audit-only
Skill207 starsChanged 4 months agoMITView on GitHub
Read-only investigation mode: answer and report findings first, change no code until told to go. Use when the user says audit, investigate, "don't touch code", or asks a plain question.
In this repository22 other files it gives its agents.
- babysitSkill
- cleanSkill
- cprSkill
- draft-tweetSkill
- engraved-figuresSkill
- free-disk-spaceSkill
- list-open-workSkill
- notarize-macSkill
- no-tropesSkill
- perfSkill
- pr-readySkill
- pr-triageSkill
- pr-updateSkill
- researchSkill
- runtime-debugSkill
- stacked-prSkill
- ticket-shipSkill
- triageSkill
- ui-onlySkill
- ui-systemSkill
- visual-verifySkill
- workSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Read the relevant code/data and answer the actual question first.
- Distinctive: line 18
If a change is warranted, describe it and wait for a go.
- Distinctive: line 19
If asked, post findings as a PR/issue comment — that's still not code edits.
- Distinctive: line 23
Start writing code because the fix seems obvious.
- Distinctive: line 25
Treat "review this" or a plain question as permission to change things.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Audit Only
Investigate and report. Do not edit code, create files, or open PRs until the user explicitly says to proceed.
Do
- Read the relevant code/data and answer the actual question first.
- Report findings: what's there, what's wrong, options + a recommendation.
- If a change is warranted, describe it and wait for a go.
- If asked, post findings as a PR/issue comment — that's still not code edits.
Don't
- Start writing code because the fix seems obvious.
- Act on assumed scope — answer what was asked, nothing more.
- Treat "review this" or a plain question as permission to change things.
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.