agentleFS
Sign inStart free
wilstowilsto/claude-code-starter-kit/.claude/skills/review/SKILL.md

review

Skill0 starsChanged 8 months agoMITView on GitHub

Route code reviews to the appropriate pr-review-toolkit agent. Triggers: before /commit with 3+ files changed, after completing a feature, after refactoring, when the user asks for review, "review my code", "check my changes", "is this correct".

192 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

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • +3 more from dzhng
  • +5 more from Lambenthan

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before /commit: when 3+ files have been changed

    line 14
  2. Distinctive:

    Before routing to agents, check spec alignment:

    line 32
  3. Very specific:

    If docs/specs/<domain>.md exists → pass its User Stories and Behavior sections as context to code-reviewer

    line 36
  4. Very specific:

    If no spec exists and change is a new feature → flag that /spec-update should run

    line 37
  5. Very specific:

    Use the Agent tool with subagent_type: "pr-review-toolkit:code-reviewer" to review current changes.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 157 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 — Plugin Routing

When to use (auto-trigger)

  • Before /commit when 3+ files have been changed
  • After completing a feature — verify before declaring "Done"
  • After a refactor — ensure behavior is preserved
  • Never on trivial changes (typo fix, single-line config change)

Available agents (pr-review-toolkit plugin)

AgentUse when
pr-review-toolkit:code-reviewerGeneral review (correctness, conventions, quality)
pr-review-toolkit:code-simplifierPost-feature cleanup, complexity reduction
pr-review-toolkit:silent-failure-hunterError handling, logging, silent failures
pr-review-toolkit:pr-test-analyzerTest coverage gaps, missing tests
pr-review-toolkit:type-design-analyzerType invariants, encapsulation quality
pr-review-toolkit:comment-analyzerComment accuracy, technical debt in docs

Spec consistency pre-check

Before routing to agents, check spec alignment:

  1. git diff --name-only → list changed source files
  2. For each, infer domain from parent directory (src/<domain>/, app/<domain>/)
  3. If docs/specs/<domain>.md exists → pass its User Stories and Behavior sections as context to code-reviewer
  4. If no spec exists and change is a new feature → flag that /spec-update should run

Advisory only — never blocks the review.

Process

Quick review (default)

Use the Agent tool with subagent_type: "pr-review-toolkit:code-reviewer" to review current changes.

Deep review (3+ files or pre-release)

Launch multiple agents in parallel for comprehensive coverage:

  1. pr-review-toolkit:code-reviewer — correctness and conventions
  2. pr-review-toolkit:silent-failure-hunter — error handling gaps
  3. pr-review-toolkit:pr-test-analyzer — test coverage
  4. Spec context (when docs/specs/<domain>.md exists): pass relevant spec sections to code-reviewer to detect behavioral regressions

Synthesize results into a single verdict: Ready to Merge, Needs Attention, or Needs Work.

After the review

  • Critical issues: Fix them before committing (Level 1 autonomy for obvious fixes)
  • Suggestions: Present to the user for decision (Level 3)
  • Clean review: Proceed to /commit

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.

Check your setup, free