
React Doctor
Skill运行 React Doctor(npx react-doctor)扫描 React 代码的安全、性能、正确性、无障碍与架构问题并给出 0–100 健康分;改完代码后只扫改动部分确认分数没有下降,输入 /doctor 时拉取官方排查流程逐项修复。
name: react-doctor
description: Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
version: "1.2.0"
React Doctor
Scans React codebases for security, performance, correctness, and architecture issues. Outputs a 0–100 health score.
After making React code changes:
Run npx react-doctor@latest --verbose --scope changed and check the score did not regress.
If the score dropped, fix the regressions before committing.
For general cleanup or code improvement:
Run npx react-doctor@latest --verbose (the default --scope full) to scan the full codebase. Fix issues by severity — errors first, then warnings.
For a focused UI design audit:
Run npx react-doctor@latest design --verbose. This selects only design-tagged UI composition, typography, interaction, accessibility, and motion rules, including focused rules that remain opt-in during a general health scan.
/doctor — full local triage workflow
When the user types /doctor, says "run react doctor", or asks for a full triage / cleanup pass (not just a regression check), fetch the canonical local-triage playbook and follow every step in it:
curl --fail --silent --show-error \
--header 'Cache-Control: no-cache' \
https://www.react.doctor/prompts/react-doctor-agent.md
The playbook is the single source of truth — a scan → filter → triage → fix → validate loop that edits the working tree directly (never commits, never opens PRs). Updating the prompt at its source updates every agent on its next fetch — no skill reinstall needed.
Pair it with the matching per-rule prompts at https://www.react.doctor/prompts/rules/<plugin>/<rule>.md (fetched on demand inside the playbook) so each fix uses the canonical, reviewer-tested recipe.
Configuring or explaining rules
When the user wants to understand a rule, disagrees with one, or wants to disable / tune which rules run (not fix code), read references/explain.md and follow it. Start with npx react-doctor@latest rules explain <rule>, then apply the narrowest control via npx react-doctor@latest rules disable|set|category|ignore-tag …, which edits your doctor.config.* (or package.json#reactDoctor).
Command
npx react-doctor@latest --verbose --scope changed
| Flag | Purpose |
|---|---|
. | Scan current directory |
--verbose | Show affected files and line numbers per rule |
--scope changed | Only report issues introduced vs the base branch (default: full) |
--scope lines | Only report issues on the changed lines |
--score | Output only the numeric score |
design | Run only the focused UI design diagnostics |
相關資源

Improve React
Skill以资深 React 工程师的视角审查整个代码库:先只读运行 React Doctor 扫描作为证据,按缺陷、性能、无障碍、安全、可维护性五类筛选并排序问题,再为选定的问题写出可交给其他 agent 执行的独立实施计划,不改源码。
millionco/react-doctor15k
Ponytail
Skill让 agent 按「能不写就不写」的阶梯解题:先问是否需要,再依次复用现有代码、标准库、平台原生能力与已装依赖,只写最少的必要代码,但保留校验、错误处理、安全与无障碍。
DietrichGebert/ponytail166k
Code Review and Quality
Skill合并前从正确性、可读性、架构、安全与性能五个维度评审代码变更,适用于自己、其他 agent 或他人写的代码与 PR,按改善整体代码健康度的标准给出结论。Addy Osmani 的 agent-skills 合集之一。
addyosmani/agent-skills108k
Open Code Review
Skill驱动阿里开源的 ocr CLI 评审 Git 变更(工作区、单个提交或分支对比),按严重级别汇总逐行评审意见,用户要求时自动修复。需先配置 LLM 接口(Anthropic、OpenAI 等协议),缺少 CLI 时会自动安装。阿里巴巴官方维护。
alibaba/open-code-review47.6k
React Composition Patterns
SkillVercel 出品的 React 组合模式指南:用复合组件、状态提升和清晰的 Context 接口取代布尔 props 泛滥,含 React 19 API 变化,适合重构组件库与评审组件架构。
vercel-labs/agent-skills32.6k
Vercel React Best Practices
SkillVercel 工程团队整理的 React 与 Next.js 性能规范,70 条规则按影响排序,涵盖消除请求瀑布、包体积、服务端性能与重复渲染,供编写、评审与重构时对照。Vercel 官方维护。
vercel-labs/agent-skills32.6k