Summary
This is the anti-rewrite skill. It keeps docs aligned with code changes without letting you turn a PR into a style cleanup. You feed it a commit range, it maps behavior changes to affected pages, updates only what needs updating, and produces diffs reviewers can actually parse. Built for the moment right before release when you realize the README still documents flags you removed three sprints ago. The drift detection checklist is practical: does the example run, do the defaults match, is the "coming soon" section lying. If you have ever approved a 47-file doc PR where you couldn't tell what actually changed versus what got rewrapped, you will appreciate the constraint system here.
Install to Claude Code
npx -y skills add getpaperclipai/paperclip --skill doc-maintenance --agent claude-codeInstalls into .claude/skills of the current project.
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 →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.md
Select a file.
Featured
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 →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
