agentleFS
tbhbtbhb/vale-ai-tells/.claude/skills/codex-review-prose-fix/SKILL.md

codex-review-prose-fix

Skill118 starsChanged 37 days agoMITView on GitHub

Independently review a prose-lint fix for changed meaning, lost precision, unrelated edits, suppression comments, and language defects the linter can't score. The codex-fix-prose skill delegates this after the writer finishes. Use only as a read-only reviewer.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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 the resulting target in full.

    line 16
  2. Distinctive:

    Don't edit any file.

    line 34

≈ “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

Review a prose fix

The caller supplies the repository root, target, and workflow state. Work read-only. Run:

bash .agents/skills/codex-fix-prose/scripts/check-suppressions.sh --diff <state> <target>
bash .agents/skills/codex-fix-prose/scripts/check-suppressions.sh --verify <state> <target>

Read the resulting target in full. Don't repeat the prose lint command. Its clean result is the premise of this review.

Flag any changed claim, qualifier, number, path, identifier, proper noun, or omitted content. Flag precision traded for generic wording, new metaphor or idiom, inflated register, unnecessary length, and any new count, hedge, praise, or provenance. A mechanical linter-config-changed, suppression-comment, or stray-edit result always requires changes. Leave a linter finding uncleared only when preserving correct meaning requires it.

Sweep the whole diff for every class of issue you find, then return exactly:

REVIEW: CLEAN

or:

REVIEW: CHANGES REQUIRED

1. `<exact text>` — <problem>. Fix: <specific correction>.

Don't edit any file.

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.