claude_skills
CLAUDE.md67 starsChanged 50 days agoMITView on GitHub
@../AGENTS.md This session's Setup hook (.claude/settings.json, matcher init|maintenance) already runs uv self update and prek install for you — skip re-running those two specific commands unless troubleshooting a setup failure. The hook does not run uv sync; still run that yourself per AGENTS.md's "Environment Setup" before assuming dependencies are installed.
In this repository41 other files it gives its agents.
- AGENTS.mdAGENTS.md
- rules/AGENTS.mdAGENTS.md
- research/CLAUDE.mdCLAUDE.md
- .cursor/rules/backlog-before-work.mdcCursor rule
- agent-browserSkill
- beadsSkill
- cccSkill
- copy-editingSkill
- daily-releasesSkill
- graph-engineeringSkill
- rebaseSkill
- receiving-pr-reviewsSkill
- topic-specialistSkill
- workshop-question-framingSkill
- agent-browserSkill
- boilSkill
- commit-stagedSkill
- complete-milestoneSkill
- cove-prompt-designSkill
- create-merge-request-changelogSkill
- create-milestoneSkill
- design-anti-patternsSkill
- evaluate-sdlc-layersSkill
- example-argument-substitutionSkill
- external-pattern-integratorSkill
- fact-checkSkill
- ghSkill
- git-history-reconSkill
- group-items-to-milestoneSkill
- knowledge-explorerSkill
- linear-walkthroughSkill
- modern-gitSkill
- prepare-walkthrough-presentationSkill
- readme-badgerSkill
- refresh-researchSkill
- research-curatorSkill
- session-historianSkill
- seven-prompt-content-engineSkill
- skill-research-processSkill
- start-milestoneSkill
- universe-of-thoughtsSkill
The file
Files
<!--
Split rule: keep material here only if BOTH hold — (a) it is meaningless to a harness that is
not Claude Code, and (b) Claude Code does not already supply it itself (available-skills/agent
listings, tool descriptions, hook execution). Everything else — every project fact, behaviour,
rule, and index, even when the mechanism it names happens to be Claude-Code-shaped — belongs in
AGENTS.md, which this file imports below. This repo's plugins ship harness manifests beside
`.claude-plugin/` (per-plugin coverage varies — follow AGENTS.md's Repository Overview to generate
and inspect the compatibility view), so "which skill to use when" is a project workflow rule, not a
Claude-Code one, even where a given plugin's non-Claude manifest doesn't exist yet.
-->@../AGENTS.md
This session's Setup hook (.claude/settings.json, matcher init|maintenance) already runs
uv self update and prek install for you — skip re-running those two specific commands unless
troubleshooting a setup failure. The hook does not run uv sync; still run that yourself per
AGENTS.md's "Environment Setup" before assuming dependencies are installed.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.