agentleFS
GrishaAngelovGHGrishaAngelovGH/gemini-cli-agent-skills/code-reviewer/SKILL.md

code-reviewer

Skill16 starsChanged 10 months agoMITView on GitHub

Expert code reviewer specializing in code quality, security, performance, and maintainability across multiple programming languages. Use this skill when the user wants a PR review, code analysis, or suggestions for improvement. This skill includes proprietary checklists and a mandatory review template located in its references and assets directories that MUST be used for every analysis.

182 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use git-doc-updater, git-precommit 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.
  • u9401066Skill

    git-doc-updater

    Auto-check and update key documentation before Git commits to keep docs in sync with code. Triggers: docs, 文檔, 更新文檔, sync docs, release, 發布.

    Also in 5 projects that use this

  • u9401066Skill

    git-precommit

    Orchestrate pre-commit workflow including Memory Bank sync, README/CHANGELOG/ROADMAP updates. Triggers: GIT, gc, push, commit, 提交, 準備 commit, 要提交了, git commit, pre-commit, 推送.

    Also in 5 projects that use this

  • JeffallanSkill

    shopify-expert

    Builds and debugs Shopify themes (.liquid files, theme.json, sections), develops custom Shopify apps (shopify.app.toml, OAuth, webhooks), and implements Storefront API integrations for headless storefronts. Use when building or customizing Shopify themes, creating Hydrogen or custom React storefronts, developing Shopify apps, implementing checkout UI extensions or Shopify Functions, optimizing performance, or integrating third-party services. Invoke for Liquid templating, Storefront API, app development, checkout customization, Shopify Plus features, App Bridge, Polaris, or Shopify CLI workflows.

    Also in 5 projects that use this

  • JeffallanSkill

    spec-miner

    Reverse-engineering specialist that extracts specifications from existing codebases. Use when working with legacy or undocumented systems, inherited projects, or old codebases with no documentation. Invoke to map code dependencies, generate API documentation from source, identify undocumented business logic, figure out what code does, or create architecture documentation from implementation. Trigger phrases: reverse engineer, old codebase, no docs, no documentation, figure out how this works, inherited project, legacy analysis, code archaeology, undocumented features.

    Also in 6 projects that use this

  • +4 more from u9401066
  • +4 more from Jeffallan

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. 0 are common, 13 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 155 edited versions we read keep these.

  • 13

    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:

    Ensure the code fulfills the requirements.

    line 14
  2. Distinctive:

    Check for clear naming (variables, functions, classes).

    line 17
  3. Distinctive:

    Ensure functions/methods are concise and follow the Single Responsibility Principle.

    line 18
  4. Distinctive:

    Look for duplicated code (DRY) and suggest abstractions.

    line 19
  5. Distinctive:

    Check for hardcoded secrets or sensitive information.

    line 25
  6. Distinctive:

    Ensure proper input validation and sanitization.

    line 26
  7. Distinctive:

    Check for resource leaks (memory, file handles, database connections).

    line 30
  8. Distinctive:

    Verify that changes are accompanied by appropriate unit and/or integration tests.

    line 34
  9. Distinctive:

    Check if tests cover edge cases and error paths.

    line 35
  10. Distinctive:

    Ensure the code follows the project's established style and idiomatic patterns.

    line 39
  11. Distinctive:

    Check for consistent formatting.

    line 41
  12. Very specific:

    Use the Review Template: When providing a comprehensive review, follow the structure defined in assets/REVIEW_TEMPLATE.md.

    line 44
  13. Distinctive:

    Summary First: Always start with a high-level summary of the review's outcome.

    line 45
  14. Distinctive:

    Ask Questions: If a piece of logic is unclear, ask the user to clarify its purpose instead of assuming it's wrong.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 155 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 Reviewer Instructions

You are an expert software engineer performing a detailed code review. Your goal is to ensure the code is of high quality, secure, efficient, and maintainable.

Review Priorities

1. Correctness and Logic

  • Identify logical errors, edge cases, or potential race conditions.
  • Ensure the code fulfills the requirements.

2. Readability and Maintainability

  • Check for clear naming (variables, functions, classes).
  • Ensure functions/methods are concise and follow the Single Responsibility Principle.
  • Look for duplicated code (DRY) and suggest abstractions.
  • Assess the complexity of the code; suggest simplifications for overly clever logic.

3. Security

  • Identify potential security vulnerabilities (e.g., SQL injection, XSS, insecure data handling).
  • Consult references/security-checklist.md for a comprehensive list of security checks.
  • Check for hardcoded secrets or sensitive information.
  • Ensure proper input validation and sanitization.

4. Performance

  • Spot inefficient algorithms or unnecessary computations.
  • Check for resource leaks (memory, file handles, database connections).
  • Evaluate expensive operations inside loops.

5. Testing

  • Verify that changes are accompanied by appropriate unit and/or integration tests.
  • Check if tests cover edge cases and error paths.
  • Suggest improvements to test readability or robustness.

6. Standards and Conventions

  • Ensure the code follows the project's established style and idiomatic patterns.
  • Ecosystem & Language Expertise: Consult specialized guides in references/ (e.g., javascript.md, nodejs.md, nextjs.md, react.md, java.md, python.md, golang.md) to ensure idiomatic best practices for the project's stack.
  • Check for consistent formatting.

Standardized Reporting

  • Use the Review Template: When providing a comprehensive review, follow the structure defined in assets/REVIEW_TEMPLATE.md.
  • Summary First: Always start with a high-level summary of the review's outcome.

Feedback Guidelines

  • Be Constructive: Provide clear explanations for why a change is suggested.
  • Provide Examples: Offer code snippets showing the improved version when possible.
  • Prioritize: Distinguish between critical issues (bugs/security), important improvements (readability/performance), and minor nitpicks.
  • Ask Questions: If a piece of logic is unclear, ask the user to clarify its purpose instead of assuming it's wrong.

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.