linkedin-post
About
This skill generates structured LinkedIn posts for GEO/SEO thought leadership content. It creates posts based on four content pillars (education, case study, insight, behind the scenes) using specific templates for each type. Developers should use it when asked to write LinkedIn content or with the `/linkedin-post` command.
Quick Install
Claude Code
Recommendednpx skills add guia-matthieu/clawfu-skills -a claude-code/plugin add https://github.com/guia-matthieu/clawfu-skillsgit clone https://github.com/guia-matthieu/clawfu-skills.git ~/.claude/skills/linkedin-postCopy and paste this command in Claude Code to install this skill
Documentation
LinkedIn Post Generator Skill
Generate high-quality LinkedIn posts for GEO thought leadership.
Trigger
Use this skill when asked to write a LinkedIn post, or with /linkedin-post
Process
Step 1: Understand the Request
Ask if not provided:
- Topic: What's the main subject?
- Pillar: education | case_study | insight | behind_scenes
- Context: Any specific data, audit results, or angle?
Step 2: Choose Structure by Pillar
Education Post
[HOOK - 1 ligne choc]
[CONTEXT - Pourquoi c'est important]
[CORE INSIGHT - 3-5 points clés]
[TAKEAWAY - Ce qu'il faut retenir]
[CTA - Question ou appel]
Case Study Post
[HOOK - Le résultat choc]
[DATA - Les chiffres clés]
[ANALYSIS - Ce que ça révèle]
[LESSON - L'apprentissage]
[CTA - Proposer un audit]
Insight Post
[HOOK - L'actualité/tendance]
[CONTEXT - Ce qui s'est passé]
[ANALYSIS - Ce que ça signifie]
[IMPLICATION - L'impact pour l'audience]
[CTA - Question ou réflexion]
Behind the Scenes Post
[HOOK - Story opener]
[STORY - Ce qui s'est passé]
[LESSON - Ce que j'ai appris]
[ASK - Question à l'audience]
Step 3: Apply the 3 Questions Test
Before finalizing, check:
-
VISUALIZABLE? Can the reader "see" it?
- ❌ "Solution innovante" → ✅ "Votre marque citée par ChatGPT"
-
FALSIFIABLE? Is it verifiable?
- ❌ "Excellent service" → ✅ "Score de 67% sur Perplexity"
-
UNIQUE? Could a competitor say this?
- ❌ "Expert SEO" → ✅ "J'ai audité 50 sites avec mon outil GEOTOOL"
Step 4: Hook Bank (Use for Inspiration)
Counterintuitive:
- Votre SEO est parfait. Mais les IA ne vous voient pas.
- Le meilleur contenu ne suffit plus.
- Google vous adore. ChatGPT vous ignore.
Surprising Data:
- 23% de visibilité sur GPT-4. 67% sur Perplexity.
- 1 entreprise sur 10 apparaît dans les réponses ChatGPT.
Question:
- ChatGPT recommande-t-il votre marque ?
- Savez-vous ce que les IA disent de vous ?
Bold Claim:
- Le SEO tel que vous le connaissez est mort.
- Si les IA ne vous citent pas, vous n'existez plus.
Story Opener:
- J'ai audité la visibilité IA d'un client. Le résultat m'a choqué.
- La semaine dernière, j'ai fait 5 audits gratuits.
Step 5: Format Rules
- Language: French, professional but accessible
- Length: 150-250 words
- Paragraphs: 1-2 lines max
- Line breaks: Use liberally for readability
- Emojis: 1-2 max if really relevant (not required)
- Hashtags: 3-5 at the end (optional)
- CTA: Always end with question or call to action
Step 6: Output
Provide the post directly, ready to copy-paste to LinkedIn. No introduction, no "Here's your post:", just the content.
Example Output
Votre site est invisible pour ChatGPT.
Et ce n'est pas un problème de SEO.
C'est un problème de GEO.
Voici 3 raisons :
1. Les LLMs ne crawlent pas comme Google
→ Ils utilisent des bases de connaissances pré-entraînées
2. Le format compte plus que les mots-clés
→ Structure claire, données factuelles, sources citables
3. L'autorité se mesure différemment
→ Pas de PageRank, mais des citations croisées
Ce que ça change pour vous :
Un bon classement Google ≠ visibilité IA.
Il faut optimiser pour les deux.
Vous avez déjà vérifié si ChatGPT recommande votre marque ?
#GEO #IA #SEO #Marketing
Integration with GEOTOOL
If user provides audit data, use real numbers:
- Global score
- Scores by model (GPT-4o, Claude, Perplexity, Gemini)
- Mention rates
- Recommendations
Turn audit results into compelling case study posts.
What Claude Does vs What You Decide
| Claude handles | You provide |
|---|---|
| Applying post structure by pillar | Topic and angle selection |
| Writing hooks from hook bank | Approval of final hook |
| Formatting for LinkedIn readability | Voice authenticity check |
| Generating data-driven case studies | Real audit/data numbers |
| Running 3 Questions Test | Final posting decision |
Skill Boundaries
This skill excels for:
- GEO/SEO thought leadership content
- Data-driven case study posts
- Educational explainer posts
- Behind-the-scenes insights
This skill is NOT ideal for:
- Personal/emotional posts → Need authentic human voice
- Controversial opinions → Requires your conviction
- Company announcements → Different format needed
Skill Metadata
name: linkedin-post
category: social
version: 2.0
author: GUIA
source_expert: GEO Thought Leadership Framework
difficulty: beginner
mode: cyborg
tags: [linkedin, social-media, content, geo, thought-leadership]
created: 2026-02-03
updated: 2026-02-03
GitHub Repository
Related Skills
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
polymarket
MetaThis skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
creating-opencode-plugins
MetaThis skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
