code-review
Skill0 starsChanged 18 days agoMITView on GitHub
Review local diffs, committed ranges, and GitLab merge requests; verify feedback before applying fixes and prepare inline comments for explicit publication. Use when asked to review code, review an MR, check a branch before merge, address review threads, or draft review feedback. Not for an adversarial two-reviewer verdict (second-opinion) or remote GitHub PR posting.
194 other projects use a version of this.
Adopted by
Most recently taken up by
- doggy8088/spec-kittheir own version, first seen Nov 9, 2026
- strelov1/freehiretheir own version, first seen Nov 9, 2026
- storybookjs/storybooktheir own version, first seen Nov 8, 2026
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 2026
- supabase/supabasetheir own version, first seen Nov 8, 2026
- The-Vibe-Company/quivrtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use close-spec, design-with-images 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.
dzhngSkillclose-spec
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
Also in 5 projects that use this
dzhngSkilldesign-with-images
Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.
Also in 5 projects that use this
PydanticSkilladd-new-model
Add support for a newly-released language or image generation model in pydantic-ai (e.g. openai:gpt-5.6, anthropic:claude-sonnet-5, openai:gpt-image-2). Use when a provider ships a new model id and you need to wire literals, profile flags, adapters, and tests to recognize it. Handles SDK-lag, gateway list conventions, capability probing, and direct image-model geometry.
Also in 9 projects that use this
transitive-bullshitSkillcompare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
Also in 5 projects that use this
Microsoft AzureSkillazsdk-common-apiview-feedback-resolution
Analyze and resolve APIView review feedback on Azure SDK PRs. **UTILITY SKILL**. USE FOR: APIView comments, API review feedback, SDK API surface changes. DO NOT USE FOR: general code review, non-APIView feedback. INVOKES: azure-sdk-mcp:azsdk_apiview_get_comments, azure-sdk-mcp:azsdk_customized_code_update, azure-sdk-mcp:azsdk_typespec_delegate_apiview_feedback, azure-sdk-mcp:azsdk_run_typespec_validation, azure-sdk-mcp:azsdk_package_generate_code.
Also in 6 projects that use this
Microsoft AzureSkillazsdk-common-generate-sdk-locally
Generate and finalize Azure SDKs locally from TypeSpec, including build, checks, tests, changelog, metadata, and version updates by default. WHEN: "generate SDK locally", "build SDK", "run SDK tests", "run CI checks", "validate package", "run checks", "update changelog", "fix SDK build errors", "resolve SDK generation errors", "customize TypeSpec", "rename SDK client", "rename SDK model", "hide operation from SDK", "fix analyzer errors", "resolve customization drift", "create subclient", "update metadata", "update version". INVOKES: azsdk_verify_setup, azsdk_package_generate_code, azsdk_package_build_code, azsdk_package_run_check, azsdk_package_run_tests, azsdk_customized_code_update, azsdk_package_update_changelog_content, azsdk_package_update_metadata, azsdk_package_update_version.
Also in 6 projects that use this
- +4 more from dzhng
- +2 more from Azure
Other versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 194
- mattpocock/skills★ 309ksame name
- TheAlgorithms/Python★ 226ksame name
- microsoft/vscode★ 195ksame name
- github/spec-kit★ 149ksame name
- ggml-org/llama.cpp★ 134ksame name
- supabase/supabase★ 115ksame name
- storybookjs/storybook★ 91ksame name
- shareAI-lab/analysis_claude_code★ 80ksame name
- shareAI-lab/learn-claude-code★ 80ksame name
- vectorize-io/hindsight★ 60ksame name
184 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 repository57 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/comments.mdcCursor rule
- .cursor/rules/commit-messages.mdcCursor rule
- .cursor/rules/git-workflow.mdcCursor rule
- .cursor/rules/manage-stack.mdcCursor rule
- .cursor/rules/no-worktrees.mdcCursor rule
- manage-stackSkill
- convert-as-skillSkill
- create-agentSkill
- create-agents-mdSkill
- create-commandSkill
- create-hookSkill
- create-ruleSkill
- create-skillSkill
- retrospectiveSkill
- super-architectureSkill
- super-cachingSkill
- super-elixirSkill
- super-nodejsSkill
- super-protobufSkill
- super-tech-blueprintSkill
- atomic-semantic-commitSkill
- create-bruno-collectionSkill
- create-documentationSkill
- create-ticketsSkill
- ready-specSkill
- write-adrSkill
- write-changelogSkill
- write-mr-descriptionSkill
- write-planSkill
- write-postmortemSkill
- write-runbookSkill
- noslopSkill
- output-saversSkill
- safe-refactorSkill
- tddSkill
- verifySkill
- get-movingSkill
- later-listSkill
- standupSkill
- challenge-meSkill
- codebase-learnerSkill
- researchSkill
- second-opinionSkill
- traceSkill
- color-kitSkill
- design-system-kitSkill
- diagramSkill
- infographicSkill
- product-polish-workflowSkill
- prototype-wireframeSkill
- ui-ux-kitSkill
- evidenceSkill
- find-skillsSkill
- handoffSkill
- rumblingSkill
- use-levistackSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 184 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 61
When: before opening a PR.
- Distinctive: line 73
When: after each subagent task, major features, before merge — see references/requesting-review.md.
- Distinctive: line 79
Verify before implementing.
- Distinctive: line 83
If anything is unclear, stop and clarify all items before partial fixes.
- Very specific: line 97
Before using a bundled helper, set REVIEW_SKILL_DIR to the absolute directory containing this SKILL.md.
- Distinctive: line 102
Read relevant source, tests, and contracts at the MR head SHA.
- Distinctive: line 113
Only after the user explicitly requests publication of the identified drafts:
- Very specific: line 121
Never set reviewer_state=approved from automation.
“Common” is measured: kept by at least 6 in 10 of the 184 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
Code review
Pick the mode from the user's goal. A review request starts read-only. Local fixes, draft notes, public comments, approvals, commits, pushes, and thread resolution are separate actions. Do only the actions the user authorized.
| Goal | Mode | Detail |
| Review uncommitted / staged changes before a PR | Diff | references/review-diff.md |
| Review your commits before merge / next task | Request | references/requesting-review.md, template references/code-reviewer.md |
| Implement feedback from a human or external reviewer | Receive | references/receiving-review.md |
| Review a GitLab MR or its open threads | GitLab MR | Below + references/draft-review-flow.md |
For comment text, use noslop and polyglot-copywriter while preserving code and exact line anchors.
Arguments ($ARGUMENTS): MR URL, MR number for current repo, or empty (current branch MR) — GitLab MR mode only.
Diff review (pre-PR)
Self-review the working tree: full diff read, edge cases, tests for behavior changes, scope creep, findings as Must fix / Should fix / Nit. Full procedure: references/review-diff.md.
When: before opening a PR; after a large local edit without dispatching a reviewer. For committed range review, use Request mode.
Requesting review
Review early; give the reviewer git range + requirements, not your session history.
- Resolve SHAs:
BASE_SHA(e.g.origin/mainor task start),HEAD_SHA(git rev-parse HEAD). - Dispatch a read-only reviewer using references/code-reviewer.md (
{DESCRIPTION},{PLAN_OR_REQUIREMENTS}, SHAs). - Triage: fix Critical immediately, Important before proceeding, Minor later; push back with reasoning when wrong.
When: after each subagent task, major features, before merge — see references/requesting-review.md.
Receiving review
Verify before implementing. No performative agreement; technical acknowledgment or reasoned pushback.
Pattern: read fully → understand (restate or ask) → verify against codebase → evaluate → respond → implement one item at a time with tests.
If anything is unclear, stop and clarify all items before partial fixes. Full rules, YAGNI checks, GitHub thread replies: references/receiving-review.md.
GitLab MR review
Three phases: preview (read-only), draft to MR (unpublished GitLab draft notes, explicitly requested), then publish (explicitly requested). A request to fix findings locally goes through the feedback workflow after preview; it does not imply posting or pushing.
Default write path: GitLab draft notes (draft_notes API / bundled scripts). Author sees nothing until publish.
Comment shape: inline findings with code suggestions on diff lines — not a wall-of-text MR summary.
Operator reference: references/gitlab-mechanics.md, references/draft-review-flow.md, references/review-dimensions.md, references/comment-body-format.md. For a risky change or requested deeper pass, use references/deep-review.md. Use references/detailed-report.md only when a longer report is requested.
Before using a bundled helper, set REVIEW_SKILL_DIR to the absolute directory containing this SKILL.md. Call "$REVIEW_SKILL_DIR/scripts/<helper>.sh"; a bare scripts/ path in the target repository may execute the wrong file.
Phase 1: Deep read-only preview
- Resolve the MR by URL, project and IID, or current branch. If several MRs match, show the choices instead of guessing. Fetch its metadata, entire diff, open discussions, pipeline status, and failing job traces.
- Read relevant source, tests, and contracts at the MR head SHA. Avoid switching branches over unrelated work. Verify each finding against the target file and diff line. Run focused tests when a safe checkout or equivalent is available; separate CI evidence from local runs.
- Apply references/review-dimensions.md. For changed behavior, map the branch to a test example and an observable assertion, or mark the gap. Use the optional deep pass for risk that needs another review lens.
- Write findings by severity with file and line, impact, evidence, and a proposed fix. Add a GitLab suggestion fence only when the replacement exactly fits the diff range. List existing open threads so the preview does not duplicate them. State CI evidence and what was not verified.
- Present the preview. If the user asked only for review, stop. If the user already requested a local fix or selected draft notes, continue with that authorized action. Even a clean preview does not authorize approval or publication.
Phase 2: Draft to MR (explicit request)
Draft only the selected, reviewable findings. Use GitLab mechanics to refresh diff SHAs and write comment bodies to files. Prefer inline drafts; a finding outside the diff becomes a general draft note. Verify pending draft notes after posting. Tell the user these notes remain unpublished. Do not treat a generic "ok" as approval to post, publish, or approve.
Phase 3: Publish drafts (explicit request)
Only after the user explicitly requests publication of the identified drafts:
export REVIEWER_STATE=requested_changes # or reviewed for comment-only
export SUMMARY_FILE=
"$REVIEW_SKILL_DIR/scripts/publish-draft-notes.sh" <repo> "$PROJECT_ID" <number>Never set reviewer_state=approved from automation. Publish only the intended drafts. Immediate public inline comments require an explicit request identifying the selected findings and public posting. A clean review remains a read-only result unless the user separately authorizes a forge action.
GitLab quick routing
| User says | Phase |
| "review MR", "review !123" | 1 |
| "draft 1,3", "post as draft" | 2, after the preview |
| "publish drafts", "submit review" | 3 |
| "fix finding 2 locally" | Local feedback workflow after preview |
| "review and draft all" | 1 then 2 |
For "fix all open threads", inspect each thread and current code, then apply only supported fixes. Verify before marking a thread addressed. A commit link must resolve on the remote before posting it; a local commit is insufficient. Keep advisory or blocked threads open. See GitLab mechanics. A GitHub PR URL does not use the GitLab adapter.
Related skills
noslop: run the noslop pass on the diff.second-opinion: the user wants an adversarial, two-reviewer verdict rather than the review loop.verify: check a review comment before you act on it.safe-refactor: apply a requested change without changing behavior.write-mr-description: the diff is clean and you need the MR text.polyglot-copywriter: polish review comments.
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.

