purity-audit
Skill3 starsChanged 29 days agoMITView on GitHub
Audit scoped artifacts for obsolete residue, duplication and factual gaps. Triggers on "purity audit", "纯净审计".
In this repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brainstormSkill
- oss-strategySkill
- specSkill
- researchSkill
- api-designSkill
- architectureSkill
- codebase-designSkill
- design-researchSkill
- domain-modelingSkill
- frontend-designSkill
- imagegenSkill
- image-to-codeSkill
- prompt-engineeringSkill
- prototypeSkill
- schema-designSkill
- auth-implementationSkill
- breakdownSkill
- context-engineeringSkill
- error-handlingSkill
- i18nSkill
- implementSkill
- multi-agent-orchestrationSkill
- cost-optimizationSkill
- performanceSkill
- refactoringSkill
- simplifySkill
- api-testingSkill
- e2e-testingSkill
- load-testingSkill
- tddSkill
- test-generationSkill
- a11y-reviewSkill
- code-reviewSkill
- debuggingSkill
- lintingSkill
- security-reviewSkill
- ci-cdSkill
- deprecation-migrationSkill
- git-workflowSkill
- oss-polishSkill
- shippingSkill
- documentation-auditSkill
- handoffSkill
- incident-responseSkill
- observabilitySkill
- skill-authoringSkill
- using-skillsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 18
Search obsolete references, repeated rules, editing prose and decoration.
- Distinctive: line 20
Check action/verification correspondence and output ownership.
≈ “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
Purity Audit
When to use
- Audit scoped artifacts for obsolete residue, duplication and factual gaps.
Not for: documentation-audit for synchronization; code-review for defects.
Steps
- Agree target and load the checklist; preserve operational versions, valid pending work and legitimate audit evidence.
- Search obsolete references, repeated rules, editing prose and decoration; judge matches in context.
- Check action/verification correspondence and output ownership; delegate only when authorized and useful.
- Fix scoped residue and produce the approved report; rerun targeted checks and classify open findings.
Output: Suggested paths, subject to human audit: docs/audit/YYYY-MM-DD-purity.md at the approved path.
Verify
- Findings have contextual evidence; necessary history, versions and unrelated content are preserved.
References
- engineering-principles.md — shared decision boundaries, scope and verification.
- human-audit.md — document consent, readability and human review.
- purity-checklist.md — the 16-point A–E checklist (the audit criteria).
- references/subagent-dispatch.md — per-category auditor dispatch: constructed-context template + worked Category-A example.
- references/templates.md — audit-report template.
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.

