codex-write-prose-fix
Skill118 starsChanged 37 days agoMITView on GitHub
Reword one settled document so its prose lint passes, without changing meaning or any other file. The codex-fix-prose skill delegates this task with no inherited conversation context.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analyze-sessionSkill
- codex-analyze-sessionSkill
- codex-commitSkill
- codex-fix-proseSkill
- codex-fix-prSkill
- codex-merge-prSkill
- codex-prSkill
- codex-rebaseSkill
- codex-resolve-rebase-conflictsSkill
- codex-review-commit-messageSkill
- codex-review-pr-descriptionSkill
- codex-review-prose-fixSkill
- codex-review-squash-messageSkill
- codex-watch-prSkill
- codex-write-pr-descriptionSkill
- commitSkill
- fix-proseSkill
- fix-prSkill
- merge-prSkill
- prSkill
- rebaseSkill
- releaseSkill
- resolve-rebase-conflictsSkill
- review-commit-messageSkill
- review-pr-descriptionSkill
- review-prose-fixSkill
- review-squash-messageSkill
- watch-prSkill
- write-pr-descriptionSkill
- write-prose-fixSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Use apply_patch for edits.
≈ “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.
Files
Fix prose and nothing else
The delegation prompt supplies the repository root, target, workflow state, and lint command. Start by running .agents/skills/codex-write-prose-fix/scripts/context.sh <target> <state> <lint command> from that root. It prints the document, findings, scope probe, and saved review notes.
Preserve every claim, qualifier, number, path, identifier, and name. Reword, but don't rewrite. Only the target's prose may change. Leave linter configuration, dictionaries, every other file, fenced code, paths, and backticked identifiers untouched. Don't add suppression comments. Preserve the target’s wrapping convention.
Run mise run fix-prose-replacements <target> first. Fix the remaining list in one editing pass, then rerun the complete lint command. Stop when it's clean or after five rounds. Stop earlier if the count fails to fall twice or a cleared finding returns. Silence proves clean only after the context script established that the rules cover the path and the command produced findings before. Report a rule that no wording can clear without changing meaning.
Use apply_patch for edits. Return exactly one form:
PROSE: CLEAN
changed: <one line per class of edit>PROSE: PARTIAL
changed: <summary or nothing>
unresolved:
1. [<rule>] <line>: <exact text>
why: <cost of clearing it>PROSE: BLOCKED
reason: <what stopped the work>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
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.

