Skill Usage Audit
Monthly skill-usage audit — classify skills alive/dormant/unused using logs/skill-usage.jsonl (v7.0+), propose archive/refine actions
Install
$ agentstack add skill-leo-atienza-atlas-claude-skill-usage-audit ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-leo-atienza-atlas-claude-skill-usage-audit) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
You are running the monthly skill-usage audit. Its purpose is to keep the active-skills set honest: skills that are never invoked are cognitive overhead, not capability.
0. Prerequisites
This task depends on logs/skill-usage.jsonl, populated by the PreToolUse Skill hook added in ATLAS v7.0. If the file is missing or has records — not enough data to audit. Skipping this month; will resume when instrumentation has collected a representative window."
test -s ~/.claude/logs/skill-usage.jsonl && wc -l ~/.claude/logs/skill-usage.jsonl || echo "no data yet"1. Gather usage
node ~/.claude/scripts/observability.js --section=skill_usageFor raw JSON suitable for scripting:
node ~/.claude/scripts/observability.js --json | jq '.sections.skill_usage'2. Classify every active skill
For each skill listed in skills/ACTIVE-DIRECTORY.md:
- Alive — invoked in the last 30 days
- Dormant — invoked 30–90 days ago
- Unused — no invocation in skill-usage.jsonl at all
Cap each list at 25 entries. If truncated, append "… +N more".
3. Propose actions (do NOT execute automatically)
For each Unused skill, look at:
- The skill's created/modified date on disk (has it had time to be used?).
- Its declared purpose (niche-but-important skills like skill-creator, security-review may warrant keeping).
Recommend one of: Archive (/skill-archive or mv to skills/_archived/), Keep (explain why), or Refine (unclear trigger/rename).
4. Summary
Output exactly:
Skill-usage audit —
Alive:
Dormant:
Unused:
Recommended archives:
Recommended refinements: This sweep is advisory only — never delete skills unattended. The user decides.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Leo-Atienza
- Source: Leo-Atienza/atlas-claude
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.