一键导入
code-standards-review
Review a codebase for adherence to code standards. Uses specialized agents with progressive disclosure to determine which standards apply.
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。
菜单
Review a codebase for adherence to code standards. Uses specialized agents with progressive disclosure to determine which standards apply.
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
Add terms, context, or instructions to Shama voice-to-text files for clipboard mode (Ctrl+Opt+Space) or shell-command mode (Ctrl+Opt+S), at project or global level.
Initialize Shama voice-to-text config for the project — create voice.json, voice-vocabulary.md, voice-context.md, and register the project in Shama's registry.toml.
Reflect on codebase navigation effectiveness at end of conversation. Surfaces dead ends, inefficiencies, missing context. Does not write files — pair with /kiro:steering-custom to persist.
Use when picking or vetting a keyboard shortcut on macOS. Triggers include "what hotkey should I use for X", "is `<combo>` available", "does this shortcut conflict", "recommend a keybinding for…", "check `<combo>` against my setup", "pick a hotkey for…", or any mention of choosing/binding/changing a shortcut in WezTerm, tmux, Zed, Chrome, Claude Code, or macOS. Determines whether a proposed combo collides with OS-reserved bindings, app defaults, or the user's customizations, and recommends ergonomic alternatives when needed.
Detect and remove dead code with knip. Use when the user asks to "run knip", "find unused files", "find unused exports", "find unused dependencies", "clean up dead code", "remove dead code", "set up knip", "configure knip", "knip.json", "knip false positive", "knip CI", or mentions a `knip` config, dependency bloat, bundle bloat from unused imports, or tree-shaking unused exports. Covers the configuration-first workflow, confidence-gated deletion, framework-specific gotchas (Next.js 15+, Tailwind, Storybook, Jest, Bun's test runner and `bun build --compile`), monorepos, CI integration, and performance tuning.
This skill should be used when the user asks to "set up react-scan", "install react-scan", "diagnose React re-renders", "find unnecessary renders", "find unstable props", "automate React render checks with Playwright", "react-scan + playwright", "measure component renders programmatically", "check why a React component is slow", or mentions React rendering issues, slow React interactions, render counts, or component-level perf attribution. Covers install across Next.js/Vite/Remix/script-tag/browser-extension, the lite headless API for CI, and the canonical render-attribution → fix → validate loop driven through Playwright.
| name | code-standards-review |
| description | Review a codebase for adherence to code standards. Uses specialized agents with progressive disclosure to determine which standards apply. |
This skill provides comprehensive code standards audits using specialized agents. It automatically determines which code standards apply to your codebase and launches focused review agents only for applicable standards, reporting findings in a user-friendly format with recommendations.
The skill provides:
When invoked, the skill first determines:
The skill uses progressive disclosure to launch only relevant agents:
Detected Automatically:
All Codebases:
TypeScript Projects:
React Projects:
The system scans for file types and project characteristics to determine relevance. The Zustand, Dependency Injection, and TanStack Query reviewers run on applicable projects even if those patterns aren't currently used, identifying opportunities for best-practice adoption.
When applicable standards are determined, specialized agents are launched in parallel:
Each agent provides prescriptive guidance:
Each finding includes:
Findings are aggregated into a summary report showing:
The user is presented with findings and asked:
To audit your entire project against code standards, invoke the skill with:
"Review my codebase for code standards"
or
"Audit my project for standards violations"
To audit a specific directory, include the path:
"Review my /src/features directory for standards"
or
"Audit /src/components for code standards violations"
or
"Check the /app/products scope against standards"
The skill produces:
Each standard has comprehensive reference documentation available in the skill's references/ directory for detailed guidance. The Testing reviewer works in conjunction with the Dependency Injection reviewer — proper DI eliminates most mocking needs. The Zustand, Dependency Injection, and TanStack Query agents are prescriptive reviewers that identify both violations of existing implementations AND opportunities to adopt these preferred patterns even if not currently used.
@references/colocation-standards.md - Code organization principles@references/general-code-standards.md - Quality and design principles@references/testing-standards.md - Test quality, mocking strategy, test value@references/zustand-reference.md - State management best practices@references/dependency-injection.md - Service layer patterns@references/typescript-general.md - Type safety standards@references/tanstack-query-key-factory-reference.md - Query pattern best practicesOnly launches agents for standards applicable to detected technologies. A vanilla JavaScript project won't get Zustand or TypeScript reviews.
Multiple agents work simultaneously, dramatically reducing review time while maintaining quality.
Findings are categorized as Critical (must fix), High (important), or Medium (nice-to-have), helping you prioritize effort.
Before implementation, you're shown summary findings and asked which issues to address, ensuring you're aligned with recommendations.
Each finding includes:
The skill provides everything needed for a comprehensive standards audit and actionable recommendations for improvement.