project-review
Skill0 starsChanged 6 months agoMITView on GitHub
Review a project and its git/GitHub history to capture learnings, summarize findings, propose improvements, and hand off a first draft PR. Use when the user says "project review", "review this project", "capture learnings", or asks for an improvement review from project history.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- Eleven-M/flowmindtheir own version, first seen Nov 8, 2026
- ubermuda/loupetheir own version, first seen Nov 8, 2026
- 70asunflower/70asunflower-skillstheir own version, first seen Nov 8, 2026
- SWEStash/swe-workflow-skillstheir own version, first seen Nov 8, 2026
- lamtuanvu/pacertheir own version, first seen Nov 1, 2026
- Lumosylva/lumosylva-skillstheir own version, first seen Oct 25, 2026
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- jerry-ai-dev/MODULAR-RAG-MCP-SERVER★ 1.2ksame name
- jiahao-shao1/sjh-skills★ 43same name
- 5throck/ai-workspace-standards★ 25same name
- rittmananalytics/wire-plugin★ 14same name
- fqmyysjjd/agent-feed★ 4same name
- ila/duckdb-claude-skills★ 4same name
- ubermuda/loupe★ 2same name
- 70asunflower/70asunflower-skills★ 1same name
- davidsolheim/skills★ 1same name
- Eleven-M/flowmind★ 1same name
5 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 repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- plugin-v2/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- plugin-v2/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/agents.mdcCursor rule
- agentic-security-reviewSkill
- arc42-baselineSkill
- caveman-commitSkill
- caveman-helpSkill
- caveman-reviewSkill
- cavemanSkill
- create-goalSkill
- design-twiceSkill
- discovery-sprintSkill
- domain-contextSkill
- github-project-setupSkill
- grillSkill
- improve-codebase-architectureSkill
- issue-breakdownSkill
- issue-draftSkill
- issue-pr-syncSkill
- new-adrSkill
- new-glossary-entrySkill
- orchestrateSkill
- portfolio-trackSkill
- product-pageSkill
- project-runSkill
- project-scaffoldingSkill
- quality-assuranceSkill
- quality-metricsSkill
- record-decisionSkill
- review-fixSkill
- roadmap-managementSkill
- sales-cycleSkill
- specorator-designSkill
- specorator-improvementSkill
- specorator-onboardSkill
- stock-takingSkill
- tackle-issueSkill
- tdd-cycleSkill
- token-budget-reviewSkill
- tracer-bulletSkill
- ubiquitous-languageSkill
- verifySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 6 are distinctive, and 8 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 9
Use this skill to run the Project-review workflow defined in docs/project-review-workflow.md.
- Very specific: line 27
Start: Create the review state file from templates/project-review-state-template.md.
- Very specific: line 28
Plan: Create review-plan.md; name artifact paths, git ranges, GitHub queries, CI evidence, local issue mirror evidence when relevant, …
- Very specific: line 29
Inspect: Create history-review.md; summarize git, PR, issue, CI, workflow-state, local issue mirror, and artifact signals.
- Very specific: line 30
Synthesize: Create findings.md; distinguish strengths, friction, risks, root-cause hypotheses, and open questions.
- Very specific: line 31
Propose: Create improvement-proposals.md.
- Distinctive: line 36
Prefer primary repo evidence: committed artifacts, commit SHAs, PRs, issues, CI runs, release tags, and command summaries.
- Very specific: line 37
Treat npm run check:backlog and npm run sync:backlog -- --dry-run --json as advisory issue mirror evidence unless the reviewed project …
- Distinctive: line 40
Keep unknowns visible in the relevant artifact.
- Distinctive: line 41
Do not use raw log dumps; summarize and cite.
- Distinctive: line 45
Do not replace feature retrospectives.
- Very specific: line 46
Do not edit source or workflow artifacts outside quality/<slug>/ until the handoff worktree is created for the first proposal.
- Distinctive: line 47
Do not merge the draft PR or delete branches.
- Distinctive: line 48
Do not make constitution or governance changes without ADR/human approval.
“Common” is measured: kept by at least 6 in 10 of the 11 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
Project Review
Use this skill to run the Project-review workflow defined in docs/project-review-workflow.md.
The workflow is evidence-first: review artifacts and history, capture learnings, rank improvements, then create a tracking issue and first draft PR from a separate worktree.
Phases
| Phase | Command | Primary outputs |
| Start | /project-review:start <slug> <scope> | quality/<slug>/project-review-state.md |
| Plan | /project-review:plan <slug> | review-plan.md |
| Inspect | /project-review:inspect <slug> | history-review.md |
| Synthesize | /project-review:synthesize <slug> | findings.md |
| Propose | /project-review:propose <slug> | improvement-proposals.md |
| Handoff | /project-review:handoff <slug> | GitHub issue + first draft PR |
Procedure
- Intake gate. List
inputs/non-recursively before scoping. Surface relevant items to the user; never auto-extract archives. Cite consumed paths inreview-plan.md. - Start. Create the review state file from
templates/project-review-state-template.md; record scope, repo, integration branch, and review period. - Plan. Create
review-plan.md; name artifact paths, git ranges, GitHub queries, CI evidence, local issue mirror evidence when relevant, review questions, exclusions, and first-PR selection criteria. - Inspect. Create
history-review.md; summarize git, PR, issue, CI, workflow-state, local issue mirror, and artifact signals. Link every claim to a source. - Synthesize. Create
findings.md; distinguish strengths, friction, risks, root-cause hypotheses, and open questions. - Propose. Create
improvement-proposals.md; rank proposals and pick one first draft PR candidate. - Handoff. Open a tracking issue when GitHub access is available, create a worktree for the first proposal, implement or scaffold it, verify, commit, push, and open a draft PR. Update
project-review-state.mdwith issue URL, PR URL, branch, commit SHA, verification, and remaining risks.
Evidence rules
- Prefer primary repo evidence: committed artifacts, commit SHAs, PRs, issues, CI runs, release tags, and command summaries.
- Treat
npm run check:backlogandnpm run sync:backlog -- --dry-run --jsonas advisory issue mirror evidence unless the reviewed project explicitly makes those checks required gates. - Report missing
ghaccess, skipped sync, stale local records, and missing issue files as review limitations or risks instead of silently filling gaps. - Label inferences explicitly.
- Keep unknowns visible in the relevant artifact.
- Do not use raw log dumps; summarize and cite.
Do not
- Do not replace feature retrospectives; consume them.
- Do not edit source or workflow artifacts outside
quality/<slug>/until the handoff worktree is created for the first proposal. - Do not merge the draft PR or delete branches.
- Do not make constitution or governance changes without ADR/human approval.
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.