agentleFS
freemafreema/ai-skills/skills/code-review/SKILL.md

code-review

Skill5 starsChanged 19 days agoMITView on GitHub

Sandwich-structured code review for PRs, MRs, diffs, or pasted code. Triggers on: "review this", "check my PR/MR", "what do you think of this code", "is this OK to merge", or any paste of code/diff where the user wants feedback. Produces motivating reviews that clearly separate blockers from nitpicks. Always use this skill — even for quick reviews. The structure matters.

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:

    Specific, not vague: Always show code. Never say "the naming could be better" without showing the fix.

    line 55
  2. Distinctive:

    Honest about preferences: If it's a style preference, say so.

    line 57
  3. Distinctive:

    Tiny snippet / quick question?: Keep the structure but compress it — 3 short paragraphs is fine.

    line 87

“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 Skill

Goal: leave the author feeling capable and motivated, not defensive. The review should make them think "yes, I'm on the right track, let me fix that one thing."


The Sandwich Method (always follow this order)

Top Slice — Overall

  • Open with genuine recognition of what's good
  • Name the design pattern or approach and why it's solid
  • One short paragraph, no hedging, no "but..."
  • Example: "Separating analytics into its own component via CustomEvents is a clean SRP refactor — event-driven decoupling between components is well-designed here."

Filling — Bugs & Notes

Bug / Blocker (must fix before merge)

  • State the bug clearly and directly
  • Show the broken code, explain WHY it's wrong
  • Provide the fix — exact code, not vague direction
  • One blocker per section. If there are multiple, list them all here.

Minor Notes (optional, low pressure)

  • Numbered list
  • Each note: what it is + why it matters (or why it's just a preference)
  • Explicitly label style preferences vs. real issues: "Style preference, not a bug — current approach works."
  • Include positive observations too (e.g., "No double-fire risk — verified both paths are cleanly separated.")

Bottom Slice — Verdict

  • Clear, confident closing statement
  • Name the blocker(s) and say everything else is solid
  • Example: "Bug with id is the only blocker. The rest is clean and well thought-out."
  • Optional: one motivating sentence — not sycophantic, just human

Tone Guidelines

  • Direct, not harsh. Say "this is wrong" not "you might want to consider..."
  • Specific, not vague. Always show code. Never say "the naming could be better" without showing the fix.
  • Proportional. A 5-line nit doesn't get 3 paragraphs.
  • Honest about preferences. If it's a style preference, say so. Don't dress up opinions as bugs.
  • Push, don't crush. The goal is the author merging better code AND feeling good about it.

Example Output Structure

## Overall
[positive opening paragraph about the approach]

## Bug
[blocker description]
[broken code snippet]
[fix snippet]

## Minor Notes
1. [note with label: bug / style preference / positive observation]
2. ...

## Verdict
[confident closing + blocker summary]

Edge Cases

  • No bugs found? Still follow the sandwich. The filling becomes only minor notes.
  • Multiple blockers? List all under "Bug / Blocker". Don't bury them in minor notes.
  • Tiny snippet / quick question? Keep the structure but compress it — 3 short paragraphs is fine.
  • Architecture review (no diff)? Same structure applies — "blockers" become design risks.

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.