By warpirate
17 skills for substance-first LinkedIn growth. Refuses templates, refuses scaled outreach, optimizes for dwell time and comment quality instead of detection-evasion. Includes a Wikipedia-based humanizer that the writing skills invoke as a final polish step.
Diagnose what is landing across the user's recent LinkedIn posts
Diagnose the user's LinkedIn profile section by section with severity-rated fixes
Produce a LinkedIn carousel SPEC (slide copy + visual brief + image-gen prompts) for assembly in Canva or Figma
Interview the user to surface specific, postable LinkedIn ideas from their actual work
Strip AI-writing tells from pasted text using Wikipedia's Signs of AI writing rules
Use when user has been posting on LinkedIn at least 4 weeks and wants to know what is landing, run a quarterly content review, or diagnose dropping engagement. Trigger phrases include "analyze my LinkedIn performance," "which of my posts are working," "what should I post more of," "why is my engagement dropping," or when user uploads a LinkedIn analytics CSV.
Use when user wants to diagnose their current LinkedIn profile before rewriting it: they have not touched it in a while, get few profile views or recruiter reach-outs, want a second opinion, or suspect something is off but cannot name it. Trigger phrases include "audit my LinkedIn profile," "check my profile," "what's wrong with my profile," "why don't I get recruiter messages," "review my About section." Run before rewrite-profile.
Use when user has an idea with multiple discrete steps, a framework, a comparison, a before/after, a list of items worth a slide each, or anything where swiping is part of the experience. Trigger phrases include "make a carousel," "build a slide deck for LinkedIn," "turn this into a carousel," "I have a framework to share," or when a find-ideas seed is marked "Best fit for: build-carousel." Produces a carousel SPEC the user assembles into a PDF in Canva or Figma; does not export the finished PDF.
Use when user wants to post on LinkedIn but has no concrete idea, has a vague topic that needs a sharper angle, or uploads a work artifact (PR description, meeting note, internal doc) and asks what to post about it. Trigger phrases include "help me come up with a LinkedIn post," "what should I write about," "I want to post something but I don't know what," "give me ideas for LinkedIn," "I have an idea but I don't know the angle." Run BEFORE any writing skill if user has not given a concrete, specific angle.
Use when editing or reviewing text that reads as AI-generated: symptoms include em dashes, "it's not X, it's Y" constructions, AI vocabulary (leverage, delve, tapestry, underscore, pivotal, crucial, vibrant, testament, landscape), rule-of-three padding, inflated symbolism, promotional language, vague attributions, negative parallelisms, filler phrases. Trigger phrases include "humanize this," "make this sound human," "strip the AI tells," "this reads like ChatGPT." Canonical reference for drafting constraints embedded in every writing skill in this plugin.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
17 Claude Code skills + slash commands for substance-first LinkedIn growth. Profile audit, content drafting (posts, carousels, longform, video, DMs, comments), performance analysis, and a Wikipedia-based humanizer. Anti-template, anti-slop, open source, MIT.
/plugin marketplace add warpirate/linkedin-maxxing
/plugin install linkedin-maxxing@linkedin-maxxing-marketplace
Restart the Claude Code session. Then type /linkedin-maxxing: and the autocomplete menu shows all 17 commands.
LinkedIn growth, LinkedIn content creation, LinkedIn AI tools, anti-AI-slop, humanizer, LinkedIn profile optimization, LinkedIn carousels, LinkedIn newsletter, LinkedIn DM writer, content repurposing, creator economy, personal branding, Claude Code plugin, Claude skills, Anthropic.
17 skills for growing on LinkedIn without producing slop.
How it works: These skills run inside Claude Code on content you paste in (drafts, profile text, past posts, analytics CSV). There is no live LinkedIn API, no scraping, no posting on your behalf. You stay in the loop: the skills draft and critique, you publish.
Most LinkedIn AI tools optimize for the wrong thing. They generate hooks from templates, evade AI detection, and produce posts in the same voice as 50,000 other posts written the same week. The result is the LinkedIn feed everyone scrolls past.
This repo refuses that approach. LinkedIn's 2026 ranking system rewards dwell time, substantive comments, and content that earns the "see more" click. The way to earn those is not better templates. It is to start with something specific the user actually wants to say, write it in the user's actual voice, and produce clean human-sounding text on the first pass.
So these skills:
Grouped by where they sit in a sensible workflow.
| Skill | What it does |
|---|---|
train-voice | Reads samples of the user's past writing (LinkedIn export, blog, pasted posts) and produces voice-profile.md that downstream writing skills read automatically. |
audit-profile | Diagnoses the user's current LinkedIn profile section by section. Severity-rated issues, prioritized fix list. |
rewrite-profile | Rewrites the full profile as one positioning unit: headline, About, Featured, Experience bullets, Skills. |
plan-content | Defines 3-5 content pillars, audience, and cadence. Outputs content-plan.md. |
| Skill | What it does |
|---|---|
find-ideas | Interviews the user to surface specific, postable ideas. Outputs 2-5 idea seeds with concrete anchors and which next skill to use. |
write-hook | Generates 3-5 hook variants for the 210-character LinkedIn "see more" fold, with the strongest marked. |
write-post | Drafts a 1,000-1,300 character text post in the user's voice. The workhorse skill. |
build-carousel | Plans and writes a 6-12 slide document carousel with copy and visual brief. The output is a SPEC the user assembles into a PDF in Canva or Figma; the skill does not export the finished PDF. |
write-longform | Writes a 600-2,000 word article or newsletter issue. |
write-video-script | Writes a 30-90 second video script with beats, timing, and on-screen text. |
repurpose-content | Takes one piece of source content (talk, podcast, blog, doc) and produces 3-7 distinct LinkedIn pieces from different angles. |
| Skill | What it does |
|---|---|
write-comment | High-signal comments on others' posts. Comments now carry ~15x the algorithmic weight of likes. |
write-dm | Connection requests, cold outreach, follow-ups, replies. One message at a time, no mail-merge. |
write-recommendation | LinkedIn recommendations for former colleagues, with specific anchors instead of templated praise. |
npx claudepluginhub warpirate/linkedin-maxxing --plugin linkedin-maxxingComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review