audit-health
Skill2 starsChanged 9 months agoApache-2.0View on GitHub
Quick meta-check that verifies the audit ecosystem is healthy and suggests which audits should be run next. Does NOT perform an actual audit — instead checks that the audit infrastructure (directories, scripts, templates, thresholds) is in good shape. Invocation: /audit-health When invoked, execute the following steps in order. Report results to the user after each step. Report the results. If any checks fail, note them as action items. Report which categories have exceeded their commit thresholds. Recommend running audits for…
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 23
When the task doesn't match this skill's scope -- check related skills
- Distinctive: line 24
When a more specialized skill exists for the specific task
- Distinctive: line 39
When invoked, execute the following steps in order.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
<!-- prettier-ignore-start -->Document Version: 1.1 Last Updated: 2026-02-24 Status: ACTIVE
<!-- prettier-ignore-end -->Audit System Health Check
When to Use
- Meta-check for audit system health — runs diagnostics on domain audits and
- User explicitly invokes
/audit-health
When NOT to Use
- When the task doesn't match this skill's scope -- check related skills
- When a more specialized skill exists for the specific task
Purpose
Quick meta-check that verifies the audit ecosystem is healthy and suggests which audits should be run next. Does NOT perform an actual audit — instead checks that the audit infrastructure (directories, scripts, templates, thresholds) is in good shape.
Invocation: /audit-health
AI Instructions
When invoked, execute the following steps in order. Report results to the user after each step.
Step 1: Run Health Check Script
node scripts/audit/audit-health-check.jsReport the results. If any checks fail, note them as action items.
Step 2: Check Audit Thresholds
node scripts/audit/count-commits-since.jsReport which categories have exceeded their commit thresholds. Recommend running audits for exceeded categories.
Step 3: Run Template Compliance
node scripts/audit/validate-templates.jsReport template compliance scores. Flag any templates below 70%.
Step 4: Run Pre-Audit Check
node scripts/audit/pre-audit-check.jsReport any missing prerequisites that would block future audits.
Step 5: Ecosystem Audit Health
Review the ecosystem audit checks (7-9) from the health check output and compile a detailed table:
### Ecosystem Audit Health
| Audit | Skill Dir | Run Script | State File | Lib Complete |
|-------|-----------|------------|------------|--------------|
| hook-ecosystem-audit | {status} | {status} | {status} | {status} |
| session-ecosystem-audit | {status} | {status} | {status} | {status} |
| tdms-ecosystem-audit | {status} | {status} | {status} | {status} |
| pr-ecosystem-audit | {status} | {status} | {status} | {status} |
| skill-ecosystem-audit | {status} | {status} | {status} | {status} |
| doc-ecosystem-audit | {status} | {status} | {status} | {status} |
| script-ecosystem-audit | {status} | {status} | {status} | {status} |Replace {status} with PASS or FAIL based on health check results.
Step 6: Summary and Recommendations
Compile a summary report:
=== Audit System Health Report ===
Infrastructure: X/9 health checks passing
Templates: Y/9 at 80%+ compliance
Prerequisites: Z/6 checks passing
Recommended Actions:
1. [URGENT] Run /audit-<category> — threshold exceeded (N commits)
2. [WARN] Fix template compliance for <template>
3. [INFO] Update stale baselines in COORDINATOR.md
Next suggested audit: /audit-<category> (highest threshold exceedance)Prioritize recommendations:
- URGENT: Any S0/S1 threshold exceedances or failed health checks
- WARN: Template compliance issues or missing prerequisites
- INFO: Stale baselines or informational items
Context Recovery
This skill runs quickly (< 1 minute) and does not need context recovery. If
interrupted, simply re-run /audit-health.
Version History
| Version | Date | Change |
| 1.1 | 2026-02-24 | Add ecosystem audit coverage (checks 7-9, health table) |
| 1.0 | 2026-02-16 | Initial version with 6 domain audit health checks |
In this repository81 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- llms.txtllms.txt
- find-skillsSkill
- add-debtSkill
- alertsSkill
- analyzeSkill
- artifacts-builderSkill
- audit-agent-qualitySkill
- audit-aggregatorSkill
- audit-ai-optimizationSkill
- audit-codeSkill
- audit-comprehensiveSkill
- audit-documentationSkill
- audit-engineering-productivitySkill
- audit-enhancementsSkill
- audit-performanceSkill
- audit-processSkill
- audit-refactoringSkill
- audit-securitySkill
- brainstormSkill
- checkpointSkill
- code-reviewerSkill
- comprehensive-ecosystem-auditSkill
- content-research-writerSkill
- convergence-loopSkill
- create-auditSkill
- data-effectiveness-auditSkill
- debt-runnerSkill
- decrypt-secretsSkill
- deep-planSkill
- deep-researchSkill
- developer-growth-analysisSkill
- doc-ecosystem-auditSkill
- doc-optimizerSkill
- docs-maintainSkill
- document-analysisSkill
- ecosystem-healthSkill
- Excel AnalysisSkill
- find-skillsSkill
- frontend-designSkill
- gh-fix-ciSkill
- github-healthSkill
- health-ecosystem-auditSkill
- hook-ecosystem-auditSkill
- market-research-reportsSkill
- mcp-builderSkill
- media-analysisSkill
- multi-ai-auditSkill
- pre-commit-fixerSkill
- pr-ecosystem-auditSkill
- pr-retroSkill
- pr-reviewSkill
- quick-fixSkill
- recallSkill
- repo-analysisSkill
- repo-synthesisSkill
- script-ecosystem-auditSkill
- session-beginSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

