Establish a single governance document at marketplace root and copy it into each of the 9 plugins so every plugin folder remains 100% self-contained. Replace the inconsistent provocative blurb across all READMEs with a uniform fork-and-own paragraph that links to the local GOVERNANCE.md. [skip-docs] Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
26 KiB
LinkedIn Thought Leadership Plugin for Claude Code
Build authentic LinkedIn authority through algorithmic understanding, strategic consistency, and AI-assisted content creation.
Solo-maintained, fork-and-own. This plugin is a starting point, not a vendor product. Issues are welcome as signals; pull requests are not accepted. See GOVERNANCE.md for the full model and what upstream provides.
AI-generated: all code produced by Claude Code through dialog-driven development. Full disclosure →
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.
Table of Contents
- What's New in v1.2.0
- What Is This?
- Quick Start
- Commands
- Agent Architecture
- Knowledge Base
- Skills
- Hooks & Automation
- Analytics System
- Personalization Engine
- Workflow Examples
- Content Quality Rules
- Configuration
- What This Plugin Does Not Cover
- Version History
- License
What's New in v1.2.0
Friction reduction release — fewer steps, faster output, smarter defaults.
- Auto-clipboard — All 8 content commands (
post,quick,react,pipeline,first-post,video,multiplatform,carousel) automatically copy finished content to your clipboard. No more manual copy-paste - Reduced interactive steps — Angle, format, and post type are inferred from context. Maximum 2 questions per post (down from 4-6)
- Deterministic state management — Post tracking, streak updates, and content history are handled by
state-updater.mjs(pure functions, tested, no AI involved). Content history auto-prunes entries older than 90 days - MCP image carousel pipeline —
/linkedin:carouselcan generate professional slide images via mcp-image with text overlays (1080x1350, 3:4 ratio). Falls back to Mermaid diagrams or text-based slides - Progressive onboarding — New users see a cleaner experience: personalization score hidden until 3+ posts, voice guardian suppressed until 5+ voice samples
- iCal calendar integration —
/linkedin:batchgenerates an.icsfile importable into macOS Calendar, Google Calendar, or Outlook. Each post gets a calendar event with reminders
What Is This?
This plugin gives you a complete LinkedIn thought leadership system inside Claude Code. Instead of staring at a blank post editor, you work through structured workflows that handle ideation, drafting, optimization, scheduling, publishing, and post-publish analytics — all calibrated to how LinkedIn's algorithm actually works.
Key capabilities:
- 360Brew profile optimization aligned with LinkedIn's AI-first content distribution (January 2026 update)
- Content Matrix System that generates 40+ post ideas from a single topic using 8 universal thought leadership angles
- Full content pipeline from ideation through post-publish 48-hour monitoring
- Batch content creation — produce a full week of posts in one session
- Analytics pipeline — import LinkedIn CSV exports, parse into structured JSON, generate performance reports
- Voice training — learns your authentic writing style and flags drift
- Growth strategy — phase-specific guidance from foundation (0-1K followers) through authority (10K+)
- Monetization and speaking — readiness assessment, lead magnets, conference CFP templates
- Video scripting — structured scripts for 30s/60s/90s/2min LinkedIn video
- Multi-platform repurposing — adapt LinkedIn content for Twitter/X, newsletters, blogs, slides
- A/B testing framework — design and track content experiments
Tip
Start with
/linkedin:profileto optimize for 360Brew, then/linkedin:setupto personalize, then/linkedin:postto create your first post.
Quick Start
Prerequisites
- Claude Code with plugin support enabled
- Node.js 18+ (for hooks and analytics CLI; analytics requires
tsx:cd scripts/analytics && npm install)
Installation
Add the marketplace and browse plugins with /plugin:
claude plugin marketplace add https://git.fromaitochitta.com/open/ktg-plugin-marketplace.git
Or enable directly in ~/.claude/settings.json:
{
"enabledPlugins": {
"linkedin-thought-leadership@ktg-plugin-marketplace": true
}
}
Get Started (5 minutes)
Run the onboarding wizard — it walks you through profile, setup, and your first post in one flow:
/linkedin:onboarding
The wizard handles everything: 360Brew profile checklist, voice and user profile setup, and a guided first post.
Already Set Up?
| Goal | Command |
|---|---|
| Write a post | /linkedin:post |
| Quick 5-min post | /linkedin:quick |
| React to an article | /linkedin:react |
| View your stats | /linkedin:report |
| See all commands | /linkedin |
Commands
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
| Command | Description |
|---|---|
/linkedin:post |
Full interactive post creation with angle selection, format choice, and refinement. Best for substantial posts (1,200-1,800 characters). |
/linkedin:quick |
5-minute quick post using the 3-line formula. Target: 150-500 characters. Best for reactions, observations, tips, and questions. |
/linkedin:templates |
Browse and apply proven post templates. 8 post types with fill-in-the-blank structures. |
/linkedin:pipeline |
Full end-to-end content pipeline from idea to published post. Guides through ideation, drafting, optimization, scheduling, pre-engagement, publishing, and post-analysis. |
/linkedin:batch |
Create a full week of LinkedIn content in one session. Input one theme, output 3-5 posts with varying angles and formats. Writes to scheduling queue. |
/linkedin:calendar |
View and manage the post scheduling queue — upcoming, overdue, published. |
/linkedin:publish |
Mark scheduled posts as published. Updates state and streak tracking. |
/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. |
Analytics
| Command | Description |
|---|---|
/linkedin:analyze |
Analyze content performance and troubleshoot engagement issues. Diagnoses algorithm penalties, profile-content mismatches, and reach drops. |
/linkedin:audit |
Periodic content strategy audit. Reviews top/bottom posts, topic distribution, format mix, and engagement trends. Run quarterly. |
/linkedin:report |
Generate weekly performance report from imported analytics data. Shows key metrics, top performers, trends, and actionable alerts. |
/linkedin:import |
Import LinkedIn analytics CSV export into structured JSON. Auto-detects files in ~/Downloads, parses CSV, detects anomalies. |
/linkedin:competitive |
Competitive analysis of other thought leaders in your niche. Analyzes posting frequency, content types, hooks, and identifies differentiation opportunities. |
/linkedin:ab-test |
Design and manage A/B content tests. Track experiments across post variations. |
Strategy
| Command | Description |
|---|---|
/linkedin:strategy |
Growth strategy planning based on your follower level. Phase-specific guidance from foundation (0-1K) through authority (10K+). |
/linkedin:authority |
Systematic authority building. Tracks cited/shared posts, identifies signature content, builds repost schedules, and monitors growing influence. |
/linkedin:monetize |
Monetization strategy with scored readiness assessment, stage-specific action plans, lead magnet blueprints, DM conversion workflows, and revenue dashboards. |
/linkedin:speaking |
Generate speaking opportunities. Speaker readiness assessment, conference search, talk abstract templates, speaker bio variants, CFP templates, and pipeline tracking. |
/linkedin:collab |
Orchestrate collaborations with other thought leaders. Partner scoring, 12 collaboration formats, outreach templates, and partnership frameworks. |
Profile & Setup
| Command | Description |
|---|---|
/linkedin:profile |
360Brew profile 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. |
Agent Architecture
The plugin delegates specialized work to 16 purpose-built agents. Each agent has its own model assignment, color identity, and focused responsibility.
| Agent | Model | Color | Primary Responsibility |
|---|---|---|---|
content-optimizer |
Sonnet | Blue | Optimize posts against algorithm signals, hooks, CTAs |
strategy-advisor |
Sonnet | Green | Growth strategy and phase-specific guidance |
analytics-interpreter |
Sonnet | Yellow | Pattern discovery from analytics data |
engagement-coach |
Haiku | Magenta | 5x5x5 method and first-hour engagement tactics |
content-planner |
Sonnet | Cyan | Weekly/monthly content calendars and mix enforcement |
content-tracker |
Haiku | Orange | Plan vs. published accountability tracking |
performance-reporter |
Sonnet | Amber | Weekly/monthly performance reports |
network-builder |
Sonnet | Teal | Strategic networking, connection scoring, DM templates |
content-repurposer |
Sonnet | Purple | Format conversion and evergreen content refresh |
comment-strategist |
Sonnet | Red | CEA commenting strategy and target selection |
trend-spotter |
Sonnet | White | Trending topics, opportunity scoring, first-mover assessment |
voice-trainer |
Sonnet | Pink | Voice profile building and drift detection |
differentiation-checker |
Sonnet | Gray | Originality scoring and commodity content detection |
post-feedback-monitor |
Haiku | Lime | Post-publish 48h monitoring and real-time interventions |
personalization-scorer |
Haiku | Indigo | Asset completeness scoring and setup recommendations |
video-scripter |
Sonnet | Violet | Video script creation with pacing and visual cues |
Content Pipeline
Agents collaborate across the end-to-end content lifecycle:
trend-spotter --> content-planner --> differentiation-checker --> content-optimizer --> [PUBLISH]
| |
voice-trainer engagement-coach
|
content-tracker --> performance-reporter comment-strategist
Parallel support agents: strategy-advisor, analytics-interpreter, network-builder, content-repurposer, video-scripter.
Which Agent Do I Need?
| Scenario | Agent |
|---|---|
| "Make this post better" | content-optimizer |
| "What should I post about?" | content-planner, trend-spotter |
| "Is this original enough?" | differentiation-checker |
| "Plan my week's content" | content-planner |
| "How did I do this week?" | performance-reporter |
| "Analyze my LinkedIn data" | analytics-interpreter |
| "Help me engage more" | engagement-coach |
| "Who should I comment on?" | comment-strategist |
| "Build my network" | network-builder |
| "Does this sound like me?" | voice-trainer |
| "Repurpose my best post" | content-repurposer |
| "What's trending in my field?" | trend-spotter |
| "How do I monetize?" | strategy-advisor |
| "How is my latest post doing?" | post-feedback-monitor |
| "How personalized is my plugin?" | personalization-scorer |
| "Write a LinkedIn video script" | video-scripter |
Knowledge Base
The plugin includes 24 reference documents covering the full LinkedIn thought leadership domain:
| Category | Document | When to Use |
|---|---|---|
| Algorithm | algorithm-signals-reference.md |
Profile setup, troubleshooting reach |
| Angles | thought-leadership-angles.md |
Choosing post angle (8 universal angles) |
| Engagement | engagement-frameworks.md |
Writing hooks, CTAs, 5x5x5 method |
| Formats | linkedin-formats.md |
Choosing content format |
| Growth | linkedin-growth-playbook-2025-2026.md |
Strategy deep-dive |
| Monetization | linkedin-monetization-strategies.md |
Revenue planning |
| Newsletter | newsletter-strategy-guide.md |
Newsletter strategy (5,000+ followers) |
| Articles | articles-strategy-guide.md |
Long-form content |
| Roadmaps | growth-roadmaps.md |
Monthly planning |
| Low-frequency | low-frequency-posting-strategy.md |
2-3x/week strategy |
| Collaborations | collaborations-guide.md |
Partnership strategy |
| Opportunities | opportunity-generation.md |
Business development |
| Analytics | analytics-tools-guide.md |
Finding your edge |
| Troubleshooting | troubleshooting-guide.md |
When reach drops |
| URLs | url-processing-templates.md |
Converting external content |
| AI Content | ai-content-framework.md |
AI-specific angles |
| First Comment | first-comment-strategy.md |
Comment templates and timing |
| Visual Style | linkedin-visual-style.md |
Image and carousel specs |
| Polls | poll-strategy-guide.md |
Poll question types and follow-up |
| A/B Testing | ab-testing-framework.md |
Content experiment design |
| Scheduling | scheduling-strategy.md |
Optimal posting times and rotation |
| Trajectory | trajectory-strategy-adjustments.md |
Growth trajectory adjustments |
| Video | video-strategy-guide.md |
LinkedIn video best practices |
| Glossary | glossary.md |
38 plugin-specific terms |
Skills
Six domain-specific skills organize the plugin's knowledge and route commands to the right context:
| Skill | Domain | Commands Routed |
|---|---|---|
linkedin-thought-leadership |
Router + shared knowledge (algorithm, quality rules) | /linkedin, /linkedin:setup |
linkedin-content-creation |
Posts, templates, batch, pipeline, video, calendar | /linkedin:post, :quick, :templates, :pipeline, :batch, :calendar, :publish, :video, :multiplatform |
linkedin-analytics |
Analysis, reporting, import, A/B testing | /linkedin:analyze, :audit, :import, :report, :ab-test |
linkedin-strategy |
Growth, authority, competitive, monetization | /linkedin:strategy, :authority, :competitive, :monetize |
linkedin-networking |
Engagement, collaborations, speaking | /linkedin:speaking, :collab |
linkedin-voice |
Voice training, profile optimization, differentiation | /linkedin:profile |
Hooks & Automation
9 hooks across 7 events provide automated quality gates, state management, and proactive reminders. All hooks are Node.js (.mjs) for cross-platform support.
| Event | Type | Purpose |
|---|---|---|
SessionStart |
command | Load persistent state, posting metrics, REMEMBER.md context, and 10K milestone tracker |
PreToolUse (Write|Edit) |
command | Content quality gate — hook length, link check, tone, post length |
PreToolUse (Write|Edit) |
command | Voice guardian — AI authenticity check and voice matching |
PreToolUse (Write|Edit) |
command | Topic rotation gate — no back-to-back same pillar, no pillar >50% in 14-day window |
Stop |
command | Update state file with posting metrics and pre-publish reminders |
UserPromptSubmit |
command | LinkedIn context enrichment based on prompt keywords (two-tier matching) |
PostToolUse (Write) |
command | Post-creation automation: alternative hooks, posting time, 5x5x5 reminder |
PreCompact |
command | Preserve critical LinkedIn context during context compaction |
Notification (idle_prompt) |
command | Proactive posting reminders: streak risk, weekly goals, optimal windows (rate-limited 30min) |
How Hooks Collaborate
PreToolUse hooks use a shared content-gatekeeper (content-gatekeeper.mjs) that first checks isLinkedInContent() before injecting the relevant prompt. This prevents false positives on non-LinkedIn file edits.
Session markers (/tmp/linkedin-hooks/session-active) are set when LinkedIn content is detected. The Stop hook only fires state updates if this marker exists (max 12h staleness). The Notification hook rate-limits via a separate marker with a 30-minute cooldown.
Note
Prompt content lives in
hooks/prompts/*.mdand is loaded dynamically at runtime. The compiledhooks.jsonis generated fromhooks.template.json— do not edit it directly.
Analytics System
A Node.js CLI tool for parsing LinkedIn CSV exports into structured JSON.
Workflow
- Export analytics CSV from LinkedIn
- Place in
assets/analytics/exports/(or use auto-detect from ~/Downloads) - Run
/linkedin:importto parse into structured JSON - Run
/linkedin:reportto generate weekly performance reports
CLI Usage
ANALYTICS_ROOT="${CLAUDE_PLUGIN_ROOT}/assets/analytics" \
node --import tsx "${CLAUDE_PLUGIN_ROOT}/scripts/analytics/src/cli.ts" import <file>
ANALYTICS_ROOT="${CLAUDE_PLUGIN_ROOT}/assets/analytics" \
node --import tsx "${CLAUDE_PLUGIN_ROOT}/scripts/analytics/src/cli.ts" report --week <W>
ANALYTICS_ROOT="${CLAUDE_PLUGIN_ROOT}/assets/analytics" \
node --import tsx "${CLAUDE_PLUGIN_ROOT}/scripts/analytics/src/cli.ts" trends --period <P> --metric <M>
Storage
assets/analytics/
├── exports/ # Raw CSV from LinkedIn (drop files here)
├── posts/ # Imported post data as JSON
└── weekly-reports/ # Generated weekly reports
Agents that consume analytics data: analytics-interpreter, performance-reporter, content-tracker.
Personalization Engine
The plugin tracks how well you've populated asset templates with your own data. A higher personalization score means more tailored content output.
Scoring Categories (100 points total)
| Category | Weight | Source |
|---|---|---|
| Voice samples | 25 | assets/voice-samples/ |
| User profile | 20 | config/user-profile.local.md |
| Case studies | 15 | assets/case-studies/ |
| Frameworks | 10 | assets/frameworks/ |
| High-engagement posts | 10 | assets/examples/ |
| Demographics | 8 | assets/audience-insights/ |
| Engagement patterns | 7 | assets/audience-insights/ |
| Post templates | 5 | assets/templates/ |
Run /linkedin:setup to see your current score and walk through guided workflows for each category. The score is also displayed in your session status line at startup.
Assets Directory
| Directory | Contents |
|---|---|
templates/ |
Post type templates, carousel blueprints, article template, content calendar |
checklists/ |
Quality scorecard for pre-publish checks |
examples/ |
High-engagement post examples |
voice-samples/ |
Your authentic voice reference (add your own) |
audience-insights/ |
Demographics and engagement patterns |
case-studies/ |
Case study template for your real stories |
frameworks/ |
Framework template for your methodologies |
analytics/ |
Imported data, weekly reports (gitignored) |
drafts/ |
Post scheduling queue and weekly drafts (gitignored) |
Workflow Examples
1. Sunday Content Prep
/linkedin:batch
> Theme: AI adoption in government IT
# Creates 3-5 posts with varying angles and formats
# Posts are added to the scheduling queue
/linkedin:calendar
# Review the upcoming week's schedule
2. Quick React Post (5 minutes)
/linkedin:quick
> Just saw Microsoft announce Copilot Studio autonomous agents —
> this changes everything for low-code teams
3. Import Analytics and Review Performance
/linkedin:import
> ~/Downloads/linkedin-analytics-2026-02.csv
/linkedin:report
> Show me last week's performance
/linkedin:audit
> Full quarterly review
4. Grow from 2K to 5K Followers
/linkedin:strategy
> I have about 2,500 followers and want to reach 5K
/linkedin:competitive
> Analyze the top 5 thought leaders in Microsoft AI for government
5. Repurpose a Viral Post
/linkedin:multiplatform
> Take my best-performing post and adapt it for a newsletter intro,
> a Twitter thread, and 3 presentation slides
Content Quality Rules
The plugin enforces quality standards through hooks and agent behavior:
| Rule | Threshold | Enforcement |
|---|---|---|
| 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 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 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 |
Configuration
User Profile
cp config/user-profile.template.md config/user-profile.local.md
Edit with your name, expertise areas, target audience, voice preferences, and LinkedIn goals. The more detail you provide, the more personalized the output.
State File
The plugin tracks posting metrics in ~/.claude/linkedin-thought-leadership.local.md:
---
last_post_date: 2026-01-28
posts_this_week: 2
weekly_goal: 3
current_streak: 12
current_week: "2026-W05"
follower_count: 0
follower_target: 10000
target_date: "2026-12-31"
next_planned_topic: ""
---
State is automatically initialized on first session start (from config/state-file.template.md) and updated by the Stop hook after each content session.
Post Queue
Scheduled posts are tracked in assets/drafts/queue.json:
- Managed by
queue-manager.mjs(imported by session-start, posting-reminder, and commands) - Status flow:
draft->scheduled->published(orcancelled) - Created by
/linkedin:batchand/linkedin:pipeline - Viewed via
/linkedin:calendar - Transitioned via
/linkedin:publish
What This Plugin Does Not Cover
| Area | Why | Alternative |
|---|---|---|
| LinkedIn API integration | No official API for content posting | Copy/paste from generated drafts |
| Real-time analytics | LinkedIn doesn't provide streaming data | Periodic CSV import via /linkedin:import |
| Engagement automation | Automated commenting violates LinkedIn ToS | Manual engagement guided by /linkedin:collab |
| Profile editing | Plugin generates recommendations, not API calls | Apply changes manually on LinkedIn |
| Team/multi-user workflows | Designed for individual thought leaders | Enterprise LinkedIn tools |
| Content scheduling via API | No official scheduling API | Queue management with manual posting via /linkedin:publish |
Version History
| Version | Date | Highlights |
|---|---|---|
| 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. |
See CHANGELOG.md for full details and known gaps.
License
This project is licensed under the MIT License.
The plugin architecture, content strategies, and algorithm analysis are original work. LinkedIn is a trademark of LinkedIn Corporation.
The algorithm rewards expertise, consistency, and authenticity. Everything else is noise.