.claude/skills/linkedin-post/SKILL.md
Generate LinkedIn posts that match the voice profile and resonate with your target audience. Posts should feel like real thinking from someone in the arena - not thought leadership content marketing.
npx skillsauth add navotvolkgroundup/nabot linkedin-postInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate 3-5 LinkedIn posts per week that read like a sharp operator sharing what they actually see, not building a personal brand. Voice, audience, and business context come from your context profiles.
Read context profiles in /context/:
voice.json - How to soundaudience.json - Who you're writing forCheck engagement data in /knowledge/engagement/ for what's working
Check recent posts to avoid repetition and ensure topic variety
Name something you're seeing across your industry.
Challenge accepted wisdom in your domain.
Tactical, operational insight from experience.
Industry culture, landscape observations, global context through a local lens.
Light promotion of your content or wins.
Use sparingly — pull from voice.json.
Defined by your voice.json. Supports primary and secondary languages with natural code-switching.
Apply the /humanizer skill to all posts before presenting. Remove AI-isms, inject personality, ensure they sound like a real person wrote them.
Before delivering:
Check /knowledge/engagement/engagement_log.json for data on what works.
Patterns to optimize for:
| Dimension | Twitter | LinkedIn | |-----------|---------|----------| | Length | 1-3 sentences | 150-300 words | | Depth | Observation, punch | Observation + developed thinking | | Tone | Sharp, fast, pithy | Sharp but more grounded, authoritative | | Promotion | Almost never | Lightly, wrapped in insight | | Formatting | Minimal | White space, occasional bold |
business
Generate tweets that match the voice profile and resonate with your target audience. Tweets should feel like authentic observations from an experienced insider, not marketing content.
data-ai
# X Reply Generator for @nabotweet ## Overview Generate replies to people who respond to your tweets. Replies should sound natural, match your voice, and add value to the conversation. ## Before Writing 1. **Read context profiles** in `/context/`: - `voice.json` — How to sound - `audience.json` — Who you're talking to - `business-groundup.json` — GroundUp Ventures context - `business-weeklysync.json` — Weekly Sync podcast context 2. **Read replies data** from `/knowledge/engagem
development
Creates value-packed, niche-specific, thought leadership newsletters (800-1,500 words) with irresistible subject lines, skimmable headers, and actionable content. Uses proven frameworks for headlines, introductions, and sectioning. Use when user mentions "write newsletter", "thought leadership content", "weekly newsletter", or wants to create educational, value-driven newsletter content.
testing
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.