docs-review
Skill18 starsChanged 5 months agoMITView on GitHub
Review project docs for staleness. Checks lib.rs, Cargo.toml, README, CONTRIBUTING, SECURITY, PRIVACY, and GitHub repo metadata.
27 other projects use a version of this.
Adopted by
Most recently taken up by
- SVN11X/skillstheir own version, first seen Nov 16, 2026
- swarm-routing/skillstheir own version, first seen Nov 15, 2026
- mintlify/docstheir own version, first seen Nov 9, 2026
- langchain-ai/docstheir own version, first seen Nov 2, 2026
- mindroom-ai/mindroomtheir own version, first seen Nov 1, 2026
- NathanForster/claude-commandstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use code-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 4 projects that use this
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
- storybookjs/storybook★ 92ksame name
- metabase/metabase★ 50ksame name
- grafana/tempo★ 5.6ksame name
- graphistry/pygraphistry★ 2.6ksame name
- perber/leafwiki★ 1.2ksame name
- jtenniswood/espcontrol★ 1.2ksame name
- Harry-kp/vortix★ 779same name
- getsentry/sentry-rust★ 755same name
- mintlify/docs★ 467same name
- langchain-ai/docs★ 452same name
17 more not listed
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 repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- archeoSkill
- auditSkill
- before-editSkill
- boundary-probeSkill
- check-my-workSkill
- cqs-batchSkill
- cqs-bootstrapSkill
- cqs-planSkill
- cqsSkill
- cqs-verifySkill
- groom-notesSkill
- idleSkill
- investigateSkill
- landSkill
- migrateSkill
- prSkill
- recall-gateSkill
- reindexSkill
- releaseSkill
- troubleshootSkill
- update-tearsSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 10 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 26 edited versions we read keep these.
10
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
- Distinctive: line 9
Check all project documentation for staleness and fix what's drifted.
- Distinctive: line 14
Run git log vLAST_TAG..HEAD --stat to see what changed since last release
- Distinctive: line 16
If no tag exists, review everything
- Distinctive: line 34
If unsure about a claim, flag it rather than guessing
- Very specific: line 38
Before releases (/release references this)
- Distinctive: line 39
After significant feature PRs
- Distinctive: line 41
When you suspect drift
- Distinctive: line 45
Don't rewrite docs for style — only fix factual staleness
- Distinctive: line 46
Don't add content — only correct what exists
- Distinctive: line 47
Check numbers against code: grep for hardcoded counts (languages, tests, dimensions) and verify
- Distinctive: line 48
If CONTRIBUTING.md Architecture Overview lists files, glob to confirm they exist
“Common” is measured: kept by at least 6 in 10 of the 26 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
Docs Review
Check all project documentation for staleness and fix what's drifted.
Process
- Scope the review:
- Run
git log vLAST_TAG..HEAD --statto see what changed since last release - Focus on docs affected by those changes
- If no tag exists, review everything
- Run
Check each item:
File What to check src/lib.rsdoc commentLanguage count, feature list, API examples compile, Quick Start accuracy Cargo.tomldescription(crates.io one-liner),keywords,categoriesREADME.mdHardcoded versions (schema, install), feature list, usage examples, badge URLs CONTRIBUTING.mdArchitecture Overview matches current file layout — any files added/moved/renamed? SECURITY.mdThreat model current, dependency notes, any new attack surfaces? PRIVACY.mdData handling claims still accurate? CLAUDE.mdSkills list matches .claude/skills/; Project Conventions accurate (MSRV, feature names); WSL/CI guidance not contradicting current practiceGitHub repo Description and topics — gh repo view, update withgh repo editif needed- Fix and report:
- Fix stale docs directly
- Report what was updated and what was already current
- If unsure about a claim, flag it rather than guessing
When to run
- Before releases (
/releasereferences this) - After significant feature PRs
- Before audits
- When you suspect drift
Rules
- Don't rewrite docs for style — only fix factual staleness
- Don't add content — only correct what exists
- Check numbers against code: grep for hardcoded counts (languages, tests, dimensions) and verify
- If CONTRIBUTING.md Architecture Overview lists files, glob to confirm they exist
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.

