agentleFS
Sign inStart free
RandyRawgustRandyRawgust/ai-knowledge-base-template/.claude/skills/audit/SKILL.md

audit

Skill1 starsChanged 6 months agoMITView on GitHub

Invoke Auditor + drift-watcher on demand to scan the vault for drift, broken refs, stale infra, and rule violations. Use when Andy says audit, audit the vault, run a check, what's drifting, find broken stuff, health check.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use delight, teach-impeccable and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • HK-hubSkill

    delight

    Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.

    Also in 32 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 19 projects that use this

  • zwy123zwySkill

    normalize

    将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。

    Also in 19 projects that use this

  • SkillPilotCHSkill

    level-up

    Eine Automatisierung pro Woche finden, scopen, shippen. Output landet als proposed-Eintrag in cadence.md mit konkreten Implementations-Schritten.

    Also in 12 projects that use this

  • ww-w-aiSkill

    pm-discovery

    PM Agent Team - Automated product discovery, strategy, and PRD generation. Runs PM analysis workflow to produce comprehensive PRD before PDCA Plan phase.

    Also in 3 projects that use this

  • +7 more from HK-hub

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Superseded-infra registry sweep: - every "Old" string in the registry, ripgrep the active vault.

    line 23
  2. Distinctive:

    Only then write the report.

    line 39
  3. Very specific:

    Write findings to 01 - Daily Notes/<YYYY-MM-DD> - Vault Audit.md (or append to today's daily note under ## Audit section).

    line 44
  4. Distinctive:

    Don't fix during audit - audit is read-only, separation of concerns

    line 52
  5. Distinctive:

    Don't suppress 🟡 / ⚪ findings - they're the early warning system

    line 53
  6. Distinctive:

    Don't skip the Activity Log row even if zero findings

    line 54
  7. Distinctive:

    Don't skip the judge protocol on substantive audits - that's the integrity gate

    line 55

“Common” is measured: kept by at least 6 in 10 of the 175 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Audit

On-demand wrapper for [[03 - Skills & Rules/Agents/Auditor|Auditor]] + [[03 - Skills & Rules/Agents/Specialists/drift-watcher|drift-watcher]]. Quarterly scheduled audits already exist via drift-watcher-quarterly; this is the same logic, on-demand.

When to use

Triggers: audit, audit the vault, run a check, what's drifting, find broken stuff, health check, vault audit, check for drift.

Load

  • 03 - Skills & Rules/Agents/Auditor.md - dept-head spec
  • 03 - Skills & Rules/Agents/Specialists/drift-watcher.md - drift heuristics
  • 03 - Skills & Rules/Rules/superseded-infra.md - registry of retired things to flag
  • CLAUDE.md + 5S_STANDARD.md - rules to check compliance against

Run

Flip Auditor + drift-watcher to status: active. Then sweep:

  1. Superseded-infra registry sweep - every "Old" string in the registry, ripgrep the active vault. Any hit outside 99 - Archived/, daily notes, Activity Log, or chats = 🔴 finding.
  2. Broken wikilinks - find [[X]] where X has no matching file (excluding placeholder examples).
  3. Ghost specialists - any dept-head's delegates_to: entry that has no matching Specialists/<name>.md.
  4. CLAUDE.md size - over 200 lines = 🟡.
  5. Frontmatter coverage - active projects without skills: / rules: / agents: arrays = 🟡 (would hide them from Dashboard queries).
  6. Stuck status flags - any agent status: active for >24h (frontmatter timestamp check) = 🟡.

Judge protocol (required for substantive audits)

Per [[03 - Skills & Rules/Agents/Auditor#Judge protocol cross-model verification|Auditor's judge protocol]]: after the primary 6-pass produces findings, dispatch a judge sub-agent in a different model before committing the report.

Pattern:

  1. Primary audit runs in current model. Produces findings + severities.
  2. Dispatch judge via Task tool, in different model (if running Sonnet, judge on Opus; or vice versa). Include the TCE preamble.
  3. Judge brief: ⊙ ⧉(audit_findings) - run ⧉ ∂ ⊗ attacks. What's missed/overstated/misrated?
  4. Integrate judge response: add missed findings, re-examine disputed ones.
  5. Only then write the report. Include a "Judge findings integrated" section.

Skip judge only when total findings <5 or speed-critical.

Report

Write findings to 01 - Daily Notes/<YYYY-MM-DD> - Vault Audit.md (or append to today's daily note under ## Audit section). Use the same 🔴/🟡/⚪ severity scheme as quarterly drift report.

Each finding includes: file path, line number if applicable, suggested fix. End the report with a ## Judge findings integrated section noting what the judge added, downgraded, or removed.

After

Suggest invoking /drift-fix to apply the fixes. Don't auto-apply.

Don't

  • Don't fix during audit - audit is read-only, separation of concerns
  • Don't suppress 🟡 / ⚪ findings - they're the early warning system
  • Don't skip the Activity Log row even if zero findings
  • Don't skip the judge protocol on substantive audits - that's the integrity gate

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.

Check your setup, free