[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75WA91AVMNDCE7SXQCVKS93":3,"skill-same:01M75WA91AVMNDCE7SXQCVKS93":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M75WA91AVMNDCE7SXQCVKS93","debug-bridge",null,"Browser automation and inspection for AI agents via WebSocket","stevengonsalvez\u002Fainb-toolkit","stevengonsalvez","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9320602?v=4","01M75W59QRYZYANWY3XG8CJB1P","Steven Gonsalvez","01M75W59RD5YW1RT67BDV0EAZF",1,"MIT","https:\u002F\u002Fgithub.com\u002Fstevengonsalvez\u002Fainb-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fdebug-bridge\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: debug-bridge\ndescription: Browser automation and inspection for AI agents via WebSocket\ntriggers:\n  - debug the app\n  - test this flow\n  - click the button\n  - take a screenshot\n  - inspect the UI\n  - capture network requests\n  - monitor navigation\ntype: cli-tool\nprotocol_version: 1\ndefault_port: 4000\ncapabilities:\n  - ui_tree\n  - dom_snapshot\n  - console\n  - errors\n  - network\n  - navigation\n  - screenshot\n  - eval\n---\n\n# Debug Bridge Runbook\n\nControl web apps via WebSocket. Click, type, screenshot, inspect, capture network traffic, monitor navigation.\n\n## Prerequisites (Webapp Setup)\n\n**The webapp MUST have the debug-bridge SDK installed and configured before agents can control it.**\n\n### Step 1: Install SDK in Webapp\n\n```bash\nnpm install debug-bridge-browser\n```\n\n### Step 2: Add Initialization Code\n\nCreate `src\u002Fdebug-bridge.ts` (or add to your app's entry point):\n\n```typescript\nimport { createDebugBridge } from 'debug-bridge-browser';\n\n\u002F\u002F ONLY runs in development - safe to leave in production builds\nif (import.meta.env.DEV) {\n  const params = new URLSearchParams(window.location.search);\n  const session = params.get('session');\n  const port = params.get('port') || '4000';\n\n  if (session) {\n    const bridge = createDebugBridge({\n      url: `ws:\u002F\u002Flocalhost:${port}\u002Fdebug?role=app&sessionId=${session}`,\n      sessionId: session,\n      appName: 'My App',  \u002F\u002F Shows in CLI when connected\n      appVersion: '1.0.0',\n\n      \u002F\u002F Feature toggles (all true by default)\n      enableNetwork: true,      \u002F\u002F Capture fetch\u002FXHR requests\n      enableNavigation: true,   \u002F\u002F Track route changes\n      enableConsole: true,      \u002F\u002F Capture console.log\u002Ferror\n      enableErrors: true,       \u002F\u002F Capture unhandled errors\n\n      \u002F\u002F Optional: filter which URLs to capture\n      networkUrlFilter: (url) => !url.includes('\u002Fanalytics'),\n      maxNetworkBodySize: 10000,  \u002F\u002F Truncate large request\u002Fresponse bodies\n    });\n\n    bridge.connect();\n\n    \u002F\u002F Optional: expose for manual debugging\n    (window as any).__debugBridge = bridge;\n  }\n}\n```\n\n### Step 3: Import in App Entry\n\n```typescript\n\u002F\u002F main.tsx or App.tsx\nimport '.\u002Fdebug-bridge';  \u002F\u002F Add this import\n```\n\n### How It Works\n\n1. Webapp reads `?session=X&port=Y` from URL\n2. If present, connects to debug server as `role=app`\n3. Agent connects to same server as `role=agent`\n4. Agent sends commands → Server relays → Webapp executes → Results returned\n\n```\n┌─────────────┐     WebSocket      ┌─────────────┐     WebSocket      ┌─────────────┐\n│   AI Agent  │ ◄─────────────────► │  CLI Server │ ◄─────────────────►│   Webapp    │\n│             │   role=agent       │  (port 4000) │   role=app         │  (browser)  │\n└─────────────┘                    └─────────────┘                    └─────────────┘\n```\n\n---\n\n## Agent Usage\n\n**Once the webapp has the SDK configured, agents can control it.**\n\n### Quick Start\n\n```bash\n# 1. Start debug server (in tmux for persistence)\nSESSION=\"debug-$(date +%s)\"\nPORT=$(shuf -i 4000-4999 -n 1)\ntmux new-session -d -s \"$SESSION\"\ntmux send-keys -t \"$SESSION\" \"npx debug-bridge-cli connect --session $SESSION --port $PORT 2>&1 | tee debug-bridge-$PORT.log\" C-m\n\n# 2. Open webapp with debug params (webapp must have SDK installed!)\nopen \"http:\u002F\u002Flocalhost:5173?session=$SESSION&port=$PORT\"\n\n# 3. Attach to tmux to use CLI\ntmux attach -t \"$SESSION\"\n```\n\n### CLI Commands\n\n| Command | Example | Description |\n|---------|---------|-------------|\n| `ui` | `ui` | List interactive elements |\n| `click \u003Ctarget>` | `click 3` or `click \"Sign In\"` | Click element |\n| `type \u003Ctarget> \u003Ctext>` | `type 1 \"hello\"` or `type \"email\" \"a@b.com\"` | Type into input |\n| `js \u003Ccode>` | `js document.title` | Run JavaScript, shows result |\n| `screenshot` | `screenshot` | Save viewport as PNG |\n| `state` | `state` | Get cookies, localStorage |\n| `go \u003Curl>` | `go \u002Flogin` | Navigate to URL |\n| `find \u003Cquery>` | `find email` | Search UI tree |\n| `eval \u003Ccode>` | `eval localStorage.clear()` | Alias for `js` |\n| `help` | `help` | Show all available commands |\n\n### AI Agent Usage (via tmux)\n\n**AI agents can't attach to terminals interactively.** Use `tmux send-keys` to send commands and `tmux capture-pane` to read output:\n\n```bash\n# Send a command to the debug-bridge CLI\ntmux send-keys -t \"$SESSION\" \"screenshot\" C-m\n\n# Wait for result and read output\nsleep 2\ntmux capture-pane -t \"$SESSION\" -p | tail -20\n\n# Run JavaScript in the browser\ntmux send-keys -t \"$SESSION\" \"js document.title\" C-m\nsleep 1\ntmux capture-pane -t \"$SESSION\" -p | tail -5\n\n# Trigger events (e.g., for testing visibility handlers)\ntmux send-keys -t \"$SESSION\" 'eval window.dispatchEvent(new Event(\"focus\"))' C-m\n```\n\n**Key Pattern for AI Agents:**\n1. Start CLI in tmux (not foreground)\n2. Send commands via `tmux send-keys`\n3. Read results via `tmux capture-pane`\n4. Screenshots are saved as PNG files in current directory\n\n### Targeting Elements\n\nElements can be targeted by:\n- **Index**: `click 3` (element #3 from `ui` output)\n- **Text**: `click \"Submit\"` (matches button\u002Flink text)\n- **Placeholder**: `type \"email\" \"test@example.com\"`\n- **StableId**: `click btn-656b07` (hash shown in `ui` output)\n\n### WebSocket API (Programmatic)\n\n```javascript\n\u002F\u002F Connect as agent\nconst ws = new WebSocket(`ws:\u002F\u002Flocalhost:4000\u002Fdebug?role=agent&sessionId=my-session`);\n\n\u002F\u002F Base message (required fields)\nconst msg = {\n  protocolVersion: 1,\n  sessionId: 'my-session',\n  timestamp: Date.now(),\n  requestId: crypto.randomUUID()\n};\n\n\u002F\u002F Send commands\nws.send(JSON.stringify({ ...msg, type: 'request_ui_tree' }));\nws.send(JSON.stringify({ ...msg, type: 'click', target: { stableId: 'btn-abc' } }));\nws.send(JSON.stringify({ ...msg, type: 'type', target: { selector: '#email' }, text: 'test@example.com' }));\nws.send(JSON.stringify({ ...msg, type: 'evaluate', code: 'document.title' }));\nws.send(JSON.stringify({ ...msg, type: 'request_screenshot' }));\nws.send(JSON.stringify({ ...msg, type: 'navigate', url: '\u002Fdashboard' }));\n```\n\n### Response Types\n\n```javascript\n\u002F\u002F UI Tree response\n{ type: 'ui_tree', items: [{ stableId, role, text, label, visible, meta }] }\n\n\u002F\u002F Command success\n{ type: 'command_result', success: true, result: any, duration: 5 }\n\n\u002F\u002F Screenshot\n{ type: 'screenshot', data: 'base64...', width: 1920, height: 1080 }\n\n\u002F\u002F Error\n{ type: 'command_result', success: false, error: { code: 'TARGET_NOT_FOUND', message: '...' } }\n\n\u002F\u002F Network request (auto-streamed)\n{ type: 'network_request', requestId: 'net-1-1234', method: 'POST', url: '\u002Fapi\u002Fusers', initiator: 'fetch' }\n\n\u002F\u002F Network response (auto-streamed)\n{ type: 'network_response', requestId: 'net-1-1234', status: 200, statusText: 'OK', duration: 45, ok: true, body: '{\"id\":1}' }\n\n\u002F\u002F Navigation event (auto-streamed)\n{ type: 'navigation', url: '\u002Fdashboard', previousUrl: '\u002Flogin', trigger: 'pushstate' }\n\n\u002F\u002F Console message (auto-streamed)\n{ type: 'console', level: 'error', args: ['Failed to fetch user', '{\"status\":401}'] }\n```\n\n---\n\n## Example Workflows\n\n### Login Flow\n```\nui                           # Discover form elements\ntype \"email\" \"user@test.com\" # Fill email field\ntype \"password\" \"secret123\"  # Fill password field\nclick \"Sign In\"              # Click submit button\nscreenshot                   # Capture result for verification\n```\n\n### Form Testing\n```\ngo \u002Fregister                 # Navigate to page\nui                           # List interactive elements\ntype 1 \"John\"                # Fill first input by index\ntype 2 \"john@test.com\"       # Fill second input\nclick \"Submit\"               # Submit form\nstate                        # Check localStorage for saved data\n```\n\n### Debugging\n```\nui                           # See current page state\njs localStorage.getItem('token')  # Check auth token\njs window.__REDUX_STATE__    # Inspect app state\nscreenshot                   # Capture for analysis\n```\n\n### API Debugging (Network Capture)\n```\n# Network requests are auto-captured - watch the CLI output:\n# 🌐 [POST] \u002Fapi\u002Flogin\n#    ✓ 200 OK (45ms)\n# 🌐 [GET] \u002Fapi\u002Fusers\u002Fme\n#    ✗ 401 Unauthorized (12ms)\n\n# Navigation is also tracked:\n# 🔀 [pushstate] \u002Fdashboard\n# 🔀 [popstate] \u002Flogin\n```\n\n### Monitoring API Calls\n```javascript\n\u002F\u002F Connect as agent and filter for network events\nws.onmessage = (e) => {\n  const msg = JSON.parse(e.data);\n  if (msg.type === 'network_response' && !msg.ok) {\n    console.log(`API Error: ${msg.status} on request ${msg.requestId}`);\n  }\n  if (msg.type === 'navigation') {\n    console.log(`User navigated to: ${msg.url}`);\n  }\n};\n```\n\n---\n\n## Error Recovery\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| `TARGET_NOT_FOUND` | Element not in DOM | Run `ui` to refresh, verify element exists |\n| `TARGET_NOT_VISIBLE` | Element off-screen | `scroll 0 500` first, then retry |\n| `EVAL_DISABLED` | App disabled eval | Use DOM commands instead |\n| `SCREENSHOT_FAILED` | Modern CSS (oklch) | Use `js` to inspect DOM directly |\n| No connection | Webapp missing SDK | Verify SDK is installed and initialized |\n| Missing network events | SDK config | Check `enableNetwork: true` in config |\n| Missing navigation events | SDK config | Check `enableNavigation: true` in config |\n\n## Telemetry Reference\n\n| Telemetry | Auto-sent | Description |\n|-----------|-----------|-------------|\n| `ui_tree` | On connect + changes | Interactive elements list |\n| `dom_mutations` | Continuous | DOM changes (batched) |\n| `console` | Continuous | Console.log\u002Fwarn\u002Ferror |\n| `error` | On error | Unhandled errors |\n| `network_request` | On fetch\u002FXHR | Outgoing API calls |\n| `network_response` | On response | API responses with status\u002Fbody |\n| `navigation` | On route change | URL changes (push\u002Fpop\u002Freplace\u002Fhash) |\n| `state_update` | On change | Custom app state (if configured) |\n\n## Troubleshooting\n\n```bash\n# Port already in use\nlsof -ti:4000 | xargs kill -9\n\n# Check if server is running\ntmux attach -t debug-*\n\n# View server logs\ntail -f debug-bridge-*.log\n\n# Webapp not connecting?\n# 1. Check URL has ?session=X&port=Y\n# 2. Check browser console for [DebugBridge] logs\n# 3. Verify SDK is imported in dev mode\n```\n","# Debug Bridge Runbook\n\nControl web apps via WebSocket. Click, type, screenshot, inspect, capture network traffic, monitor navigation.\n\n## Prerequisites (Webapp Setup)\n\n**The webapp MUST have the debug-bridge SDK installed and configured before agents can control it.**\n\n### Step 1: Install SDK in Webapp\n\n```bash\nnpm install debug-bridge-browser\n```\n\n### Step 2: Add Initialization Code\n\nCreate `src\u002Fdebug-bridge.ts` (or add to your app's entry point):\n\n```typescript\nimport { createDebugBridge } from 'debug-bridge-browser';\n\n\u002F\u002F ONLY runs in development - safe to leave in production builds\nif (import.meta.env.DEV) {\n  const params = new URLSearchParams(window.location.search);\n  const session = params.get('session');\n  const port = params.get('port') || '4000';\n\n  if (session) {\n    const bridge = createDebugBridge({\n      url: `ws:\u002F\u002Flocalhost:${port}\u002Fdebug?role=app&sessionId=${session}`,\n      sessionId: session,\n      appName: 'My App',  \u002F\u002F Shows in CLI when connected\n      appVersion: '1.0.0',\n\n      \u002F\u002F Feature toggles (all true by default)\n      enableNetwork: true,      \u002F\u002F Capture fetch\u002FXHR requests\n      enableNavigation: true,   \u002F\u002F Track route changes\n      enableConsole: true,      \u002F\u002F Capture console.log\u002Ferror\n      enableErrors: true,       \u002F\u002F Capture unhandled errors\n\n      \u002F\u002F Optional: filter which URLs to capture\n      networkUrlFilter: (url) => !url.includes('\u002Fanalytics'),\n      maxNetworkBodySize: 10000,  \u002F\u002F Truncate large request\u002Fresponse bodies\n    });\n\n    bridge.connect();\n\n    \u002F\u002F Optional: expose for manual debugging\n    (window as any).__debugBridge = bridge;\n  }\n}\n```\n\n### Step 3: Import in App Entry\n\n```typescript\n\u002F\u002F main.tsx or App.tsx\nimport '.\u002Fdebug-bridge';  \u002F\u002F Add this import\n```\n\n### How It Works\n\n1. Webapp reads `?session=X&port=Y` from URL\n2. If present, connects to debug server as `role=app`\n3. Agent connects to same server as `role=agent`\n4. Agent sends commands → Server relays → Webapp executes → Results returned\n\n```\n┌─────────────┐     WebSocket      ┌─────────────┐     WebSocket      ┌─────────────┐\n│   AI Agent  │ ◄─────────────────► │  CLI Server │ ◄─────────────────►│   Webapp    │\n│             │   role=agent       │  (port 4000) │   role=app         │  (browser)  │\n└─────────────┘                    └─────────────┘                    └─────────────┘\n```\n\n---\n\n## Agent Usage\n\n**Once the webapp has the SDK configured, agents can control it.**\n\n### Quick Start\n\n```bash\n# 1. Start debug server (in tmux for persistence)\nSESSION=\"debug-$(date +%s)\"\nPORT=$(shuf -i 4000-4999 -n 1)\ntmux new-session -d -s \"$SESSION\"\ntmux send-keys -t \"$SESSION\" \"npx debug-bridge-cli connect --session $SESSION --port $PORT 2>&1 | tee debug-bridge-$PORT.log\" C-m\n\n# 2. Open webapp with debug params (webapp must have SDK installed!)\nopen \"http:\u002F\u002Flocalhost:5173?session=$SESSION&port=$PORT\"\n\n# 3. Attach to tmux to use CLI\ntmux attach -t \"$SESSION\"\n```\n\n### CLI Commands\n\n| Command | Example | Description |\n|---------|---------|-------------|\n| `ui` | `ui` | List interactive elements |\n| `click \u003Ctarget>` | `click 3` or `click \"Sign In\"` | Click element |\n| `type \u003Ctarget> \u003Ctext>` | `type 1 \"hello\"` or `type \"email\" \"a@b.com\"` | Type into input |\n| `js \u003Ccode>` | `js document.title` | Run JavaScript, shows result |\n| `screenshot` | `screenshot` | Save viewport as PNG |\n| `state` | `state` | Get cookies, localStorage |\n| `go \u003Curl>` | `go \u002Flogin` | Navigate to URL |\n| `find \u003Cquery>` | `find email` | Search UI tree |\n| `eval \u003Ccode>` | `eval localStorage.clear()` | Alias for `js` |\n| `help` | `help` | Show all available commands |\n\n### AI Agent Usage (via tmux)\n\n**AI agents can't attach to terminals interactively.** Use `tmux send-keys` to send commands and `tmux capture-pane` to read output:\n\n```bash\n# Send a command to the debug-bridge CLI\ntmux send-keys -t \"$SESSION\" \"screenshot\" C-m\n\n# Wait for result and read output\nsleep 2\ntmux capture-pane -t \"$SESSION\" -p | tail -20\n\n# Run JavaScript in the browser\ntmux send-keys -t \"$SESSION\" \"js document.title\" C-m\nsleep 1\ntmux capture-pane -t \"$SESSION\" -p | tail -5\n\n# Trigger events (e.g., for testing visibility handlers)\ntmux send-keys -t \"$SESSION\" 'eval window.dispatchEvent(new Event(\"focus\"))' C-m\n```\n\n**Key Pattern for AI Agents:**\n1. Start CLI in tmux (not foreground)\n2. Send commands via `tmux send-keys`\n3. Read results via `tmux capture-pane`\n4. Screenshots are saved as PNG files in current directory\n\n### Targeting Elements\n\nElements can be targeted by:\n- **Index**: `click 3` (element #3 from `ui` output)\n- **Text**: `click \"Submit\"` (matches button\u002Flink text)\n- **Placeholder**: `type \"email\" \"test@example.com\"`\n- **StableId**: `click btn-656b07` (hash shown in `ui` output)\n\n### WebSocket API (Programmatic)\n\n```javascript\n\u002F\u002F Connect as agent\nconst ws = new WebSocket(`ws:\u002F\u002Flocalhost:4000\u002Fdebug?role=agent&sessionId=my-session`);\n\n\u002F\u002F Base message (required fields)\nconst msg = {\n  protocolVersion: 1,\n  sessionId: 'my-session',\n  timestamp: Date.now(),\n  requestId: crypto.randomUUID()\n};\n\n\u002F\u002F Send commands\nws.send(JSON.stringify({ ...msg, type: 'request_ui_tree' }));\nws.send(JSON.stringify({ ...msg, type: 'click', target: { stableId: 'btn-abc' } }));\nws.send(JSON.stringify({ ...msg, type: 'type', target: { selector: '#email' }, text: 'test@example.com' }));\nws.send(JSON.stringify({ ...msg, type: 'evaluate', code: 'document.title' }));\nws.send(JSON.stringify({ ...msg, type: 'request_screenshot' }));\nws.send(JSON.stringify({ ...msg, type: 'navigate', url: '\u002Fdashboard' }));\n```\n\n### Response Types\n\n```javascript\n\u002F\u002F UI Tree response\n{ type: 'ui_tree', items: [{ stableId, role, text, label, visible, meta }] }\n\n\u002F\u002F Command success\n{ type: 'command_result', success: true, result: any, duration: 5 }\n\n\u002F\u002F Screenshot\n{ type: 'screenshot', data: 'base64...', width: 1920, height: 1080 }\n\n\u002F\u002F Error\n{ type: 'command_result', success: false, error: { code: 'TARGET_NOT_FOUND', message: '...' } }\n\n\u002F\u002F Network request (auto-streamed)\n{ type: 'network_request', requestId: 'net-1-1234', method: 'POST', url: '\u002Fapi\u002Fusers', initiator: 'fetch' }\n\n\u002F\u002F Network response (auto-streamed)\n{ type: 'network_response', requestId: 'net-1-1234', status: 200, statusText: 'OK', duration: 45, ok: true, body: '{\"id\":1}' }\n\n\u002F\u002F Navigation event (auto-streamed)\n{ type: 'navigation', url: '\u002Fdashboard', previousUrl: '\u002Flogin', trigger: 'pushstate' }\n\n\u002F\u002F Console message (auto-streamed)\n{ type: 'console', level: 'error', args: ['Failed to fetch user', '{\"status\":401}'] }\n```\n\n---\n\n## Example Workflows\n\n### Login Flow\n```\nui                           # Discover form elements\ntype \"email\" \"user@test.com\" # Fill email field\ntype \"password\" \"secret123\"  # Fill password field\nclick \"Sign In\"              # Click submit button\nscreenshot                   # Capture result for verification\n```\n\n### Form Testing\n```\ngo \u002Fregister                 # Navigate to page\nui                           # List interactive elements\ntype 1 \"John\"                # Fill first input by index\ntype 2 \"john@test.com\"       # Fill second input\nclick \"Submit\"               # Submit form\nstate                        # Check localStorage for saved data\n```\n\n### Debugging\n```\nui                           # See current page state\njs localStorage.getItem('token')  # Check auth token\njs window.__REDUX_STATE__    # Inspect app state\nscreenshot                   # Capture for analysis\n```\n\n### API Debugging (Network Capture)\n```\n# Network requests are auto-captured - watch the CLI output:\n# 🌐 [POST] \u002Fapi\u002Flogin\n#    ✓ 200 OK (45ms)\n# 🌐 [GET] \u002Fapi\u002Fusers\u002Fme\n#    ✗ 401 Unauthorized (12ms)\n\n# Navigation is also tracked:\n# 🔀 [pushstate] \u002Fdashboard\n# 🔀 [popstate] \u002Flogin\n```\n\n### Monitoring API Calls\n```javascript\n\u002F\u002F Connect as agent and filter for network events\nws.onmessage = (e) => {\n  const msg = JSON.parse(e.data);\n  if (msg.type === 'network_response' && !msg.ok) {\n    console.log(`API Error: ${msg.status} on request ${msg.requestId}`);\n  }\n  if (msg.type === 'navigation') {\n    console.log(`User navigated to: ${msg.url}`);\n  }\n};\n```\n\n---\n\n## Error Recovery\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| `TARGET_NOT_FOUND` | Element not in DOM | Run `ui` to refresh, verify element exists |\n| `TARGET_NOT_VISIBLE` | Element off-screen | `scroll 0 500` first, then retry |\n| `EVAL_DISABLED` | App disabled eval | Use DOM commands instead |\n| `SCREENSHOT_FAILED` | Modern CSS (oklch) | Use `js` to inspect DOM directly |\n| No connection | Webapp missing SDK | Verify SDK is installed and initialized |\n| Missing network events | SDK config | Check `enableNetwork: true` in config |\n| Missing navigation events | SDK config | Check `enableNavigation: true` in config |\n\n## Telemetry Reference\n\n| Telemetry | Auto-sent | Description |\n|-----------|-----------|-------------|\n| `ui_tree` | On connect + changes | Interactive elements list |\n| `dom_mutations` | Continuous | DOM changes (batched) |\n| `console` | Continuous | Console.log\u002Fwarn\u002Ferror |\n| `error` | On error | Unhandled errors |\n| `network_request` | On fetch\u002FXHR | Outgoing API calls |\n| `network_response` | On response | API responses with status\u002Fbody |\n| `navigation` | On route change | URL changes (push\u002Fpop\u002Freplace\u002Fhash) |\n| `state_update` | On change | Custom app state (if configured) |\n\n## Troubleshooting\n\n```bash\n# Port already in use\nlsof -ti:4000 | xargs kill -9\n\n# Check if server is running\ntmux attach -t debug-*\n\n# View server logs\ntail -f debug-bridge-*.log\n\n# Webapp not connecting?\n# 1. Check URL has ?session=X&port=Y\n# 2. Check browser console for [DebugBridge] logs\n# 3. Verify SDK is imported in dev mode\n```\n",{"name":5,"type":24,"triggers":25,"description":7,"capabilities":33,"default_port":42,"protocol_version":14},"cli-tool",[26,27,28,29,30,31,32],"debug the app","test this flow","click the button","take a screenshot","inspect the UI","capture network requests","monitor navigation",[34,35,36,37,38,39,40,41],"ui_tree","dom_snapshot","console","errors","network","navigation","screenshot","eval",4000,"main","9cf32d1e636db09530158af14ba301bfa5d401e9","skills\u002Fdebug-bridge","https:\u002F\u002Fgithub.com\u002Fstevengonsalvez\u002Fainb-toolkit","https:\u002F\u002Fgithub.com\u002Fstevengonsalvez","stevengonsalvez.com","2026-11-12 00:50:59",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add stevengonsalvez\u002Fainb-toolkit --skill debug-bridge",{"tool":56,"command":57},"bunx","bunx skills add stevengonsalvez\u002Fainb-toolkit --skill debug-bridge",{"tool":59,"command":60},"pnpm","pnpm dlx skills add stevengonsalvez\u002Fainb-toolkit --skill debug-bridge","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstevengonsalvez\u002Fainb-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fdebug-bridge\u002FSKILL.md",true,[64],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"examples\u002Flogin-flow.md","REFERENCE","参考文档",4725,"https:\u002F\u002Fgithub.com\u002Fstevengonsalvez\u002Fainb-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fdebug-bridge\u002Fexamples\u002Flogin-flow.md",[71,78,85,91,98,105],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M75WK9B8DKVJBJJ4CX2QMJMX","well-formed","Fixture skill that satisfies every mechanical rule, used to prove the conformance check passes a clean tree instead of failing everything.","https:\u002F\u002Fgithub.com\u002Fstevengonsalvez\u002Fainb-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagentskills\u002Fclean\u002Fwell-formed\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M75WK6ZGDXJJN8879K49QEYG","underscore-tools","Fixture skill that spells the tool allowlist key with an underscore instead of the hyphen the spec requires.","https:\u002F\u002Fgithub.com\u002Fstevengonsalvez\u002Fainb-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagentskills\u002Fbroken\u002Funderscore-tools\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M75WK524MVT2H9E27ZCEA3HR","no-frontmatter","https:\u002F\u002Fgithub.com\u002Fstevengonsalvez\u002Fainb-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagentskills\u002Fbroken\u002Fno-frontmatter\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M75WJWZBMKR8R60PG3T3MCCC","long-description","Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling. Fixture skill with a deliberately oversized description used to prove the conformance check rejects anything past the 1024 character ceiling.","https:\u002F\u002Fgithub.com\u002Fstevengonsalvez\u002Fainb-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagentskills\u002Fbroken\u002Flong-description\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M75WJVRH3J22WKED7E5D01S8","some-other-name","Fixture skill whose frontmatter name does not match its parent directory name.","https:\u002F\u002Fgithub.com\u002Fstevengonsalvez\u002Fainb-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagentskills\u002Fbroken\u002Fdir-mismatch\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M75WJTC7H5FRP6S129VBSMZC","bad_Name","Fixture skill whose name uses an underscore and a capital letter, so it violates the agentskills.io name pattern.","https:\u002F\u002Fgithub.com\u002Fstevengonsalvez\u002Fainb-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fagentskills\u002Fbroken\u002Fbad_Name\u002FSKILL.md",[],[]]