agentleFS
euxxeuxx/claude-skills-for-copilot/skills/code-review/SKILL.md

code-review

Skill4 starsChanged 7 months agoMITView on GitHub

Multi-agent code review for local changes, files, or directories. Detects bugs, security issues, and conventions-file violations (AGENTS.md/CLAUDE.md/GEMINI.md).

194 other projects use a version of this.

Adopted by

Most recently taken up by

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.
  • dzhngSkill

    close-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

  • dzhngSkill

    design-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

  • PydanticSkill

    add-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-bullshitSkill

    compare-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 AzureSkill

    azsdk-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 AzureSkill

    azsdk-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

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 184 edited versions we read keep these.

  • 9

    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
  1. Distinctive:

    Use a sub-agent to list file paths of relevant conventions files in this priority order: AGENTS.md, then CLAUDE.md, then GEMINI.md.

    line 18
  2. Distinctive:

    Use a sub-agent to scan the code changes and return a summary of the change.

    line 19
  3. Distinctive:

    Agent 4 - Logic and security: Look for incorrect logic and concrete security problems introduced by the changed code.

    line 28
  4. Distinctive:

    Check the actual code and surrounding context to confirm the failure and its trigger.

    line 36
  5. Distinctive:

    Check whether the behavior is pre-existing or an intentional part of the requested change.

    line 37
  6. Distinctive:

    If no issues remain, output that no issues were found.

    line 44
  7. Distinctive:

    Keep output in chat. Posting GitHub comments requires an explicit user request and tools available in the target environment.

    line 46
  8. Distinctive:

    Treat the following as false positives in steps 2 and 3:

    line 50
  9. Distinctive:

    Do not attempt to build or typecheck the app — these run separately in CI.

    line 63

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Code Review

Provide a code review for the given code changes (e.g. local changes, a file, or a directory).

Steps

Make a todo list first, then follow these steps precisely:

1. Gather context

  • Use a sub-agent to list file paths of relevant conventions files in this priority order: AGENTS.md, then CLAUDE.md, then GEMINI.md. Include the repository root and all ancestor directories of changed files, including the changed files' own directories.
  • Use a sub-agent to scan the code changes and return a summary of the change.
  • Give every review and validation agent the user's requested scope and the change summary. Include the PR title and description when provided as context.

2. Parallel review

Launch 4 parallel sub-agents to independently review the change. Each agent returns a list of issues with the reason flagged (e.g. conventions-file adherence, bug):

  • Agents 1 and 2 - Conventions-file compliance: Independently audit changes against AGENTS.md or similar conventions files (CLAUDE.md, GEMINI.md), using priority order AGENTS.md -> CLAUDE.md -> GEMINI.md. Apply each file only to its directory and descendants, respecting more specific instructions. Quote the exact applicable rule for each violation; not all writing instructions apply during code review.
  • Agent 3 - Diff-focused bug scan: Scan the changed lines for significant, demonstrable bugs. Avoid nitpicks, speculative concerns, and findings that cannot be validated from the diff alone.
  • Agent 4 - Logic and security: Look for incorrect logic and concrete security problems introduced by the changed code. Read surrounding context when needed to verify the behavior.

Prioritize actionable findings with clear evidence and actual impact. For input- or state-dependent bugs, identify the concrete trigger and resulting failure. Do not report subjective improvements or general quality concerns.

3. Independent validation

For each candidate issue, launch an independent validation sub-agent. Give it the scope, change summary, issue description, and relevant conventions-file paths.

  • Check the actual code and surrounding context to confirm the failure and its trigger.
  • Check whether the behavior is pre-existing or an intentional part of the requested change.
  • For conventions-file findings, verify both the exact rule and its directory scope.
  • Return whether the issue is confirmed, with supporting evidence. Discard issues that cannot be validated with high confidence.

4. Filter and output

  • Discard unvalidated issues and deduplicate reports of the same underlying problem.
  • If no issues remain, output that no issues were found.
  • Output the review directly to the user following the output format below.
  • Keep output in chat. Posting GitHub comments requires an explicit user request and tools available in the target environment.

False Positives

Treat the following as false positives in steps 2 and 3:

  • Pre-existing issues
  • Something that looks like a bug but is not actually a bug
  • Pedantic nitpicks that a senior engineer wouldn't call out
  • Issues a linter, typechecker, or compiler would catch (missing imports, type errors, formatting). Assume these run separately in CI.
  • General code quality issues (lack of test coverage, poor documentation), unless explicitly required in a conventions file
  • Issues called out in a conventions file but explicitly silenced in code (e.g. a lint-ignore comment)
  • Intentional functionality changes directly related to the broader change
  • Real issues on lines the user did not modify

Notes

  • Do not attempt to build or typecheck the app — these run separately in CI.
  • Cite and link each issue. If referring to a conventions file, you must link it.

Output Format

With issues found

### Code review

Found N issues:

1. <brief description> (conventions file says "<...>")

   <link to file and line range>

2. <brief description> (some/other conventions file says "<...>")

   <link to file and line range>

3. <brief description> (bug due to <file and snippet>)

   <link to file and line range>

No issues found

### Code review

No issues found. Checked for bugs and conventions-file compliance.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.