - January 2026)
### Algorithm Context (Profile/Topic Relevance, 2026)
LinkedIn's 360Brew algorithm now validates your profile across 5 criteria (About, Experience, Content History, Network, Engagement Patterns) BEFORE distributing content. Strong profile alignment = wider distribution. See the `linkedin-voice` skill for detailed profile optimization guidance and the full 360Brew framework.
LinkedIn's topic-relevance ranking now validates your profile across 5 criteria (About, Experience, Content History, Network, Engagement Patterns) BEFORE distributing content. Strong profile alignment = wider distribution. See the `linkedin-voice` skill for detailed profile optimization guidance and the full relevance-model framework.
---
@ -74,9 +74,9 @@ These rules apply to ALL content created by any skill or command:
1. **Hook:** 110-140 characters (mobile cutoff threshold)
2. **Post length:** 1,200-1,800 chars (standard), 150-500 chars (quick)
3. **No external links** in post body (40-50% reach suppression)
3. **No external links** in post body (correlate with lower reach — see `references/algorithm-signals-reference.md`)
4. **No corporate buzzwords:** leverage, synergy, paradigm shift, thought leader, disruptive, value proposition, ecosystem, holistic approach
5. **Topic alignment:** Must align with user's 5 core expertise areas (360Brew signal)
5. **Topic alignment:** Must align with user's 5 core expertise areas (topic-relevance signal)
6. **Voice:** Always read `assets/voice-samples/` before generating content
7. **Quality scorecard:** See `assets/checklists/quality-scorecard.md`
@ -122,7 +122,7 @@ These rules apply to ALL content created by any skill or command:
| `/linkedin:react` | URL-to-post pipeline -- react to articles, news, research |
| `/linkedin:post` | Full post creation (10-15 min workflow) |
| `/linkedin:quick` | 5-minute quick post (3-line formula) |
| `/linkedin:profile` | 360Brew profile optimization |
| `/linkedin:profile` | profile/topic-relevance optimization |
| `/linkedin:analyze` | Content/performance analysis |
| `/linkedin:ab-test` | Design and manage A/B content tests |
| `/linkedin:strategy` | Growth strategy planning |

20
plugins/linkedin-studio/skills/linkedin-voice/SKILL.md
View file

@ -2,14 +2,14 @@
name: linkedin-voice
description: |
LinkedIn voice training, profile optimization, content differentiation, and authenticity
checking. Covers voice profile building, drift detection, 360Brew profile alignment,
checking. Covers voice profile building, drift detection, topic-relevance profile alignment,
originality scoring, and maintaining authentic presence on LinkedIn.
This skill should be used when the user wants to optimize their LinkedIn profile, train their voice,
check content originality, detect voice drift, build a voice profile, or ensure
their content is differentiated from commodity content.
Triggers on: "optimize my LinkedIn profile", "360Brew", "profile optimization",
Triggers on: "optimize my LinkedIn profile", "topic-relevance", "profile optimization",
"analyze my voice", "build voice profile", "voice audit", "does this sound like me",
"voice drift", "is this original", "differentiation check", "originality check",
"commodity content", "unique angle", "am I authentic", "my writing style",
@ -18,7 +18,7 @@ description: |
## Voice and Profile Domain
This skill covers voice identity, profile optimization for the 360Brew algorithm, content differentiation, and authenticity maintenance.
This skill covers voice identity, profile optimization for the topic-relevance ranking, content differentiation, and authenticity maintenance.
---
@ -26,7 +26,7 @@ This skill covers voice identity, profile optimization for the 360Brew algorithm
| Command | Purpose | When to Use |
|---------|---------|-------------|
| `/linkedin:profile` | 360Brew profile optimization | Profile setup and audit |
| `/linkedin:profile` | profile/topic-relevance optimization | Profile setup and audit |
## Agents
@ -37,17 +37,17 @@ This skill covers voice identity, profile optimization for the 360Brew algorithm
---
## 360Brew Profile Validation (January 2026)
## Profile/Topic Relevance Validation
**This is the most significant LinkedIn algorithm change since the platform launched.**
### The Fundamental Shift
**Before January 2026:** Post something -> Goes to 10% of your audience -> LinkedIn tracks engagement -> Decides if more people should see it.
**In the older feed model:** Post something -> Goes to 10% of your audience -> LinkedIn tracks engagement -> Decides if more people should see it.
**After January 2026:** LinkedIn auditions you FIRST. Before your post goes anywhere, the algorithm scans your profile to determine if you're actually qualified to talk about the topic.
**In the 2026 relevance model:** profile/topic relevance is weighed alongside engagement — content matched to your demonstrated expertise is distributed more widely (including beyond your network), so an off-topic post from a misaligned profile tends to underperform.
### The 360Brew Scoring System
### The Profile/Topic Relevance Factors
LinkedIn's 150B parameter foundation model evaluates **five criteria** before your post reaches anyone:
@ -77,7 +77,7 @@ For detailed algorithm mechanics, see `references/algorithm-signals-reference.md
### About Section (CRITICAL)
Your About section is the **first signal** telling 360Brew what you're qualified to discuss.
Your About section is the **first signal** telling topic-relevance what you're qualified to discuss.
**Structure for optimization:**
@ -197,7 +197,7 @@ The differentiation-checker agent evaluates content across five dimensions:
| File | When to Read |
|------|--------------|
| `references/algorithm-signals-reference.md` | Profile optimization, 360Brew |
| `references/algorithm-signals-reference.md` | Profile optimization, topic-relevance |
| `references/linkedin-visual-style.md` | Visual identity consistency |
| `assets/voice-samples/` | Voice reference (always read before content creation) |
| `config/user-profile.template.md` | User personalization setup |