菜单
Catch bad React in your changes — run react-doctor's deterministic scan and fix what it flags
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
Run a verifiable security scan (vulns, secrets, misconfig) over code you wrote or deps you added, before calling the work done
Drive a real browser verifiably — navigate, snapshot, act BY INDEX, extract; every step provable
Run multi-agent work as ONE provable causal DAG — parallel subagents, an Orchestrate graph, an immutable spec-seed
Author or connect a Model Context Protocol server so an agent gains new tools
Build automated pipelines that gate merges and ship reliably
Build reliable, resumable data connectors and transforms (ETL)
| name | react-doctor |
| description | Catch bad React in your changes — run react-doctor's deterministic scan and fix what it flags |
| version | 1 |
| trust | built-in |
When you've written or changed React/JSX (components, hooks, state, effects), run react-doctor — a deterministic linter that catches the mistakes agents commonly make in React — before calling the work done.
npx CLI; requires Node):
npx react-doctor@latest
On a large repo, scope to the files you touched.doctor.config.{ts,js,json}, respect it — it tunes which
rules run.This is the "your agent writes bad React → this catches it" check: cheap, fast, and
it catches the bug classes that slip past a quick read. (react-doctor also ships an
install command that drops editor skills/rules, and an experimental LSP server —
but for an agent loop, running the CLI on your diff is the direct path.)