@krispuckett/skill-issue
AAudit and review all installed agent skills. Run on-demand or via cron to get a health report: skill inventory, usage tracking, version checks, dependency health, and actionable recommendations (keep, update, review, remove). Use when asked to review skills, check for skill updates, find unused skills, or audit the skill ecosystem.
Install
agr install @krispuckett/skill-issue --target claudeWrites 3 files into .claude/skills/, pinned to git-784e636a.
- .claude/skills/skill-issue/LICENSE
- .claude/skills/skill-issue/README.md
- .claude/skills/skill-issue/SKILL.md
Document
name: skill-issue description: "Audit and review all installed agent skills. Run on-demand or via cron to get a health report: skill inventory, usage tracking, version checks, dependency health, and actionable recommendations (keep, update, review, remove). Use when asked to review skills, check for skill updates, find unused skills, or audit the skill ecosystem."
Skill Issue — Skill Auditor
Audit all installed skills and produce a markdown report with recommendations.
Quick Start
# Basic — scans ./skills and ./memory
node scripts/audit.mjs
# Custom directories
SKILL_DIRS="./skills,/path/to/more/skills" MEMORY_DIR="./memory" node scripts/audit.mjs
# Save report
node scripts/audit.mjs > /tmp/skill-audit-report.md
Environment Variables
| Variable | Default | Description |
|---|---|---|
SKILL_DIRS | ./skills | Comma-separated skill directories to scan |
MEMORY_DIR | ./memory | Dated markdown logs for usage tracking |
AUDIT_DAYS | 7 | Days back to scan for usage |
What It Checks
- Inventory — Finds every subdirectory containing a
SKILL.mdwith YAML frontmatter - Usage — Scans recent memory/log files for skill name mentions
- Health — Verifies required binaries (
requires.bins) and env vars (requires.env) - Versions — Checks ClawdHub registry if
clawdhubCLI is available - Recommendations — keep (active+healthy), update (outdated), review (unused), remove (broken deps)
Safety
- Read-only — Never modifies, installs, or removes anything
- Advisory only — Recommendations require manual action
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-784e636a0b8e2026-07-31