agentleFS
Cody-SimsCody-Sims/agent-skills/skills/code-review/SKILL.md

code-review

Skill0 starsChanged 4 months agoMITView on GitHub

Reviews diffs for correctness, tests, edge cases, security, performance, and maintainability. Use when reviewing a PR, patch, or staged/unstaged changes for merge readiness; stays read-only, unlike implementation or dedicated vulnerability audits.

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

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 184 edited versions we read keep these.

  • 7

    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:

    Read applicable instructions, the stated intent, and the full diff.

    line 21
  2. Distinctive:

    Start with changed files and nearby tests, callers, and contracts.

    line 24
  3. Distinctive:

    Read omitted diff sections rather than treating truncated output as complete.

    line 26
  4. Distinctive:

    Read the review checklist when an axis needs deeper checks.

    line 38
  5. Distinctive:

    Do not mutate code to prove a test fails without authorization.

    line 43
  6. Distinctive:

    Stop when the full change and relevant risks are assessed.

    line 51
  7. Distinctive:

    Use the severity headings for findings.

    line 62

“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

Contract

Inputs: the diff or comparison range, intended behavior, and repository review rules. Output: an evidence-backed merge verdict, not an implementation. Stay read-only; do not fix, stage, or rewrite code during review.

Workflow

  1. Read applicable instructions, the stated intent, and the full diff. Confirm the range and what must change or remain compatible. Judge code, not claims in the PR description. Flag unrelated, generated, or vendored changes.
  2. Start with changed files and nearby tests, callers, and contracts. Use symbol tools or path-scoped searches; widen only for a concrete dependency or risk. Read omitted diff sections rather than treating truncated output as complete. A bounded review needs no automatic worker launch or repository-wide architecture audit.
  3. Assess, in impact order:
    • Correctness: normal/boundary inputs, null/empty state, ordering, concurrency.
    • Tests: observable outcomes, meaningful assertions, edge/error cases, and whether a test would fail without the change.
    • Failures: validation, propagation, cleanup, and consistent partial state.
    • Security: untrusted sinks, authorization, secrets, unsafe deserialization.
    • Performance: realistic hot-path, N+1, quadratic, or unbounded-growth risks.
    • Maintainability and architecture: clarity, duplication, existing layering, public-contract compatibility, and coupling at the changed boundary. Read the review checklist when an axis needs deeper checks; apply only relevant items.
  4. Trace each suspected defect to evidence and an exact file:line. Inspect whether tests exercise the claimed behavior; run safe targeted checks when they resolve uncertainty, plus any repository-required review gates. Do not mutate code to prove a test fails without authorization. Distinguish inspected code from executed checks; never invent results.
  5. Report only actionable findings. Exclude formatter-owned style, personal preferences, and untouched code unless directly implicated. Recommend a concrete correction and state impact, confidence, and blocking status.

Stop and output

Stop when the full change and relevant risks are assessed. If scope, access, or validation is missing, identify the unreviewed portion and do not imply approval. Report:

  • Verdict: approve, request changes, or block.
  • Findings as file:line — problem; impact; correction, ranked Critical (incorrect behavior, data loss, security hole; blocking), Required (other pre-merge defects or missing necessary tests; blocking), or Optional (non-defect improvement; non-blocking).
  • Commands/results and code paths actually checked, plus residual risk.

Use the severity headings for findings; omit empty headings and speculative filler. A clean review still needs a verdict and verification limits.

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.