skill-audit SKILL.md skillA
skill-audit from vanducng/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add vanducng/skills/skill-audit@v0.1.0Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- vanducng/skills
- Path
skills/skill-audit/SKILL.md- Versions recorded
- 4
- Latest version
- v0.1.0, committed Sep 11, 2026
- First version recorded
- Jul 17, 2026
- Size
- 7,592 bytes
- Repository stars
- 8
- License
- MIT
Mine your Claude Code, Codex, pi and Cursor session history for how your skills actually get used - invocations, coverage, tool-error rates, corrections, interrupts, tokens - attributed per invocation rather than per session, then turn the aggregates into a reviewed report. Use when the user says 'audit my skills', 'which skills do I actually use', 'skill usage stats', 'are my skills working', 'mine my session history', or asks which skills to keep, merge, or drop.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Skill Audit Answers "which skills earn their keep, and which are quietly failing?" from transcripts, not vibes. Deterministic mining first, agent judgment second - never the reverse. ## Workflow 1. **Mine.** `python3 scripts/mine-sessions.py --since 30 --out <scratch dir>` (stdlib only, any python3 >= 3.9; fall back to `~/.claude/skills/.venv/bin/python3` if the system python3 is older; `--runtime claude|codex|pi|cursor|all`, default all; `both` stays as a legacy alias for claude+codex). `--since` filters individual events, including subagent events. Writes `skill-aggregates.json` + `sessions-<runtime>.jsonl` and prints a top-15 table. Multi-GB corpora stream fine; a missing runtime dir is a note, not an error. 2. **Read the aggregates.** Rank by the question asked - usage (`invocations`, `projects`), quality (`err_rate`, `corrections`, `interrupts` on `solo_sessions`), cost (`tokens`), coverage (`coverage.never_used`). 3. **Verify before concluding.** Counters flag *candidates*. Open `sessions-<runtime>.jsonl`, find the session, read the transcript. No claim of "skill X is broken" ships without a quote. …
Read the whole file at its exact version.
How to install
mdr add vanducng/skills/skill-audit@sha256:a7c7756544ab4810The line at the top of this page pins the label v0.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_rlngmo4jwghddh4r)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 17, 2026 and Sep 11, 2026, about one every 19 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.0 latest | 2026-09-11 | 9e58ef3 | 7,592 B | A | view · diff |
| v0.1.0 | 2026-07-24 | 51405ee | 6,927 B | A | view · diff |
| v0.1.0 | 2026-07-18 | a50575f | 6,953 B | A | view · diff |
| v0.1.0 | 2026-07-17 | 77e2152 | 6,889 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7592 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
vanducng/skills · 8 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rlngmo4jwghddh4r GET https://markdownregistry.com/api/v1/resolve?ref=vanducng/skills/skill-audit GET https://markdownregistry.com/api/v1/blob/a7c7756544ab481015be23d8b0e944c49044703cbaecd54447dc44a610764d09
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.