agentleFS
alamenaialamenai/terrae/.claude/skills/review/SKILL.md

review

Skill245 starsChanged 9 months agoMITView on GitHub

Review code changes implemented in the current session before committing

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, daily-arxiv 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

  • 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

  • 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

    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

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

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 0

    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. Very specific:

    Use git diff <file> for modified files to see what changed.

    line 24
  2. Very specific:

    Read the rule files in .claude/rules/ and verify the code follows them:

    line 77
  3. Very specific:

    If docs pages were added or modified, verify the prev and next props in DocsLayout match the sidebar navigation order defined in …

    line 93

“Common” is measured: kept by at least 6 in 10 of the 156 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

Review Skill

Review the code changes implemented in the current session before committing.

Instructions

  1. Gather Changes

    git status
    git diff --stat

    Identify all modified and new files from the current work.

  2. Read Changed Files For each modified or new file, read the full content to understand the implementation. Use git diff <file> for modified files to see what changed.
  3. Analyze Changes Review the code for:
    • Correctness: Logic errors, edge cases, potential bugs
    • Project Conventions: Following Terrae patterns (arrow functions, type over interface, etc.)
    • Performance: Unnecessary re-renders, memory leaks, inefficient algorithms
    • Security: XSS, injection vulnerabilities, exposed secrets
    • TypeScript: Proper typing, avoiding any, type safety
    • React Patterns: Proper hooks usage, effect dependencies, cleanup functions
  4. Structure the Review Format your review with clear sections:

    ## Code Review: [Feature/Change Name]
    
    ### Overview
    Brief summary of what the changes do.
    
    ### Code Quality & Style
    - Positives
    - Issues found
    
    ### Potential Issues & Risks
    Bugs, edge cases, or concerns.
    
    ### Performance Implications
    Any performance considerations.
    
    ### Suggestions for Improvement
    Specific, actionable recommendations.
    
    ### Summary
    Overall assessment and next steps.
  5. Be Constructive
    • Acknowledge good code, not just problems
    • Provide specific line numbers when referencing issues
    • Suggest fixes, not just problems
    • Distinguish between blockers and nice-to-haves
  6. Check for Common Issues
    • Missing cleanup in useEffect
    • Missing dependencies in hooks
    • Unhandled promise rejections
    • Missing error boundaries
    • Hardcoded values that should be constants
    • Missing TypeScript types
    • Console.log statements left in code
  7. Verify Against Project Rules Read the rule files in .claude/rules/ and verify the code follows them:

    • .claude/rules/typescript.md: Types, naming, ordering
    • .claude/rules/javascript.md: Formatting, arrow functions, explicit returns, early returns
    • .claude/rules/react/component.md: File structure, component structure, map component template
    • .claude/rules/react/hooks.md: useEffect extraction, dependencies, memoization rules
    • .claude/rules/react/props.md: Type extraction, ordering, defaults, documentation
    • .claude/rules/react/patterns.md: Component size, composition, common patterns
    • .claude/rules/react/rendering.md: Conditional rendering, inline functions, keys, fragments
    • .claude/rules/react/performance.md: Resource cleanup, refs vs state, layer management, canvas, DOM
    • .claude/rules/clean-code.md: Naming, functions, comments, formatting, error handling
    • .claude/rules/nextjs.md: App Router folder structure, file naming
    • .claude/rules/security.md: XSS, CSP, CORS, CSRF, secrets, rate limiting

    Flag any violations with the specific rule and file location.

  8. Verify Page Navigation If docs pages were added or modified, verify the prev and next props in DocsLayout match the sidebar navigation order defined in src/app/docs/_components/docs-sidebar.tsx. Check:
    • prev/next titles match the sidebar item titles exactly
    • prev/next hrefs point to the correct neighboring pages
    • New pages are linked from their neighbors (both prev and next sides)
    • The first page has no prev, the last page has no next

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.