review-code
Skill1 starsChanged 3 months agoMITView on GitHub
Judge code against the repository's own conventions. Use as a required review, or as /review-code. Not for tests: review-tests covers those.
68 other projects use a version of this.
Adopted by
Most recently taken up by
- Moriarty33/jb-kaizentheir own version, first seen Nov 8, 2026
- serionist/claude-session-restoretheir own version, first seen Nov 8, 2026
- GeiserX/sstacktheir own version, first seen Nov 8, 2026
- GeiserX/agent-skillstheir own version, first seen Nov 6, 2026
- GeiserX/claude-skillstheir own version, first seen Nov 6, 2026
- 0xdeafcafe/skillstheir own version, first seen Nov 6, 2026
Used with
Projects with it also use audit-test-suite, change-data-safely and 10 more.
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.
yaohuangguanSkillaudit-test-suite
Find where an existing test suite is weak and decide what to test next, ranked by risk. Use this when asked to add missing tests, find gaps, raise coverage, assess test quality or see which areas are thin, even if the request only mentions a coverage percentage.
Also in 3 projects that use this
yaohuangguanSkillchange-data-safely
Change a database schema or stored data without breaking running code or losing data. Use this for any migration, new or changed column, backfill, bulk update, delete, index, or change to a stored format, including in small projects. Data mistakes are often impossible to undo.
Also in 3 projects that use this
mrdulasolutionsSkillclear-caches
Clear extension caches, analysis data, and drafts from the database. Use when testing sender lookups, analysis, or draft generation from a clean state.
Also in 3 projects that use this
GeiserXSkilldocs-loop
Use when the user asks to audit docs, check documentation for stale claims, or verify docs against the code.
Also in 3 projects that use this
mrdulasolutionsSkillelectron-devtools-testing
Test the Electron app interactively using Chrome DevTools Protocol. Use when the user asks to test, verify, or interact with the running app via browser automation.
Also in 3 projects that use this
GeiserXSkillfull-loop
Drive a repository to done with sergio-loop, then keep improving it with refine-loop at a descending theta. Use only when the user explicitly invokes full-loop.
Also in 3 projects that use this
- +1 more from mrdulasolutions
- +4 more from GeiserX
- +1 more from yaohuangguan
Other versions68 projects use a version of this.
Word for word · 1
- cjohnhanson/almanac★ 1100% same
Edited · 0
None found.
Wrote their own version · 67
- penpot/penpot★ 62ksame name
- pnpm/pnpm★ 37ksame name
- verdaccio/verdaccio★ 18ksame name
- NVIDIA-NeMo/DataDesigner★ 2.4ksame name
- OpenAEV-Platform/openaev★ 1.8ksame name
- bazel-contrib/rules_python★ 692same name
- wataru-maeda/react-native-boilerplate★ 521same name
- ankitvgupta/exo★ 494same name
- ankitvgupta/mail-app★ 494same name
- ninehills/skills★ 280same name
57 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 repository5 other files it gives its agents.
- review-depsSkill
- review-docsSkill
- review-testsSkill
- review-usabilitySkill
- signoff-driverSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 56 edited versions we read keep these.
4
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 18
Read the neighbors before the change.
- Very specific: line 27
If code-review-eval is installed, load it and run its passes in its order: design, correctness, security, SOLID, smells, complexity.
- Distinctive: line 35
Judge by the neighbors: Read the code around the change first.
- Distinctive: line 38
minor: when the new one is a documented migration.
- Distinctive: line 51
Blocking: when the reach crosses a module boundary, minor within one.
“Common” is measured: kept by at least 6 in 10 of the 56 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
Review: code
You are one independent check on a change you did not write. Judge the
code. Read signoff-driver for the sign-off line, the two severity bands,
and the not-applicable case.
Method
Read the neighbors before the change. A repository's conventions live in its existing code, not in a document. A reviewer who reads only the diff cannot see a second pattern being invented.
Then three named catalogs. SOLID (Martin) for responsibility and substitution. Fowler's smells for naming a defect in a way its author can act on. The Law of Demeter and Inappropriate Intimacy for reach through an abstraction.
If code-review-eval is installed, load it and run its passes in its
order: design, correctness, security, SOLID, smells, complexity. Map its
four bands as signoff-driver states. Keep its rule that a lint
suppression is weighed rather than condemned. If architecture-eval is
installed, load it when the change moves a boundary.
Criteria
- Judge by the neighbors. Read the code around the change first. A change may invent a second pattern for a problem the repository already solves. That is blocking when both patterns stay live, and minor when the new one is a documented migration. Name the file that solves it the other way.
- Name each violation by its standard name. Say "feature envy",
"primitive obsession", "shotgun surgery", or which SOLID principle
broke. A named defect is arguable and fixable. "This feels wrong" is
neither. Grade the defect by reach, as
signoff-driverstates. - Judge reach through abstractions. Does a type expose its internals? Does a caller walk a chain to touch what is behind an abstraction, against the Law of Demeter? Does a module know a fact it must not know, which Fowler calls Inappropriate Intimacy? Ask what breaks when the thing behind the abstraction changes. Blocking when the reach crosses a module boundary, minor within one.
- Every error names its fix. An error stating a fault without the remedy makes the reader guess: minor. An error path that swallows a failure is blocking, because it turns a fault into wrong behavior with no signal.
- Weigh each lint suppression. A suppression needs a stated reason beside it, because the next reader cannot recover it. Judge whether the suppression is right before judging the comment. An unexplained suppression over correct code is minor; one hiding a real defect is blocking.
Worked examples
The defect lives beside the change, not in it
A change adds a config field and merges two config layers.
A weak review reads the diff, sees the field added to the struct and the default, confirms the types line up, and passes.
This skill reads the merge function beside the change and asks what happens to the new field there. The merge handles each field by name, and the new one is absent, so the repository layer is dropped whenever a user layer exists. The tests pass because they run with no user layer.
signoff[review-code] FAIL 0f00b85 blocking: overlaid_with never
carries reviews from the repo layer, so a user config empties the
listThe same change, after the fix
signoff[review-code] PASS 62628cd read the four call sites and the
merge beside the change; the union is handled by name and covered;
no reach crosses a module boundary; minor: merge_reviews repeats a
match arm that a helper would foldDoes 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.

