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.
Scanned 9/13/2026
Install to Claude Code
npx -y skills add tbhb/vale-ai-tells --skill codex-review-prose-fix --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Codex Review Prose Fix?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/tbhb-codex-review-prose-fix)More formats (shields.io, HTML) on the badges page.
---
name: codex-review-prose-fix
description: >-
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.
---
# Review a prose fix
The caller supplies the repository root, target, and workflow state. Work read-only. Run:
```text
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:
```text
REVIEW: CLEAN
```
or:
```text
REVIEW: CHANGES REQUIRED
1. `<exact text>` — <problem>. Fix: <specific correction>.
```
Don't edit any file.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling