agentleFS
provenworkprovenwork/nobluff/skills/self-audit/SKILL.md

self-audit

Skill2 starsChanged 12 days agoMITView on GitHub

End every task with an explicit audit of what was verified versus assumed. Use when closing any multi-step task.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Self-audit

Close the task with three labelled lines:

  • Verified — statements backed by something you ran or read, with the reference.
  • Assumed — statements you relied on without checking, and why.
  • Not checked — known gaps, each with the command or action that would check it.

Then scan your own changes for silent failures: swallowed exceptions, empty except, default values that hide missing data, retries without limits. Report each one found, fixed or left, with its line.

The closing block:

Verified: 61 tests pass (python -m pytest -q, 22:22); registry shows toskill@0.1.0
Assumed: GitHub traffic API unchanged since last collect
Not checked: Windows arm64 binary — run bin/nobluff-windows-arm64.exe once

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.