auto-claude-skills
AGENTS.md6 starsChanged 51 days agoMITView on GitHub
Read CLAUDE.md in this directory and follow it. It is the single source of truth for this repo: architecture, style, the six canonical doc locations, and a long list of gotchas that exist because each one already cost someone a day. This file exists only because some agents look for AGENTS.md by convention. It is a pointer on purpose. Do not copy CLAUDE.md into this file. A duplicate drifts within days — the previous version of this file was a…
In this repository27 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-safety-reviewSkill
- agent-team-executionSkill
- agent-team-reviewSkill
- alert-hygieneSkill
- authorial-judgmentSkill
- batch-scriptingSkill
- capture-knowledgeSkill
- deploy-gateSkill
- design-debateSkill
- implementation-drift-checkSkill
- improvement-minerSkill
- incident-analysisSkill
- incident-trend-analyzerSkill
- openspec-shipSkill
- outcome-reviewSkill
- panelSkill
- product-discoverySkill
- project-verificationSkill
- prototype-labSkill
- runtime-validationSkill
- second-opinionSkill
- security-scannerSkill
- skill-scaffoldSkill
- supply-chain-investigationSkill
- synthesizeSkill
- unified-context-stackSkill
The file
Files
auto-claude-skills — agent instructions
Read CLAUDE.md in this directory and follow it. It is the single source of truth for
this repo: architecture, style, the six canonical doc locations, and a long list of gotchas
that exist because each one already cost someone a day.
This file exists only because some agents look for AGENTS.md by convention. It is a
pointer on purpose.
Do not copy CLAUDE.md into this file. A duplicate drifts within days — the previous
version of this file was a verbatim copy that fell ten days behind and still described the
project under the wrong name, which is worse than having no file at all, because a stale
copy reads as authoritative.
Two things worth knowing before you touch anything:
bash tests/run-tests.shruns the whole suite. It is also the declared local gate, so one red file blocks every push that touchesskills/,config/orhooks/.- Hooks are Bash 3.2 (macOS
/bin/bash) and fail open. Syntax-check any hook edit withbash -n hooks/<name>.sh, and read the gotchas inCLAUDE.mdbefore changing one — the failure mode there is silence, not an error.
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.