audit-content-quality SKILL.md skillA
audit-content-quality from velimirmueller/lab-claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add velimirmueller/lab-claude-skills/audit-content-quality@git:20261009.0ae007bPins git:20261009.0ae007b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- velimirmueller/lab-claude-skills
- Path
skills/landing/audit-content-quality/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261009.0ae007b, committed Oct 9, 2026
- First version recorded
- Jun 10, 2026
- Size
- 3,022 bytes
- Repository stars
- 5
- License
- MIT
Use when reviewing an article, guide, or landing page before publishing or republishing — scores it against a rubric (project's .claude/rubrics/content-quality.md, else the bundled default) with quoted evidence and fixes only the failed criteria.
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
# Audit Content Quality Score first, then fix *only the gaps* — never rewrite what already passes. The procedure is generic; the law comes from a rubric file, so a team's own scorecard (points, knockouts, house rules) plugs in without changing the skill. ## 1. Gate — is this a public page? Run the gate from `../_shared/page-types.md`. Content quality scoring is for pages meant to be found and read; app surfaces are out of scope. ## 2. Load the rubric Per `../_shared/rubric-convention.md`: ```bash cat .claude/rubrics/content-quality.md 2>/dev/null # project law, if present ``` Present → it is the entire rubric (criteria, knockouts, any points/weights it defines). Present but empty — or with no `##` criterion headings — → malformed: report it and stop; do not fall through to the default (`../_shared/rubric-convention.md`). Absent → use `./default-rubric.md`, and offer the install at the end of the report. ## 3. Gather the page ```bash curl -s "$URL" -o /tmp/page.html # or the built file ``` Read the rendered text top to bottom — the audit quotes evidence, so skimming isn't enough. Identify the page's target question/intent first (from title + h1); several …
Read the whole file at its exact version.
How to install
mdr add velimirmueller/lab-claude-skills/audit-content-quality@sha256:b4263f36354da90cThe line at the top of this page pins the label git:20261009.0ae007b, 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_tob42rvb3znaco5l)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jun 10, 2026 and Oct 9, 2026, about one every 60 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261009.0ae007b latest | 2026-10-09 | 0ae007b | 3,022 B | A | view · diff |
| git:20260610.f3949f8 | 2026-06-10 | f3949f8 | 3,201 B | A | view · diff |
| git:20260610.6f56716 | 2026-06-10 | 6f56716 | 3,033 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 (3022 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
velimirmueller/lab-claude-skills · 5 stars · license MIT · pushed 2026-10-12 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tob42rvb3znaco5l GET https://markdownregistry.com/api/v1/resolve?ref=velimirmueller/lab-claude-skills/audit-content-quality GET https://markdownregistry.com/api/v1/blob/b4263f36354da90c50b6a7a32b18e053e61f2422bdc60b9ebc0104ca89608fa6
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 velimirmueller/lab-claude-skills
Every file in velimirmueller/lab-claude-skills