hermeticormus/markdown-discipline-skills/markdown-discipline
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Markdown writing discipline that strips AI-slop tells — no em dashes, no marketing fluff, no emoji bullets, no triple-cataloging, no soft closes. Use when writing or editing any markdown content (README, docs, briefs).
Install
npx vskill@latest install hermeticormus/markdown-discipline-skills/markdown-disciplineSKILL.md
Markdown discipline
Apply to docs, READMEs, briefs, and any markdown content. The goal: high-signal text that reads well as both a doc and as context for an LLM.
Banned
- Emoji in any markdown (unless explicitly requested by the user)
- Marketing adjectives ("robust", "powerful", "comprehensive", "seamless", "world-class", "leverage" as verb)
- Welcome banners + celebration emoji + "Let's dive in!" energy
- Triple-cataloging ("fast, simple, and reliable")
- Antithesis pattern ("It's not X; it's Y")
- Soft closes ("Hope this helps!" / "Let me know if you have questions")
- Title Case headings
- Em dash overuse (sparingly, < 2 per page)
- Excessive bold (one bolded phrase per paragraph max)
- Block quotes used as warning callouts
- Multiple H1s per file
- Sentence fragments for emphasis
Required
- Sentence case for headings
- One H1 per file
- Headings describe content, don't announce sections
- One sentence per bullet
- Max 2 nesting levels in lists
- Code fences specify language
- Inline code for filenames, identifiers, types
- Descriptive link text
- Tables only for comparison matrices
Reading test
- Does the second half of a paragraph add new info? If no, cut.
- Are bullets in a list distinct or padded? If padded, cut.
- Does a heading describe what's below or announce a section? Describe.
- Would a comma work where an em dash is? Use it.
Full content + before/after examples at https://github.com/HermeticOrmus/markdown-discipline-skills.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/markdown-discipline/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/hermeticormus/markdown-discipline-skills/markdown-discipline)