LinkedIn Studio Plugin for Claude Code

Turn your expertise into LinkedIn authority — without the blank page, the guesswork, or the generic AI slop.

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 →

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.

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.

Tip

New here? Run /linkedin:onboarding — it walks you through profile optimization, personalization, and your first published post in one guided flow (~10 minutes).

Note

Pre-1.0. The earlier 1.0.0–4.1.0 numbering reflected ambition, not maturity. Honest about where it stands today: the architecture workstream (M0) is done — user data lives in a per-user data dir outside the plugin, with automatic migration — and the 29 pre-0.7.0 command surfaces have all passed both the interactive hardening gate (29/29) and independent cold-review (29/29) (/linkedin:trends, shipped in 0.7.0, is not yet gated). What remains for 1.0.0 is a GUI. See CHANGELOG.md.

---

Two Engines

LinkedIn Studio is really two content engines sharing one surface. They have different speeds, different gates, and different goals.

⚡ The Feed Engine — short-form, fast, frictionless

For everyday presence. The point is velocity without losing quality: every content command auto-copies the result to your clipboard, asks at most two questions, and runs your draft through the same algorithm-aware quality gates before it leaves your editor.

Want to…	Command	Time
React to an article or observation	/linkedin:quick	~5 min
Write a substantial post	/linkedin:post	10–15 min
Turn a URL into a reaction post	/linkedin:react	~5 min
Build a carousel (highest engagement format)	/linkedin:carousel	~15 min
Script a video	/linkedin:video	~10 min
Fill a whole week in one sitting	/linkedin:batch	~30 min

📖 The Long-Form Engine — /linkedin:newsletter

For the pieces that build authority — newsletter editions, essays, series articles. This is what sets LinkedIn Studio apart from "AI writes your post" tools: an 18-phase pipeline where the draft is grounded in your real material before research (lived-specifics extraction) and then has to survive a gauntlet of quality gates before it locks.

skeleton gate ──▶ voice scrub ──▶ fact-check ──▶ editorial craft gate ──▶
persona resonance ──▶ cold adversarial review ──▶ visual assets ──▶ LOCK ──▶ hook conversion
   (before prose)      (de-AI)     (sources)        (is it well-made?)
                                                  (does it land?)   (cold, headless)

Each gate exists because skipping it is expensive: spine errors are caught at the outline stage, not after a full draft; claims past the model's knowledge cutoff must be web-searched; an editor judges craft a resonance sweep can't see; and a frozen draft is re-read by reviewers carrying no drafting-session context (argument, language, facts, reader-fit) — inline at Step 6.5 or in a fresh session via /linkedin:headless-review for maximum independence.

Short-form lives in /linkedin:post, :quick, :react, :carousel, :video. Long-form lives in /linkedin:newsletter. /linkedin:multiplatform adapts short-form across platforms; long-form repurposing routes back to /linkedin:newsletter.

---

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, then install the plugin:

claude plugin marketplace add https://git.fromaitochitta.com/open/ktg-plugin-marketplace.git
claude plugin install linkedin-studio@ktg-plugin-marketplace

Or add the marketplace and browse interactively with /plugin. Or enable directly in ~/.claude/settings.json:

{
  "enabledPlugins": {
    "linkedin-studio@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

Already Set Up?

Goal	Command
Write a post	/linkedin:post
Quick 5-min post	/linkedin:quick
React to an article	/linkedin:react
Write a long-form edition	/linkedin:newsletter
View your stats	/linkedin:report
See all commands	/linkedin

---

Commands

All 30 commands use colon notation: /linkedin:post, /linkedin:quick, etc. The surface is organized into five journeys (Start · Create · Engage · Measure · Grow); /linkedin:create and /linkedin:measure are guided front-doors that route you to the right command when you know the journey but not the exact command. Run /linkedin for the live router with your posting status.

Onboarding & Setup

Command	Description
/linkedin:onboarding	Multi-step wizard — profile optimization, 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	Populate asset templates with your real voice, case studies, and audience data (6 sub-workflows; calculates personalization score).
/linkedin:profile	profile/topic-relevance optimization checklist — About, Experience, Headline, content-history alignment.
/linkedin	Main router — posting status (streak, weekly progress) + the full command menu.

Content Creation

Command	Description
/linkedin:create	Create front-door. Routes you to the creation command that owns the format (post/quick/react/carousel/video/multiplatform/batch/newsletter). Delegates only.
/linkedin:post	Full interactive post creation — angle, format, drafting, refinement. Best for substantial posts (1,200–1,800 chars).
/linkedin:quick	5-minute quick post (3-line formula, 150–500 chars) + the 8 post-type templates.
/linkedin:react	URL-to-post pipeline — paste an article or link, get a reaction post.
/linkedin:carousel	Structured multi-slide carousel with per-slide copy + layout guidance; optional slide images via mcp-image.
/linkedin:video	Video script generator for 30s/60s/90s/2-min videos with pacing and visual cues.
/linkedin:multiplatform	Adapt LinkedIn content for X threads, newsletter sections, blog posts, slides, YouTube scripts.
/linkedin:batch	A full week of content in one session — one theme in, 3–5 posts out, written to the queue.
/linkedin:pipeline	Full end-to-end pipeline from idea to published post (ideation → publish → post-analysis).
/linkedin:newsletter	Long-form orchestrator — newsletter/essay/series article at series quality. Multi-session 18-phase pipeline; lived-specifics grounding BEFORE research, all gates BEFORE lock.
/linkedin:headless-review	Cold adversarial review package on a FROZEN draft (content-reviewer + language-reviewer + fact-reviewer + persona-reviewer) — run in a fresh session for maximum isolation.
/linkedin:pivot	Re-open a long-form edition after a substantive late change so cleared gates re-run before lock (heuristic: >20 % word-count or >2 new sections).

Engage

Command	Description
/linkedin:calendar	View/manage the scheduling queue + run the publish action (mark a post published, update state/streak, surface the first-hour plan).
/linkedin:firsthour	Post-publish first-hour / reply-loop sprint — timestamped targets, draft comments, timeline; hands off to post-feedback-monitor.
/linkedin:outreach	Collaborations + speaking under one paradigm — partner scoring, CFP search, formats, abstracts, pipeline tracker (unlocks ~1K).

Measure

Command	Description
/linkedin:measure	Measure front-door. Routes you to the right analytics command (import/report/analyze/audit/ab-test). Delegates only.
/linkedin:import	Import a LinkedIn analytics CSV export into structured JSON (auto-detects ~/Downloads, parses, flags anomalies).
/linkedin:report	Weekly performance report from imported data — metrics, top performers, trends, alerts.
/linkedin:analyze	Diagnose performance issues — algorithm penalties, profile-content mismatch, reach drops.
/linkedin:audit	Periodic strategy audit — top/bottom posts, topic distribution, format mix, trends. Run quarterly.
/linkedin:ab-test	Design and track A/B content experiments.
/linkedin:competitive	Competitive analysis of other creators in your niche — frequency, formats, hooks, differentiation gaps.

Grow

Command	Description
/linkedin:strategy	Growth + authority — phase guidance (0–1K → 10K+), trajectory-aware adjustments, signature-content compounding.
/linkedin:monetize	Monetization — scored readiness, stage-specific plans, lead magnets, DM conversion, revenue dashboards (unlocks ~1K).

---

Agents

19 purpose-built agents power the commands — each with a fixed model and a focused job. The collaboration pipeline and a "which agent do I need?" map live in CLAUDE.md.

Agent	Model	Responsibility
content-optimizer	Sonnet	Optimize posts — hooks, structure, CTAs
strategy-advisor	Sonnet	Growth strategy + phase guidance
analytics-interpreter	Sonnet	Audience patterns + weekly/monthly reports
engagement-coach	Sonnet	5x5x5 + first-hour + CEA commenting
content-planner	Sonnet	Weekly/monthly content calendars
network-builder	Sonnet	Strategic networking + outreach
content-repurposer	Sonnet	Format conversion + evergreen refresh
trend-spotter	(inherits session)	Trending topics + opportunity scores
demand-spotter	(inherits session)	Demand-sweep «innenfra og ut»: reader's verbatim questions → pain-point map → vocabulary translation → arc map with honest market verdict
voice-trainer	Sonnet	Voice profile building + drift detection
differentiation-checker	Sonnet	Originality scoring + commodity detection
video-scripter	Sonnet	Video scripts with pacing + visual cues
post-feedback-monitor	Opus	Post-publish 48h monitoring
fact-checker	Opus	Claim verification, post-cutoff web search (longform)
editorial-reviewer	Opus	Craft gate — prose + narrative architecture (longform)
persona-reviewer	Opus	Reader-persona skeleton / resonance / conversion gate (longform)
voice-scrubber	Opus	De-AI scrub + Norwegian-chronicle voice (longform)
content-reviewer	Opus	Cold/headless argument-integrity review (longform)
language-reviewer	Opus	Cold/headless Norwegian-language review (longform)
fact-reviewer	Opus	Cold/headless re-verification + pivot-risk (longform)

---

Boundaries (as of 2026-07)

LinkedIn Studio is honest about what it can and cannot do for a personal profile:

• Post-level analytics via API — exists, but is partner-gated (a vetted Community Management API app + a verified organization + a Page). Not self-serve for a solo profile, so the practical floor is the CSV export you drop into /linkedin:import. Per-post saves are visible in native post analytics (count-only, since ~Sept 2025) but absent from the CSV and have no self-serve API — the tool does not auto-track them, but you can add a Saves column to the CSV manually and /linkedin:import ingests it (omit it and saves stays unknown, never 0, never folded into engagement rate).
• Auto-publish — technically possible via the w_member_social scope, so this is a design choice, not an API limit: the OAuth/token overhead plus LinkedIn's terms on automated posting make copy-to-clipboard + you-paste the right default. The calendar's "publish" action marks a post you posted as published — it never posts on your behalf.
• In-network vs out-of-network reach — LinkedIn shows this split natively in post analytics (Discovery, under the impressions count; global rollout from June 2026), but as percentages and not in the CSV export — whether it will ever be exported is unverified. So it follows the saves pattern: add an Out-of-network (or In-network) column with the percentage you read off that panel and /linkedin:import ingests it — omit it and the share stays unknown, never 0. It is not folded into the engagement rate: a high out-of-network share means the post reached new people (acquisition), high in-network engagement means it landed with the audience you already have (resonance). Roll-ups are impressions-weighted.
• Dwell time — internal to LinkedIn for organic posts; not exportable, no count to transcribe, no API. Explicitly unmeasurable — the plugin does not estimate it.
• Also not covered: real-time/streaming analytics, automated engagement (ToS), profile editing via API, and team/multi-user workflows. The plugin generates recommendations and drafts; you apply them.

---

Content Quality Rules

Enforced through hooks and agent behavior, calibrated to documented topic-relevance signals:

Rule	Threshold
Hook length	110–140 characters
Post length (standard / quick)	1,200–1,800 / 150–500 characters
No external links in body	body links correlate with lower reach → first comment
No corporate buzzwords	blocklist: leverage, synergy, paradigm shift, thought leader, disruptive, value proposition, ecosystem, holistic approach
Topic alignment	must align with your 5 core expertise areas
Topic rotation	no back-to-back same pillar; no pillar >50 % in 14 days (warn-only)
Voice consistency	AI-authenticity check + voice matching (voice-guardian hook)

---

Example Workflows

Sunday content prep

/linkedin:batch        # one theme → 3–5 posts, varying angles, into the queue
/linkedin:calendar     # review the upcoming week

A long-form edition, done right

/linkedin:newsletter   # multi-session: skeleton → spine prose → voice scrub →
                       # fact-check → editorial craft → persona resonance →
                       # cold adversarial review → visual assets → lock → hook conversion

---

Deeper Documentation

The README is the front door. The detail lives alongside it:

For…	See
Architecture — agent pipeline & selection, 9 hooks, 6 skills, personalization scoring, configuration, analytics internals	CLAUDE.md
The 28-document knowledge base (algorithm signals, angles, frameworks, strategy guides)	references/
Full version history and known gaps	CHANGELOG.md
Maintenance model, fork-and-own, what upstream provides	GOVERNANCE.md

---

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.