菜单
Orchestrates a comprehensive code review using up to 6 specialist skills. Dispatches code-review, code-simplifier, comment-analyzer, silent-failure-hunter, type-design-analyzer, and test-analyzer based on the scope of changes. Use for thorough end-to-end review of code changes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.
Use for landing pages, websites, apps, and UI where visual composition and structure are the primary concern. Enforces art direction, image-led hierarchy, content structure, and restrained motion. Complements frontend-design by focusing on layout and composition rules rather than aesthetic boldness.
Use when the user asks to build an MCP server, create an MCP integration, wrap an API for AI agents, or expose tools via the Model Context Protocol. Guides through deployment model selection (remote HTTP, MCPB, local stdio), tool-design patterns, and framework choice before scaffolding code.
Multi-agent code review for local changes, files, or directories. Detects bugs, security issues, and conventions-file violations (AGENTS.md/CLAUDE.md/GEMINI.md).
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Works on recently modified code, a set of changes, or the whole codebase.
| name | review-toolkit |
| description | Orchestrates a comprehensive code review using up to 6 specialist skills. Dispatches code-review, code-simplifier, comment-analyzer, silent-failure-hunter, type-design-analyzer, and test-analyzer based on the scope of changes. Use for thorough end-to-end review of code changes. |
| argument-hint | [file, directory, or git diff to review] |
| user-invocable | true |
Comprehensive code review orchestrator. Dispatches specialist review agents based on the scope of changes and aggregates all findings in a unified report.
| Skill | Purpose |
|---|---|
| code-review | Bugs, security issues, correctness, conventions-file violations |
| code-simplifier | Unnecessary complexity, duplication, readability |
| comment-analyzer | Comment accuracy, comment rot, misleading documentation |
| silent-failure-hunter | Silent errors, inadequate user feedback, catch block quality |
| type-design-analyzer | Type encapsulation, invariant expression and enforcement |
| test-analyzer | Behavioral coverage gaps, test quality, anti-pattern detection |
Always run:
Run when applicable:
try/catch, error callbacks, fallbacks)Run after correctness is confirmed (regardless of other findings):
## Toolkit Summary
Specialists dispatched: [list]
Overall assessment: [PASS / NEEDS WORK / CRITICAL ISSUES]
## Critical Issues
[Aggregated CRITICAL findings from all specialists, with source skill noted]
## Important Issues
[Aggregated HIGH/IMPORTANT findings]
## Suggestions
[Aggregated MEDIUM/lower priority findings]
## Positive Observations
[Notable good practices found across all reviews]
Severity order: Critical → Important → Suggestions → Positive Observations.