reviewer
Performs multi-perspective local code reviews (security, performance, logic) on diffs or files.
Install
mkdir -p .claude/skills/reviewer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13588" && unzip -o skill.zip -d .claude/skills/reviewer && rm skill.zipInstalls to .claude/skills/reviewer
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
reviewerエージェントにローカルの差分・ファイルをレビューさせる。バグ・セキュリティ・パフォーマンス・保守性・命名一貫性・リグレッション・データアクセス重複などの観点でレビューし VERDICT: PASS/FAIL を返す。「reviewerに見せて」「reviewer」「ローカルの差分を見て」といった要望に使う。PR番号・リモートブランチ・gh pr 経由のレビューは /review-pr を使うこと。ユーザーが /reviewer と入力したら必ずこのスキルを使う。Key capabilities
- →Identify the scope of code to review based on arguments
- →Determine the set of reviewer roles for parallel execution
- →Execute code review agents in a hybrid parallel manner
- →Integrate and present review verdicts from multiple agents
- →Summarize critical and high-severity findings
How it works
The skill identifies the review scope, dynamically selects reviewer roles, and then launches multiple subagents in parallel to perform reviews based on correctness, consistency, quality, security, and architecture. It then consolidates their verdicts and findings.
Inputs & outputs
When to use reviewer
- →Review uncommitted changes
- →Check code security locally
- →Perform style and quality check
About reviewer
This skill triggers hybrid AI reviews focusing on correctness, consistency, quality, and security. It inspects local repository diffs and outputs a pass/fail verdict with actionable findings.
reviewerエージェントにローカルの差分・ファイルをレビューさせる。バグ・セキュリティ・パフォーマンス・保守性・命名一貫性・リグレッション・データアクセス重複などの観点でレビューし VERDICT: PASS/FAIL を返す。「reviewerに見せて」「reviewer」「ローカルの差分を見て」といった要望に使う。PR番号・リモートブランチ・gh pr 経由のレビューは /review-pr を使うこと。ユーザーが /reviewer と入力したら必ずこのスキルを使う。
When not to use it
- →When reviewing PRs, remote branches, or via `gh pr`
- →When the target files for review are zero
- →When the `function_calls` block is split across multiple turns
Limitations
- →Subagent calls from within a subagent are not possible
- →The `function_calls` block must not be split across multiple turns
- →The number of launched agents must match the declared N
How it compares
This skill automates code review by dispatching multiple specialized AI agents in parallel to analyze local diffs, providing a structured verdict and findings, which differs from a manual, single-reviewer process.
Compared to similar skills
reviewer side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| reviewer (this skill) | 0 | 3mo | Review | Advanced |
| github-code-review | 13 | 4mo | Review | Advanced |
| reviewing-nextjs-16-patterns | 11 | 10mo | Review | Intermediate |
| agent-code-analyzer | 3 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
github-code-review
ruvnet
Comprehensive GitHub code review with AI-powered swarm coordination
reviewing-nextjs-16-patterns
djankies
Review code for Next.js 16 compliance - security patterns, caching, breaking changes. Use when reviewing Next.js code, preparing for migration, or auditing for violations.
agent-code-analyzer
ruvnet
Agent skill for code-analyzer - invoke with $agent-code-analyzer
code-review-ai-ai-review
sickn33
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C
code-review-developer
anyproto
Context-aware routing to code review guidelines. Use when reviewing pull requests, providing code feedback, or discussing review standards.
codex-code-review
tyrchen
Perform comprehensive code reviews using OpenAI Codex CLI. This skill should be used when users request code reviews, want to analyze diffs/PRs, need security audits, performance analysis, or want automated code quality feedback. Supports reviewing staged changes, specific files, entire directories, or git diffs.