SkillAgentSearch skills...

deep-audit

Deep consistency audit of the entire repository — launches 4 parallel specialist agents to find factual errors, code bugs, broken references, count mismatches, and cross-document inconsistencies, then fixes all issues and loops until clean.

Install / Use

npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill deep-audit

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

87/100

Supported Platforms

Universal

Our assessment of deep-audit

deep-audit scores 87/100 on our quality scale, 632nd of 1,155 Content & Media skills we index.

Its SKILL.md is 5.6 KB long, well organised into 18 sections with 1 code example: a solid amount of guidance for an agent.

With 4,360 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
17/20
Description
15/15
Adoption
15/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so deep-audit is actively maintained.
  • Our last check on 2026-11-02 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-29. Automated pattern scan on 2026-09-29. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

deep-audit compared with similar skills

All 4 of these similar skills score higher than deep-audit; compare them before choosing.

SkillScoreStarsUpdatedFormat
deep-audit (this skill)by brycewang-stanford874.4k54d agoSKILL.md
siyuanby siyuan-note10047.3ktodayMCP Server
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md
pptxby anthropics100177.9k55d agoSKILL.md

Frequently asked questions

How do I install deep-audit?
Run npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill deep-audit. The install tabs above show the steps for each supported agent.
Which AI agents does deep-audit work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is deep-audit safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is deep-audit still maintained?
The repository was last updated about 2 months ago, so deep-audit is actively maintained.

name: deep-audit description: >- Deep consistency audit of the entire repository — launches 4 parallel specialist agents to find factual errors, code bugs, broken references, count mismatches, and cross-document inconsistencies, then fixes all issues and loops until clean. Make sure to use this skill whenever the user wants a comprehensive repository-wide check — not a targeted review of a single file. Triggers include: "audit", "deep audit", "find inconsistencies", "check everything", "run a full audit", "are there any broken references", "check the whole repo", "something feels off", "run the audit loop", or after making broad changes across multiple files. argument-hint: "(no arguments needed)" allowed-tools: ["Read", "Write", "Edit", "Bash", "Glob", "Grep", "Task"]

/deep-audit — Repository Infrastructure Audit

Run a comprehensive consistency audit across the entire repository, fix all issues found, and loop until clean.

When to Use

  • After broad changes (new skills, rules, hooks, guide edits)
  • Before releases or major commits
  • When the user asks to "find inconsistencies", "audit", or "check everything"

Workflow

PHASE 1: Launch 4 Parallel Audit Agents

Launch these 4 agents simultaneously using Task with subagent_type=general-purpose:

Agent 1: Guide Content Accuracy

Focus: README.md, CLAUDE.md, rules/workflow-overview.md

  • All numeric claims match reality (skill count, agent count, rule count, hook count)
  • All file paths mentioned actually exist on disk
  • All skill/agent/rule names match actual directory names
  • No stale counts from previous versions

Agent 2: Hook Code Quality

Focus: hooks/*.py and hooks/*.sh

  • No remaining /tmp/ usage (should use ~/.claude/sessions/)
  • Hash length consistency ([:8] across all hooks)
  • Proper error handling (fail-open pattern: top-level try/except with sys.exit(0))
  • JSON input/output correctness (stdin for input, stdout/stderr for output)
  • Exit code correctness (0 for non-blocking, non-zero only when intentionally blocking)
  • from __future__ import annotations for Python 3.8+ compatibility
  • Correct field names from hook input schema (source not type for SessionStart)
  • PreCompact hooks print to stderr (stdout is ignored)

Agent 3: Skills and Rules Consistency

Focus: skills/*/SKILL.md and rules/*.md

  • Valid YAML frontmatter in all files
  • No stale disable-model-invocation: true
  • allowed-tools values are sensible
  • Rule paths: reference existing directories
  • No contradictions between rules
  • CLAUDE.md skills table matches actual skill directories 1:1
  • All templates referenced in rules/guide exist in templates/

Agent 4: Cross-Document Consistency

Focus: README.md, CLAUDE.md

  • All feature counts agree across both documents
  • All links point to valid targets
  • Directory tree matches actual structure
  • No stale counts from previous versions

PHASE 2: Triage Findings

Categorize each finding:

  • Genuine bug: Fix immediately
  • False alarm: Discard (document WHY it's false for future rounds)

Common false alarms to watch for:

  • Quarto callout ## Title inside ::: divs — this is standard syntax, NOT a heading bug
  • allowed-tools linter warning — known linter bug (Claude Code issue #25380), field IS valid
  • Counts in old session logs — these are historical records, not user-facing docs

PHASE 3: Fix All Issues

Apply fixes in parallel where possible. For each fix:

  1. Read the file first (required by Edit tool)
  2. Apply the fix
  3. Verify the fix (grep for stale values, check syntax)

PHASE 4: Documentation Check

This plugin does not maintain a Quarto source file. If README.md or CLAUDE.md were modified, verify they are consistent with each other — no render step is needed.

PHASE 5: Loop or Declare Clean

After fixing, launch a fresh set of 4 agents to verify.

  • If new issues found → fix and loop again
  • If zero genuine issues → declare clean and report summary

Max loops: 5 (to prevent infinite cycling)

Key Lessons from Past Audits

These are real bugs found across 7 rounds — check for these specifically:

| Bug Pattern | Where to Check | What Went Wrong | |-------------|---------------|-----------------| | Stale counts ("19 skills" → "21") | Guide, README, landing page | Added skills but didn't update all mentions | | Hook exit codes | All Python hooks | Exit 2 in PreCompact silently discards stdout | | Hook field names | post-compact-restore.py | SessionStart uses source, not type | | State in /tmp/ | All Python hooks | Should use ~/.claude/sessions/<hash>/ | | Hash length mismatch | All Python hooks | Some used [:12], others [:8] | | Missing fail-open | Python hooks __main__ | Unhandled exception → exit 1 → confusing behavior | | Python 3.10+ syntax | Type hints like dict | None | Need from __future__ import annotations | | Missing directories | quality_reports/specs/ | Referenced in rules but never created | | Always-on rule listing | Guide + README | meta-governance omitted from listings | | macOS-only commands | Skills, rules | open without xdg-open fallback | | Protected file blocking | settings.json edits | protect-files.sh blocks Edit/Write |

Output Format

After each round, report:

## Round N Audit Results

### Issues Found: X genuine, Y false alarms

| # | Severity | File | Issue | Status |
|---|----------|------|-------|--------|
| 1 | Critical | file.py:42 | Description | Fixed |
| 2 | Medium | file.qmd:100 | Description | Fixed |

### Verification
- [ ] No stale counts (grep confirms)
- [ ] All hooks have fail-open + future annotations
- [ ] Guide renders successfully
- [ ] docs/ updated

### Result: [CLEAN | N issues remaining]

Related Skills

View on GitHub
GitHub Stars4.4k
CategoryContent
Updated1mo ago
Forks527

Languages

Stata

Trust signals

88/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium