skill-audit SKILL.md skillA
skill-audit from ai-business-tools/claude-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ai-business-tools/claude-code/skill-audit@git:20260830.80a4dcdPins git:20260830.80a4dcd in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ai-business-tools/claude-code
- Path
skills/skill-audit/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260830.80a4dcd, committed Aug 30, 2026
- First version recorded
- Jun 4, 2026
- Size
- 11,827 bytes
- Repository stars
- 5
- License
- MIT
Audit recent Claude Code session transcripts for recurring friction (repeated corrections, routing misfires, repeated reprompts, enforcement gaps, post-upgrade regressions) and sweep your skill files for a standard stated in more than one place, orphaned reference files, and broken pointers, then recommend conservative changes to your personal skills, CLAUDE.md, protocols, or settings. Report-only: it proposes, it never edits. Prefers no change. Triggers on "skill audit", "audit my skills…
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 Audit recent Claude Code session transcripts for recurring friction and recommend conservative changes to your personal configuration. This skill **proposes only; it never edits anything**. Prefer no change. "Recommend nothing" is a valid and common result. ## Argument - No argument: scan the last **7 days**. - A number: scan that many days (for example, `14`). ## Model Runs on a mid-tier model by default, which is sufficient given the report-only design and the mandatory verification step below. For the run right after a model upgrade, when catching regressions is the point, invoke under the strongest available model. ## Report-only contract This skill reads transcripts and configuration and produces a report. It does not change any file. After you rule on the findings, the actual edits and the two log updates (below) are made as a separate, deliberate step outside this skill. ## State files (in this skill's folder) - `declined.md`: findings you have ruled "do not pursue." **Read this first, every run.** Do not re-recommend a matching item. If the friction still recurs, note it as "previously declined, still occurring," without re-proposing the fix. …
Read the whole file at its exact version.
How to install
mdr add ai-business-tools/claude-code/skill-audit@sha256:4047c9ea7465f52eThe line at the top of this page pins the label git:20260830.80a4dcd, 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_s7kjyznohtnqau2p)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jun 4, 2026 and Aug 30, 2026, about one every 44 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260830.80a4dcd latest | 2026-08-30 | 80a4dcd | 11,827 B | A | view · diff |
| git:20260830.4d0b69c | 2026-08-30 | 4d0b69c | 9,459 B | A | view · diff |
| git:20260604.286c7b2 | 2026-06-04 | 286c7b2 | 7,533 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 (11827 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
ai-business-tools/claude-code · 5 stars · license MIT · pushed 2026-09-25 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_s7kjyznohtnqau2p GET https://markdownregistry.com/api/v1/resolve?ref=ai-business-tools/claude-code/skill-audit GET https://markdownregistry.com/api/v1/blob/4047c9ea7465f52ee4d5962bafa86b57f254d9a5eb1c6ede2eefd27ab8928fff
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.
More from ai-business-tools/claude-code
Every file in ai-business-tools/claude-code