change-review
Skill0 starsChanged 11 days agoMITView on GitHub
Use before committing, pushing, or declaring work ready, and when asked to review a diff, branch, or merge request. Checks correctness, security, data safety, capability standards, tests and evidence, and maintainability, and reports findings with severity and file references.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- amkisko/prayerstheir own version, first seen Nov 6, 2026
- BurakD/ai-engineering-harnesstheir own version, first seen Nov 1, 2026
- assistant-ui/assistant-uitheir own version, first seen Oct 25, 2026
- yuanJewel/skillstheir own version, first seen Oct 11, 2026
- marinsokol5/change-reviewtheir own version, first seen Sep 19, 2026
- goldenprofile/llm-skillstheir own version, first seen Aug 12, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- assistant-ui/assistant-ui★ 13ksame name
- goldenprofile/llm-skills★ 3same name
- amkisko/prayers★ 2same name
- flying-dice/pseudoscript★ 2same name
- yuanJewel/skills★ 2same name
- BurakD/ai-engineering-harness★ 1same name
- marinsokol5/change-review★ 1same name
- straider911/claude-skills★ 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 repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- backend-engineeringSkill
- change-planningSkill
- device-healthSkill
- genai-engineeringSkill
- instruction-maintenanceSkill
- pakemSkill
- pakem-updateSkill
- project-bootstrapSkill
- release-deliverySkill
- root-cause-debuggingSkill
- sensitive-operationsSkill
- state-and-handoffSkill
- ui-ux-qualitySkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Run the project's format check, lint, type check, tests, and build exactly as CI does.
- Distinctive: line 16
Check capabilities: if the diff adds one (database, deployed, money, personal-data, background-jobs, api-consumers, multi-user, llm), its …
- Distinctive: line 24
Read the linked plan or OpenSpec change first.
- Distinctive: line 29
Do not rewrite the change yourself unless asked.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Change Review
1. Before declaring your own work ready
- Run the project's format check, lint, type check, tests, and build exactly as CI does; record results against the revision tested.
- Walk the review checklist over the full diff
(
git diff <base>...HEADplus untracked files). - Confirm every task's named evidence exists and the change's
verification.mdis complete (testing standard). - Check capabilities: if the diff adds one (database, deployed, money, personal-data, background-jobs, api-consumers, multi-user, llm), its standards are present or recorded as debt.
- Report passed, failed, not run, and blocked separately. Never call work ready with failing or skipped required checks.
2. Reviewing someone else's change
- Read the linked plan or OpenSpec change first; review against its acceptance.
- Trace each changed path through callers and contracts; do not review lines in isolation.
- Report findings as described in section 3; confirm each finding against the code before reporting it. Separate verified defects from questions and suggestions.
- Do not rewrite the change yourself unless asked.
3. Findings format
For each finding: severity (blocker, major, minor, nit), file:line, what is wrong,
the concrete failure scenario (inputs or state leading to the wrong result), and the
suggested fix. Order by severity. If nothing survives verification, say so.
4. Related skills
- Reliability, data, and API checks:
backend-engineering. - Secrets, migrations, production, deletion:
sensitive-operations. - UI and accessibility evidence:
ui-ux-quality. - LLM features:
genai-engineering.
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.