agentleFS
DonemebDonemeb/Donemeb-Skills/skills/software-engineering/code-review/SKILL.md

code-review

Skill0 starsChanged 3 months agoMITView on GitHub

Layered code review of staged git changes against the project's own review checklist (any naming). Items: global prohibitions + per-layer checks. If no checklist exists, guide the user to create one first. Use when the user says 'review the code before commit', 'check this change for issues', 'run the review checklist'. Don't use for style/formatting feedback (use linters).

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

4 rules. 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the project does not yet have this checklist, tell the user: this skill depends on it.

    line 30
  2. Very specific:

    Search project root, docs/, .github/ and other common locations for a review checklist document.

    line 35
  3. Distinctive:

    Run git diff and git diff --staged to see all uncommitted code changes (additions, deletions, modifications).

    line 38
  4. Distinctive:

    All changes: first run through global prohibitions (veto items).

    line 42

“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

Layered code review of staged git changes, run against the project's own review checklist. This skill provides the flow and the summary template; it does not assume any specific checklist content.

When to use

  • About to commit and want a structured review against the project's existing checklist.
  • User asks "run the review checklist over this change".
  • Need a layered audit (global prohibitions + per-layer checks) of staged work.

When NOT to use

  • Style or formatting feedback — use linters / formatters instead.
  • The project has no review checklist yet — see Prerequisites below; this skill will guide the user to create one rather than fabricate content.

Prerequisites

The project root or docs/ contains a review checklist document (any name — common examples: code-review.md, CODE_REVIEW.md, review-checklist.md, .github/CHECKLIST.md). The document should include:

  • Global prohibitions — one-strike-veto items that every change must pass.
  • Per-layer checks — grouped by code layer / module / concern, one section per layer.

If the project does not yet have this checklist, tell the user: this skill depends on it; suggest sedimenting one (after reviewing this change once, lock in the recurring issues as a checklist). This skill does not generate checklist content for the project.

Steps

  1. Locate the checklist Search project root, docs/, .github/ and other common locations for a review checklist document. If multiple exist, ask the user to pick one. If none exists, stop and prompt the user to create one (see Prerequisites).
  2. Get the change scope Run git diff and git diff --staged to see all uncommitted code changes (additions, deletions, modifications). Also run git status to see new untracked files. If there are no changes, tell the user "no code changes to review" and stop.
  3. Walk through each item Based on the layers/sections the change touches, walk through the corresponding parts of the checklist:

    • All changes: first run through global prohibitions (veto items).
    • Changes touching a specific layer/module: locate the corresponding section in the checklist and check each item.

    For each checklist item, judge whether the changed code passes. Skip layers the change does not touch.

  4. Output the review result

    Use this format:

    ## Code Review Result
    
    **Changed files:** <list all changed files>
    **Checklist source:** <document path>
    
    ### Global prohibitions
    - [✅/❌] 1. <check item description>
    ...
    
    ### <layer / module name>
    - [✅/❌] 1. <check item description>: <note>
    ...
    
    ### Issues
    <if any item failed, list specific file, line number, problem description, fix suggestion>
    <if all pass, show "No issues found">

Relationship to other skills

  • change-recap — sediments new review items into the checklist (expands checklist content). This skill consumes the checklist to do the review.
  • workspace-consistency — the "changes traceable" dimension can invoke this skill to retroactively review a change that lacks review.

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.

Reviews can't be read right now.

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.