review-workflow
Skill0 starsChanged 7 months agoMITView on GitHub
Use when a change should receive a structured review before merge, handoff, or closure and the findings should be captured in `docs/reviews` or the issue doc. Trigger for non-trivial code changes, architecture changes, risky bug fixes, or external-tool evaluations. This skill defines review content and findings, not whether sub-agents should be used to perform the review.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- issue-orchestrator/issue-orchestratortheir own version, first seen Sep 6, 2026
- sasuketorii/rev_harness_publictheir own version, first seen Aug 19, 2026
- Abeautifulsnow/skillstheir own version, first seen Jul 28, 2026
- hefgi/skillstheir own version, first seen Jul 5, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- issue-orchestrator/issue-orchestrator★ 10same name
- hefgi/skills★ 7same name
- Abeautifulsnow/skills★ 2same name
- sasuketorii/rev_harness_public★ 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 repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- decision-recordingSkill
- harness-bootstrapSkill
- issue-driven-workflowSkill
- planning-workflowSkill
- spec-writingSkill
- subagent-workflowSkill
- technical-learning-noteSkill
- troubleshooting-workflowSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 8
Run meaningful changes through a repeatable review instead of relying on scattered comments.
- Distinctive: line 13
Read validation evidence before commenting on style.
- Very specific: line 40
Use subagent-workflow only if the review should be delegated or split across roles.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Review Workflow
Run meaningful changes through a repeatable review instead of relying on scattered comments.
Default flow
- Confirm what changed and why it was done.
- Read validation evidence before commenting on style.
- Check:
- correctness
- readability
- boundary fit
- operational risk
- follow-up work
- Separate blockers from suggestions.
- Record the result where the next contributor will see it:
- issue doc for small reviews
docs/reviews/for broader analysis or reusable findings
Good fit
- multi-file implementation work
- high-risk fixes
- architecture or tooling changes
- external package or service evaluation
Avoid for
- obvious typo fixes
- tiny changes with no real behavioral risk
Resources
- See
references/review-lenses.mdfor a short review checklist. - Use
subagent-workflowonly if the review should be delegated or split across roles.
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.