agentleFS
Sign inStart free
mtarcuremtarcure/claude-vibe-squad/.agents/skills/copy-refinement/SKILL.md

copy-refinement

Skill220 starsChanged 18 days agoMITView on GitHub

Use when revising an existing draft for clarity, structure, and established voice while preserving its meaning and factual claims; produce a semantic diff and escalate uncertain voice choices to brand-voice. For new marketing copy, use brand-voice instead.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Read for intent: what the copy must do and who it addresses.

    line 12
  2. Distinctive:

    Verify no factual claim was introduced or distorted.

    line 21
  3. Distinctive:

    No new/unsupported claims introduced.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Copy Refinement

Tighten existing copy for clarity, voice, and correctness without changing its meaning or inventing claims.

Steps

  1. Read for intent: what the copy must do and who it addresses; preserve that job through every edit.
  2. Cut redundancy and hedging; make each sentence earn its place and each claim verifiable.
  3. Enforce voice/tone and terminology against the operator-approved voice memory. If that authority is absent, stale, or ambiguous, name brand-voice as the required guidance follow-up and stop the voice-specific rewrite instead of inventing a standard.
  4. Fix grammar, mechanics, and structure; improve flow and scannability (headings, front-loading).
  5. Produce a semantic-diff table for every substantive edit: original meaning, revised meaning, factual claims before/after, and the voice-memory rule applied. Revert or flag any row whose meaning or claim changed without explicit authorization.
  6. Verify no factual claim was introduced or distorted; flag any claim that needs a source rather than asserting it.

Acceptance

  • Meaning is preserved; the copy is tighter and clearer, not just different.
  • The semantic-diff table demonstrates meaning and claim preservation for every substantive edit.
  • Voice and terminology trace to the approved voice memory, or the ambiguity is handed to brand-voice.
  • No new/unsupported claims introduced; claims needing sources are flagged.

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