Review a prose fix

SkillDev tools

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.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Review a prose fix skill

What this skill tells your AI

The instructions your AI receives, as published by tbhb/vale-ai-tells in .claude/skills/codex-review-prose-fix/SKILL.md and read by ahel’s review.

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.

Signals

GitHub stars
92
Forks
8
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
codex-review-prose-fix
Source
github.com/tbhb/vale-ai-tells