agentleFS
Sign inStart free
XuHo-ITXuHo-IT/Content-Agent-Kit/skills/audit-and-fix/SKILL.md

audit-and-fix

Skill3 starsChanged 3 months agoMITView on GitHub

Audit ALREADY-published content and fix low-quality items, for an agent built with content-agent-kit. Use when the user says "audit the published content", "review old posts and fix them", or "clean up the backlog". Rule-audit first, then subagent grading, then STOP for confirmation before mutating live content.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Rule-based audit first (cheap): Run the project's rule audit (e.g.

    line 11
  2. Very specific:

    STOP and present: Write audit_report.md (failing items + proposed fixes) and show the user.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Audit & fix (published content)

This is separate from daily creation and it mutates LIVE content — so it stops for human confirmation before changing anything.

  1. Rule-based audit first (cheap). Run the project's rule audit (e.g. node scripts/audit-quality.mjs) → audit_report.md. Hard rules only: length, missing fields, broken id references, duplicate/missing images. No AI needed.
  2. List recent published items: node scripts/list-published.mjs --limit 40 → audit_input.json.
  3. Subagent audit (fan-out) — one reviewer per item grades cover/images/content/logic → { id, ok, issues[] }.
  4. STOP and present. Write audit_report.md (failing items + proposed fixes) and show the user. Do NOT change anything until they choose which items to fix.
  5. Fix confirmed items — regenerate the bad part / new images, keep the id stable, apply with node scripts/update.mjs <fix>.json. Re-audit to confirm clean.
  6. Report → brain/<id>/audit_fix_report.md: fixed / skipped / dropped.

Priority: items visible to logged-out / free users first, then paid, then the long tail. Work in batches of 20–30 (not >100 per run).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free