skill-issue

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.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "skill-issue" with this command: npx skills add krispuckett/skill-issue/krispuckett-skill-issue-skill-issue

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

VariableDefaultDescription
SKILL_DIRS./skillsComma-separated skill directories to scan
MEMORY_DIR./memoryDated markdown logs for usage tracking
AUDIT_DAYS7Days back to scan for usage

What It Checks

  1. Inventory — Finds every subdirectory containing a SKILL.md with YAML frontmatter
  2. Usage — Scans recent memory/log files for skill name mentions
  3. Health — Verifies required binaries (requires.bins) and env vars (requires.env)
  4. Versions — Checks ClawdHub registry if clawdhub CLI is available
  5. Recommendations — keep (active+healthy), update (outdated), review (unused), remove (broken deps)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

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open in GitHubOpen in ClawHub

Related Skills

Related by shared tags or category signals.

Security

Sentinel — Agent Security Layer

Runtime security layer for OpenClaw agents. Intercepts and scans all external input (emails, API responses, web content, chat messages, calendar events) for...

Registry SourceRecently Updated
520Profile unavailable
Security

Ring Security

Monitor and manage Ring doorbells and security cameras. Query device status, review motion events, manage modes, and export event history. Use when you need...

Registry SourceRecently Updated
1780Profile unavailable
Security

Watadot Aws Iam

IAM security patterns by Watadot Studio. Manage users, roles, and policy verification.

Registry SourceRecently Updated
120Profile unavailable
Security

Moses Audit

MO§ES™ Audit Trail — SHA-256 chained append-only governance ledger. Every agent appends before final response. Provides moses_log_action and moses_verify_cha...

Registry SourceRecently Updated
870Profile unavailable