Summary
Strict, opinionated documentation manager that enforces a hard split: README.md for humans browsing GitHub, AGENTS.md for developers and AI agents running commands. No tutorial fluff, no marketing copy in the wrong file, no guessing. It verifies the actual codebase before writing anything and defaults to terse, imperative style. Handles init and update workflows for both file types, with flags like preserve, minimal, and dry-run. The most useful part is probably the enforcement itself: it will tell you to move your CLI commands out of the README and into AGENTS.md where they belong. Opinionated in a good way if you're tired of documentation drift.
Install to Claude Code
npx -y skills add paulrberg/agent-skills --skill md-docs --agent claude-codeInstalls into .claude/skills of the current project.
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Files
SKILL.md
Select a file.
Featured
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
