agentleFS
namddpnamddp/social-media-agent-skills/skills/social-quality-auditor/SKILL.md

social-quality-auditor

Skill0 starsChanged 3 months agoMITView on GitHub

Audit a social draft for evidence, voice, platform fit, usefulness, accessibility, and publishing safety.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check the draft against the voice anchors and anti-patterns.

    line 22
  2. Distinctive:

    Test whether the format feels native to the target platform.

    line 23
  3. Distinctive:

    Every blocker describes a concrete failure and resolution.

    line 43
  4. Distinctive:

    Do not silently rewrite quotes or legal disclosures.

    line 51
  5. Distinctive:

    Never publish, schedule, reply, or message from this workflow.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Social Quality Auditor

Purpose

Produce a release-style review that identifies material problems without rewriting the author's voice by default.

Inputs

  • Draft content and target platform
  • Source brief and voice card
  • Campaign objective and desired reader action
  • Optional output from social-skills lint

Workflow

  1. Trace every factual claim to the source brief.
  2. Check the draft against the voice anchors and anti-patterns.
  3. Test whether the format feels native to the target platform.
  4. Evaluate usefulness, clarity, accessibility, disclosure, and call-to-action fit.
  5. Classify findings as Blocker, Important, or Polish.
  6. Suggest the smallest revision that resolves each material finding.
  7. Return a publish recommendation without publishing.

Output

# Social quality audit
- Recommendation: BLOCK / REVISE / READY FOR HUMAN APPROVAL
## Blockers
## Important findings
## Polish
## Verified claims
## Required human decisions

Quality gate

  • Every blocker describes a concrete failure and resolution.
  • Style preferences are not mislabeled as factual errors.
  • A clean audit still states which claims and decisions were checked.
  • READY means ready for human approval, never automatically approved.

Safety

  • Block unsupported claims, missing disclosures, privacy leaks, and unsafe advice.
  • Do not silently rewrite quotes or legal disclosures.
  • Never publish, schedule, reply, or message from this workflow.

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.