agentleFS
ryanschueryanschue/automated-product-engineer/skills/code-review/SKILL.md

code-review

Skill0 starsChanged 25 days agoMITView on GitHub

Review the current working diff or branch for correctness defects and worthwhile reuse, simplification, and efficiency improvements. Use before opening or updating a pull request. Use pr-review for a remote pull request and security-review for a dedicated security pass.

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, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 184 edited versions we read keep these.

  • 4

    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 references/verified-review.md for the candidate-finding matrix, verification procedure, severity model, and examples of useful …

    line 10
  2. Distinctive:

    Read the repository instructions and the architecture, feature, or test documents that govern changed files.

    line 20
  3. Distinctive:

    Check whether another layer already prevents the failure.

    line 41
  4. Distinctive:

    Only edit, comment, commit, or push when the request authorizes that action.

    line 50

“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

Review the change, not the entire repository. Prefer a few verified findings with concrete failure paths over speculative advice or style nits.

Read references/verified-review.md for the candidate-finding matrix, verification procedure, severity model, and examples of useful findings.

Intake and pushback

Resolve the exact base, head, diff, intended behavior, and repository rules from local evidence before asking the user. Ask only when the target diff or intended contract remains ambiguous enough to change the review conclusion. If an external owner must clarify behavior, provide a concise request containing the observed code path, the concrete ambiguity, and the decision needed to verify correctness.

Establish scope

  • Identify the exact base, head, staged changes, and uncommitted changes that are in scope.
  • Read the repository instructions and the architecture, feature, or test documents that govern changed files.
  • Inspect enough surrounding code and call sites to understand the contract; a diff alone is often insufficient.
  • Preserve unrelated user changes and distinguish new defects from pre-existing behavior.

Review angles

  • Correctness: wrong conditions, edge cases, null handling, async races, partial failures, stale state, and error propagation.
  • Contracts: type, API, schema, serialization, authorization, cache, and migration assumptions across boundaries.
  • Architecture: misplaced responsibility, leaky abstractions, duplicate sources of truth, and changes that bypass established seams.
  • Maintainability: existing helpers that should be reused, dead paths, unnecessary branching, and avoidable complexity.
  • Efficiency: repeated queries, unbounded work, needless allocations or renders, and work performed at the wrong layer.
  • Tests: missing coverage for behavior introduced by the diff, especially failure and concurrency paths.

Route a change with meaningful security exposure through security-review as a separate pass.

Verify proposed findings

For each proposed finding:

  1. Trace a specific input or state to the incorrect outcome.
  2. Confirm the problem is introduced or exposed by this change.
  3. Check whether another layer already prevents the failure.
  4. Cite the narrowest changed line that owns the defect.

Drop anything that cannot survive this verification. Do not report compiler, formatter, or linter output as a review finding unless it reveals a deeper behavioral problem.

Output

Lead with findings ordered by severity. For each, include file:line, the violated contract, a concrete failure scenario, and the smallest safe correction. Then note residual test risk or say plainly that no actionable findings survived review.

Only edit, comment, commit, or push when the request authorizes that action. When asked to fix findings, rerun the focused checks affected by each fix.

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.