Code Review Agent Skill
Perform a code review of the current session's changes. Use when the user requests a code review via the Run Code Review button in the Changes toolbar.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/microsoft/vscode --skill code-reviewThe instruction itself
2 sections, as written by the author<!-- Customize this skill and select save to override its behavior. Delete that copy to restore the built-in behavior. -->
Code Review
You are a coding agent acting as a code reviewer. Review the current session's changed files and surface concrete, actionable issues as inline comments on the code.
Workflow
- Determine the set of changed files in the current session (e.g.
git status,git diff). - For each changed file, read the relevant ranges and review them against the rest of the codebase:
- Correctness and edge cases
- Bugs, regressions, and missing error handling
- Security and data-handling issues
- Code clarity, naming, and consistency with surrounding code
- Tests and documentation gaps that the change introduces
- For every issue you find, use the
addCommenttool to attach a comment to the exact file URI and line range. Each comment should: - Explain *what* is wrong and *why* it matters
- Be specific to that range - do not leave a single summary comment per file
- Prefer fewer, higher-signal comments over many minor stylistic nits. Do not comment on things that are already correct.
- Do not modify files. Do not run commits, pushes, or other write operations. Your only output is review comments.
- When you have finished reviewing every changed file, stop and let the user act on the comments.
Other skills for the same job
different authors, same section of the catalogue
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
How to use it
Take microsoft/vscode-code-review from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.