菜单
Chokidar-based file watcher that triggers `claude -p` on changes. Useful for automated AI reactions to file changes — design sync, code validation, config regeneration, etc.
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
| name | file-watcher |
| description | Chokidar-based file watcher that triggers `claude -p` on changes. Useful for automated AI reactions to file changes — design sync, code validation, config regeneration, etc. |
Sets up a file watcher using chokidar that monitors a path for changes and runs a Claude prompt against every changed file. The prompt supports a {{file}} placeholder that gets replaced with the changed file path.
# Watch src/ and analyze any changed file
node scripts/watch-files.mjs ./src 'Analyze {{file}} for issues'
# Watch only .tsx files with 1s debounce
node scripts/watch-files.mjs ./src 'Review {{file}} for React best practices' --glob '*.tsx' --debounce 1000
# Via package.json script (pass args after --)
bun run watch:files -- ./src 'Check {{file}}'
node scripts/watch-files.mjs <path> <prompt> [--glob '<pattern>'] [--debounce <ms>]
| Arg | Required | Description |
|---|---|---|
<path> | Yes | File or directory to watch |
<prompt> | Yes | Claude prompt. Use {{file}} for the changed file path |
--glob | No | Glob filter (e.g. *.tsx, *.css) |
--debounce | No | Debounce delay in milliseconds (default: 500) |
add and change events{{file}} placeholder in the prompt is replaced with the actual file pathclaude -p '<prompt>' --print is executed via child_process.execSync| Use Case | Prompt |
|---|---|
| Code review | 'Review {{file}} for bugs and suggest fixes' |
| Type checking | 'Check {{file}} for TypeScript type issues' |
| Design sync | 'The design file {{file}} changed. Update the corresponding React component' |
| Test generation | 'Generate unit tests for {{file}}' |
| Documentation | 'Update documentation for changes in {{file}}' |
Filter which files trigger the watcher:
--glob '*.tsx' # Only TypeScript React files
--glob '*.css' # Only CSS files
--glob '*.{ts,tsx}' # TypeScript files (not supported by chokidar glob — use without braces)
Control how long to wait after the last change before triggering:
--debounce 200 # Fast (200ms) — good for single-file saves
--debounce 1000 # Slow (1s) — good for batch operations
--debounce 5000 # Very slow (5s) — good for build output directories
| Issue | Solution |
|---|---|
claude CLI not found | Install Claude Code: npm install -g @anthropic-ai/claude-code |
| Watcher not detecting changes | Check the path exists and you have read permissions |
| Too many invocations | Increase --debounce value |
| Prompt with special characters | Wrap prompt in single quotes; {{file}} is the only placeholder |
| Permission denied | Ensure the watched directory is readable |
chokidar (devDependency) — file system watcherclaude CLI — must be installed globally and authenticatedAnalyze environment variables in JavaScript/TypeScript projects. Identifies unused variables, infers permission scopes, detects specific services (Stripe, AWS, Supabase), and documents code paths. Includes optional cleanup of unused variables with regression detection. Use when auditing .env files, reviewing security, or documenting project configuration.
BigCommerce API expert for building integrations, apps, headless storefronts, and automations. Full lifecycle - REST APIs, GraphQL Storefront, webhooks, authentication, app development, and multi-storefront. Use when working with BigCommerce platform APIs.
Transcribes audio/video files using ElevenLabs Scribe v2 API. Use when transcribing audio files, generating transcripts, or converting speech to text.
Extracts frames and timestamped audio segments from video files (GIF, MP4, MOV) at configurable intervals and stores them in a directory with a manifest file. Use when analyzing video content, preparing frames for visual review, extracting audio for transcription, or creating frame+audio sequences for another agent to process.
Safely identifies and removes dead code in TypeScript/JavaScript projects using multi-agent analysis with automatic backup branches. Use when cleaning up unused exports, orphaned files, dead imports, unreachable functions, or unused dependencies.
Configure agent-tail log aggregation for the current project. Auto-detects framework (Vite, Next.js, plain Node, monorepo) and sets up CLI runner, browser log plugins, and output destinations. Use when setting up agent-tail, configuring dev server logging, or piping logs for AI agent consumption.