# LinkedIn Poster

> Drafts and publishes high-quality LinkedIn posts that sound like the user, not like an AI summary. Reads a reusable per-user profile (interests, audience, voice samples, archetypes, forbidden phrases) and runs a per-post loop: pick an archetype (news reaction, lesson, milestone, provocative question, story), source content, draft 2-3 variants, surface for explicit approval, publish. Works in two tiers — Tier 2 (Cowork or any environment with browser-control tools) auto-fetches voice samples from a LinkedIn URL, surfaces drafts in Dispatch, and auto-types posts into LinkedIn at 35-68 WPM; Tier 1 (Claude.ai, API, mobile) works from manually pasted samples and hands the user a copy/paste-ready draft. Use this skill whenever the user asks to "write a LinkedIn post", "draft a post", "post on LinkedIn", "share something on LinkedIn", "react to [news] on LinkedIn", "write a thought-leadership post", "announce [milestone] on LinkedIn", "build my LinkedIn voice profile", "model my voice from my LinkedIn", or anything similar — even when they don't say "LinkedIn" explicitly but the context is clearly a public professional update.

## Facts
- Page: https://tashan.sh/capability/skill-cnfcnf-linkedin-poster
- tashan id: skill:cnfcnf/linkedin-poster
- Source: https://github.com/cnfcnf/linkedin-poster
- Type: skill
- Category: other
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 68.0
- Freshness: 70.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- GitHub stars: 0
- License: NOASSERTION
- Official: no

## Install

```sh
cp -r linkedin-poster ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-14 by tashan (https://tashan.sh) from public evidence. Scorer s5.