code-review
Skill1 starsChanged 6 months agoMITView on GitHub
Use after writing or modifying code to get severity-tagged findings (CRITICAL/HIGH/MEDIUM/LOW) with inline fixes before committing.
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 repository10 other files it gives its agents.
- api-designSkill
- brainstormSkill
- commitSkill
- evaluate-feedbackSkill
- go-apiSkill
- multi-agentSkill
- planSkill
- tddSkill
- ts-apiSkill
- workflowSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 6 are distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 46
No unchecked type assertions (as SomeType) without a prior type guard
- Very specific: line 52
No unchecked type assertions — v, ok := x.(T) not x.(T) directly
- Very specific: line 57
No silent swallowing (catch (e) {} / if err != nil { return } without logging/wrapping)
- Distinctive: line 66
No hardcoded secrets, API keys, passwords, or tokens
- Distinctive: line 68
No internal error messages (stack traces, DB errors) sent to clients
- Very specific: line 83
No direct mutation of objects — flag obj.field = value outside constructors
- Distinctive: line 88
No N+1 queries — service should batch fetch, not loop-and-query
- Distinctive: line 92
If a file list is specified, review those files only
- Distinctive: line 93
If no scope given, review all files changed since last commit: git diff HEAD --name-only
- Distinctive: line 100
Never rewrite code that isn't broken.
“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
Review code for quality, type safety, DRY, security, and adherence to project standards. Produces actionable, severity-tagged findings.
Recommended model: Opus (deep multi-file analysis)
Output Format
One finding per line:
path/to/file.ts:42 — CRITICAL: problem description. Fix: what to do.
path/to/file.ts:88 — HIGH: problem description. Fix: what to do.
path/to/file.go:15 — MEDIUM: problem description. Fix: what to do.Group findings by severity: CRITICAL → HIGH → MEDIUM → LOW.
At the end, output a summary:
Review complete. N findings: X critical, Y high, Z medium, W low.
Action required before proceeding: [list critical/high items]Severity Definitions
| Severity | When |
| CRITICAL | Security vulnerability, data loss risk, broken auth, hardcoded secret |
| HIGH | Type safety violation (any), unhandled error path, exposed internal data, missing validation at boundary |
| MEDIUM | DRY violation, mutation of shared state, business logic in wrong layer, missing context propagation |
| LOW | Naming inconsistency, minor style deviation, redundant code |
What to Check
Type Safety (TypeScript)
- No
any— flag every occurrence; suggestunknown+ type guard - No unchecked type assertions (
as SomeType) without a prior type guard - Zod schema present for every HTTP boundary (body, params, query)
- Response type matches the declared DTO — no extra fields leaking
Type Safety (Go)
- Error return values never ignored (no
_on error unless explicitly justified) - No unchecked type assertions —
v, ok := x.(T)notx.(T)directly context.Contextpresent as first arg on all service/repo methods
Error Handling
- Errors caught at the correct layer (handler layer, not buried in service)
- No silent swallowing (
catch (e) {}/if err != nil { return }without logging/wrapping) - Errors mapped to the standard envelope before the client sees them
DRY
- Duplicate logic across files that could be a shared utility
- Inline response envelope construction that should use the shared helper
- Copy-pasted validation that should be a shared schema
Security
- No hardcoded secrets, API keys, passwords, or tokens
- Input validated before use — never pass raw user input to DB/service
- No internal error messages (stack traces, DB errors) sent to clients
- Auth middleware applied to protected routes
Layer Separation (TypeScript)
- Router handlers contain no business logic
- Services contain no SQL / DB calls
- Repositories contain no business rules
Layer Separation (Go)
- Handlers contain no business logic
- Services contain no SQL
- Repositories contain no business rules
http.Requestnot passed beyond handler layer
Immutability (TypeScript)
- No direct mutation of objects — flag
obj.field = valueoutside constructors - No
Object.assign(existing, ...)— should beObject.assign({}, existing, ...)
Performance
- No
awaitinside loops (TypeScript) — should bePromise.all - No N+1 queries — service should batch fetch, not loop-and-query
Review Scope
- If a file list is specified, review those files only
- If no scope given, review all files changed since last commit:
git diff HEAD --name-only - Detect language from file extensions (
.ts/.tsx→ TypeScript rules;.go→ Go rules)
After Findings
For each CRITICAL and HIGH finding, offer a concrete fix inline. For MEDIUM and LOW, describe the fix without rewriting the code.
Never rewrite code that isn't broken. Never suggest changes outside the review scope.
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.

