agentleFS
Kuan-AI-comKuan-AI-com/agent-skills/skills/code-review/SKILL.md

code-review

Skill0 starsChanged 6 days agoMITView on GitHub

Review code changes for bugs, security holes and regressions before they merge. Use when the user says "review my changes", "review this PR", "check this diff", "is this safe to merge", or names a branch, commit or files to look over.

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

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 184 edited versions we read keep these.

  • 3

    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:

    If the diff is over ~1500 lines, say so and review the riskiest files first (auth, payments, data writes, migrations, concurrency), listing …

    line 15
  2. Distinctive:

    Read the commit messages or PR text.

    line 19
  3. Distinctive:

    Nit: only if it costs the reader nothing.

    line 43

“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

The goal is a short list of real problems, each one verified against the code. A review with two true findings beats one with ten guesses.

1. Get the exact change

  • Working tree: git status first, then git diff HEAD (staged + unstaged). Untracked files do not show in a diff: read them.
  • Branch: find the base, do not assume main. Use git symbolic-ref refs/remotes/origin/HEAD or ask. Diff with git diff <base>...HEAD (three dots = since the merge base).
  • PR number: gh pr diff <n> if gh is available; otherwise ask for the branch.
  • If the diff is over ~1500 lines, say so and review the riskiest files first (auth, payments, data writes, migrations, concurrency), listing what you skipped.

2. Understand intent

Read the commit messages or PR text. A bug is a gap between what the change is meant to do and what it does. If the intent is unclear, state your assumption.

3. Read beyond the hunk

For every changed function, open the full function and the code it calls. For every changed signature, return type, default value, config key or DB column, search for all usages (git grep -n <name>) and check each caller still works. Most real bugs live in code the diff did not touch.

4. Look for these, in this order

  1. Wrong behavior: inverted conditions, wrong variable, missing await, early return skipping cleanup, error swallowed, partial writes without a transaction.
  2. Security: untrusted input reaching SQL, shell, HTML, file paths, redirects or deserialization; missing authorization on a new route (auth is not the same as ownership); secrets or tokens in code or logs.
  3. Data and compatibility: migrations that lock or drop data, removed fields still read by clients, changed API response shape, cache keys that now collide.
  4. Missing tests for the changed behavior.

Skip what a linter, formatter or type checker already catches, unless the project has none.

5. Verify before reporting

For each candidate finding, confirm it by reading the code path that triggers it. If you can run the tests or a quick script to prove it, do. If you still are not sure, either drop it or list it under "Questions", never as a bug.

Output

Group by severity:

  • Blocker: will break production, lose data or open a security hole.
  • Should fix: real bug in a less common path, or a missing test for risky logic.
  • Nit: only if it costs the reader nothing; max 3.

Each finding:

path/to/file.ts:42 - <what is wrong, one sentence>
Scenario: with <input/state>, <what happens> instead of <expected>.
Fix: <smallest change, a code snippet if under 5 lines>

End with "Questions" (things you could not verify) and a one-line verdict: merge, merge after fixes, or rework.

Do not

  • Edit files during a review unless the user asks for fixes.
  • Pad the list. If you find nothing, say "No bugs found" and what you checked.
  • Restate what the diff does line by line.
  • Report a problem in unchanged code as part of this change; mention it separately if it is serious.

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.