writing-review
Skill0 starsChanged yesterdayMITView on GitHub
Review public-facing writing for artificial simplicity, vagueness, awkward phrasing and lost precision, and propose rewrites that keep the meaning. For pull request descriptions, issue text, release notes, documentation and kit guidance. Load it by its path.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- slogsdon/skills-writingtheir own version, first seen Nov 12, 2026
- michaelwjohnson/claude-skillstheir own version, first seen Nov 1, 2026
- ragnos-labs/skill-indextheir own version, first seen Aug 23, 2026
- markrstevenson/skillstheir own version, first seen Aug 10, 2026
- darrenCWJ/agent-skills-scaffoldtheir own version, first seen Aug 9, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- darrenCWJ/agent-skills-scaffold★ 0same name
- markrstevenson/skills★ 0same name
- michaelwjohnson/claude-skills★ 0same name
- ragnos-labs/skill-index★ 0same name
- slogsdon/skills-writing★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- humanizerSkill
- release-notesSkill
- review-issuesSkill
- review-public-docsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
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 14
Every text a reader outside this session will read: pull request descriptions and comments, issue text, release notes, CHANGELOG.md, …
- Distinctive: line 24
Leave clear, natural and accurate sentences alone.
- Distinctive: line 25
Check each rewrite against the original: the same scope, conditions and certainty, and no new fact.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Writing review
references/framework.md is the standard. Read it in full before you review.
It names twelve writing problems, how to fix each one, and when a rewrite is
an improvement.
What it covers
Every text a reader outside this session will read: pull request descriptions
and comments, issue text, release notes, CHANGELOG.md, README.md,
docs/DESIGN.md, CONTRIBUTING.md, and the Markdown guidance under kit/.
How to run it
- Establish the meaning first: the actors, operations, conditions and reader. For a claim about the kit, read the code or the diff that supports it.
- Review the text against the twelve criteria. Report each problem with the original sentence, the criterion, the reason and a rewrite.
- Leave clear, natural and accurate sentences alone.
- Check each rewrite against the original: the same scope, conditions and certainty, and no new fact.
- Then run
.agents/maintainer-skills/humanizer/SKILL.mdin its embedded mode.
For a release, a long document or a text you wrote yourself, ask a fresh reviewer to review the text: a subagent, or Codex in a read-only subprocess. Make the recommended changes yourself, after checking each finding against the evidence.
Fixed constraints
These override the framework where the two conflict: British spelling, no contractions in release notes, no em or en dashes, no issue or pull request numbers in a tracked file, and every command, setting and name kept exactly as written.
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.

