Agent skill
audit-skills
Audits skills, commands, and prompt templates for best practice violations including length, checklists, verification steps, and progressive disclosure. Use after creating or modifying skills, during reviews, or to improve existing prompt files. Produces prioritized improvement suggestions.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/audit-skills
SKILL.md
Audit Skills
Analyze skills, legacy commands, and prompt templates in this repository against best practices and produce prioritized improvements.
Workflow
Copy this checklist and track progress:
Audit Progress:
- [ ] Step 1: Discover all auditable files (skills, commands, prompts)
- [ ] Step 2: Load criteria
- [ ] Step 3: Audit each file
- [ ] Step 4: Score and prioritize
- [ ] Step 5: Output report
Step 1: Discover All Auditable Files
Find all skill-like files in the repository:
Use Glob to find files matching these patterns:
.claude/skills/*/SKILL.md— Skills.claude/commands/*.md— Legacy commands.claude/skills/*/PROMPT.md— Co-located prompts*_PROMPT.md— Root-level prompt templates
Classify each file:
| Type | Example | Criteria Applied |
|---|---|---|
| Skill | .claude/skills/*/SKILL.md |
All criteria (L, C, S, E, D) |
| Command | .claude/commands/*.md |
All criteria (L, C, S, E, D) — same frontmatter as skills |
| Prompt | PROMPT.md, *_PROMPT.md |
L, C, S, E only — no frontmatter, so skip D1-D3 |
Record the total count across all types for verification later.
Step 2: Load Criteria
Read CRITERIA.md for the full audit checklist.
Read SCORING.md for severity definitions.
Step 3: Audit Each File
For each discovered file:
- Read the file — note line count immediately
- Check applicable criteria from CRITERIA.md (see type table in Step 1)
- For skills with co-located PROMPT.md — audit the PROMPT.md too and report alongside the SKILL.md (they function as a unit)
- Record violations with criterion ID and evidence
Use this template per file:
File: <path>
Type: Skill | Command | Prompt
Lines: <count> (+ <N> in PROMPT.md if applicable)
Violations:
- <ID>: <brief evidence>
Step 4: Score and Prioritize
Group findings by severity (from SCORING.md):
- Critical: Likely to cause execution failures
- Medium: Degrades quality but may still work
- Low: Polish items
Within each severity, sort by:
- Most violations in single skill (fix skill holistically)
- Most common violation across skills (systemic issue)
Step 5: Output Report
Use this format:
# Skill Audit Report
Generated: <date>
Skills audited: <N>
Total findings: <N>
## Critical (fix first)
- **<skill-name>**: <violation summary> (<criterion-id>)
- Evidence: <quote or line numbers>
- Suggested fix: <concrete action>
## Medium Priority
...
## Low Priority
...
## Summary by Criterion
| ID | Description | Count |
|----|-------------|-------|
| C1 | Missing checklist | 5 |
| ... | ... | ... |
Error Handling
| Situation | Action |
|---|---|
| CRITERIA.md or SCORING.md not found | Report the missing file and stop — audit cannot proceed without criteria definitions. |
| No auditable files found (no skills, commands, or prompts) | Report that no files were discovered and stop. |
| Individual file unreadable | Log the file as "skipped (unreadable)" in the report and continue with remaining files. |
REMINDER: After completing the audit, verify your report includes all discovered files (skills, commands, and prompts). Missing files indicates incomplete analysis.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?