[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GSSE11WGDMMNTBQ9A95FP1":3,"skill-same:01M6GSSE11WGDMMNTBQ9A95FP1":88},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6GSSE11WGDMMNTBQ9A95FP1","ck:agent-browser",null,"AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).","yosnap\u002Fdevdock","yosnap","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F66257788?v=4","01M6GSRTCX7DZKZ29PPYZNEFQG","Paulo Guachizaca","01M6GSRTH6M80S52Z0FSXKVYK4",6,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fagent-browser\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"ck:agent browser","agent browser","browser","context","recording","URL","browserbase","long","self","snapshots","use","autonomous","testing","Video","browser testing","sessions","workflows","automation","browser automation","cli","2026-11-10 10:12:30",false,"---\nname: ck:agent-browser\ndescription: AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).\nlicense: Apache-2.0\nargument-hint: \"[url or task]\"\n---\n\n# agent-browser Skill\n\nBrowser automation CLI designed for AI agents. Uses \"snapshot + refs\" paradigm for 93% less context than Playwright MCP.\n\n## Quick Start\n\n```bash\n# Install globally\nnpm install -g agent-browser\n\n# Download Chromium (one-time)\nagent-browser install\n\n# Linux: include system deps\nagent-browser install --with-deps\n\n# Verify\nagent-browser --version\n```\n\n## Core Workflow\n\nThe 4-step pattern for all browser automation:\n\n```bash\n# 1. Navigate\nagent-browser open https:\u002F\u002Fexample.com\n\n# 2. Snapshot (get interactive elements with refs)\nagent-browser snapshot -i\n# Output: button \"Sign In\" @e1, textbox \"Email\" @e2, ...\n\n# 3. Interact using refs\nagent-browser fill @e2 \"user@example.com\"\nagent-browser click @e1\n\n# 4. Re-snapshot after page changes\nagent-browser snapshot -i\n```\n\n## When to Use (vs chrome-devtools)\n\n| Use agent-browser | Use chrome-devtools |\n|-------------------|---------------------|\n| Long autonomous AI sessions | Quick one-off screenshots |\n| Context-constrained workflows | Custom Puppeteer scripts needed |\n| Video recording for debugging | WebSocket full frame debugging |\n| Cloud browsers (Browserbase) | Existing workflow integration |\n| Multi-tab handling | Need Sharp auto-compression |\n| Self-verifying build loops | Session with auth injection |\n\n**Token efficiency:** ~280 chars\u002Fsnapshot vs 8K+ for Playwright MCP.\n\n## Command Reference\n\n### Navigation\n```bash\nagent-browser open \u003Curl>       # Navigate to URL\nagent-browser back             # Go back\nagent-browser forward          # Go forward\nagent-browser reload           # Reload page\nagent-browser close            # Close browser\n```\n\n### Analysis (Snapshot)\n```bash\nagent-browser snapshot         # Full accessibility tree\nagent-browser snapshot -i      # Interactive elements only (recommended)\nagent-browser snapshot -c      # Compact output\nagent-browser snapshot -d 3    # Limit depth\nagent-browser snapshot -s \"nav\" # Scope to CSS selector\n```\n\n### Interactions (use @refs from snapshot)\n```bash\nagent-browser click @e1        # Click element\nagent-browser dblclick @e1     # Double-click\nagent-browser fill @e2 \"text\"  # Clear and fill input\nagent-browser type @e2 \"text\"  # Type without clearing\nagent-browser press Enter      # Press key\nagent-browser hover @e1        # Hover over element\nagent-browser check @e3        # Check checkbox\nagent-browser uncheck @e3      # Uncheck checkbox\nagent-browser select @e4 \"opt\" # Select dropdown option\nagent-browser scroll @e1       # Scroll element into view\nagent-browser scroll down 500  # Scroll page by pixels\nagent-browser drag @e1 @e2     # Drag from e1 to e2\nagent-browser upload @e5 file.pdf  # Upload file\n```\n\n### Information Retrieval\n```bash\nagent-browser get text @e1     # Get text content\nagent-browser get html @e1     # Get HTML\nagent-browser get value @e2    # Get input value\nagent-browser get attr @e1 href  # Get attribute\nagent-browser get title        # Page title\nagent-browser get url          # Current URL\nagent-browser get count \"li\"   # Count elements\nagent-browser get box @e1      # Bounding box\n```\n\n### State Checks\n```bash\nagent-browser is visible @e1   # Check visibility\nagent-browser is enabled @e1   # Check if enabled\nagent-browser is checked @e3   # Check if checked\n```\n\n### Media\n```bash\nagent-browser screenshot           # Capture viewport\nagent-browser screenshot --full    # Full page\nagent-browser screenshot -o ss.png # Save to file\nagent-browser pdf -o page.pdf      # Export PDF\nagent-browser record start         # Start video recording\nagent-browser record stop          # Stop and save video\nagent-browser record restart       # Restart recording\n```\n\n### Wait Conditions\n```bash\nagent-browser wait @e1                    # Wait for element\nagent-browser wait --text \"Success\"       # Wait for text to appear\nagent-browser wait --url \"\u002Fdashboard\"     # Wait for URL pattern\nagent-browser wait --load                 # Wait for page load\nagent-browser wait --idle                 # Wait for network idle\nagent-browser wait --fn \"() => window.ready\"  # Wait for JS condition\n```\n\n### Browser Configuration\n```bash\nagent-browser viewport 1920 1080   # Set viewport size\nagent-browser device \"iPhone 14\"   # Emulate device\nagent-browser geolocation 40.7 -74.0  # Set geolocation\nagent-browser offline true         # Enable offline mode\nagent-browser headers '{\"X-Custom\":\"val\"}'  # Set headers\nagent-browser credentials user pass  # HTTP auth\nagent-browser color-scheme dark    # Set color scheme\n```\n\n### Storage Management\n```bash\nagent-browser cookies              # List cookies\nagent-browser cookies set name=val # Set cookie\nagent-browser cookies clear        # Clear cookies\nagent-browser storage local        # Get localStorage\nagent-browser storage session      # Get sessionStorage\nagent-browser state save auth.json # Save browser state\nagent-browser state load auth.json # Load browser state\n```\n\n### Network Control\n```bash\nagent-browser network route \"**\u002F*.jpg\" --abort    # Block requests\nagent-browser network route \"**\u002Fapi\u002F*\" --body '{\"data\":[]}'  # Mock response\nagent-browser network unroute \"**\u002F*.jpg\"          # Remove specific route\nagent-browser network requests                    # List intercepted requests\n```\n\n### Semantic Finding\n```bash\nagent-browser find role button           # Find by ARIA role\nagent-browser find text \"Submit\"         # Find by text content\nagent-browser find label \"Email\"         # Find by label\nagent-browser find placeholder \"Search\"  # Find by placeholder\nagent-browser find testid \"login-btn\"    # Find by data-testid\nagent-browser find first \"button\"        # First matching element\nagent-browser find last \"li\"             # Last matching element\nagent-browser find nth 2 \"li\"            # Nth element (0-indexed)\n```\n\n### Advanced\n```bash\nagent-browser tabs                 # List tabs\nagent-browser tab new              # New tab\nagent-browser tab 2                # Switch to tab\nagent-browser tab close            # Close current tab\nagent-browser frame 0              # Switch to frame\nagent-browser dialog accept        # Accept dialog\nagent-browser dialog dismiss       # Dismiss dialog\nagent-browser eval \"document.title\"  # Execute JS\nagent-browser highlight @e1        # Highlight element visually\nagent-browser mouse move 100 200   # Move mouse to coordinates\nagent-browser mouse down           # Mouse button down\nagent-browser mouse up             # Mouse button up\n```\n\n## Global Options\n\n| Option | Description |\n|--------|-------------|\n| `--session \u003Cname>` | Named session for parallel testing |\n| `--json` | JSON output for parsing |\n| `--headed` | Show browser window |\n| `--cdp \u003Cport>` | Connect via Chrome DevTools Protocol |\n| `-p \u003Cprovider>` | Cloud browser provider |\n| `--proxy \u003Curl>` | Proxy server |\n| `--headers \u003Cjson>` | Custom HTTP headers |\n| `--executable-path` | Custom browser binary |\n| `--extension \u003Cpath>` | Load browser extension |\n\n## Environment Variables\n\n| Variable | Description |\n|----------|-------------|\n| `AGENT_BROWSER_SESSION` | Default session name |\n| `AGENT_BROWSER_PROVIDER` | Cloud provider (e.g., browserbase) |\n| `AGENT_BROWSER_EXECUTABLE_PATH` | Browser binary location |\n| `AGENT_BROWSER_EXTENSIONS` | Comma-separated extension paths |\n| `AGENT_BROWSER_STREAM_PORT` | WebSocket streaming port |\n| `AGENT_BROWSER_HOME` | Custom installation directory |\n| `AGENT_BROWSER_PROFILE` | Browser profile directory |\n| `BROWSERBASE_API_KEY` | Browserbase API key |\n| `BROWSERBASE_PROJECT_ID` | Browserbase project ID |\n\n## Common Patterns\n\n### Form Submission\n```bash\nagent-browser open https:\u002F\u002Fexample.com\u002Flogin\nagent-browser snapshot -i\nagent-browser fill @e1 \"user@example.com\"\nagent-browser fill @e2 \"password123\"\nagent-browser click @e3  # Submit button\nagent-browser wait url \"\u002Fdashboard\"\n```\n\n### State Persistence (Auth)\n```bash\n# Save authenticated state\nagent-browser open https:\u002F\u002Fexample.com\u002Flogin\n# ... login steps ...\nagent-browser state save auth.json\n\n# Reuse in future sessions\nagent-browser state load auth.json\nagent-browser open https:\u002F\u002Fexample.com\u002Fdashboard\n```\n\n### Video Recording (Debugging)\n```bash\nagent-browser open https:\u002F\u002Fexample.com\nagent-browser record start\n# ... perform actions ...\nagent-browser record stop  # Saves to recording.webm\n```\n\n### Parallel Sessions\n```bash\n# Terminal 1\nagent-browser --session test1 open https:\u002F\u002Fexample.com\n\n# Terminal 2\nagent-browser --session test2 open https:\u002F\u002Fexample.com\n```\n\n## Cloud Browsers (Browserbase)\n\nFor CI\u002FCD or environments without local browser:\n\n```bash\n# Set credentials\nexport BROWSERBASE_API_KEY=\"your-api-key\"\nexport BROWSERBASE_PROJECT_ID=\"your-project-id\"\n\n# Use cloud browser\nagent-browser -p browserbase open https:\u002F\u002Fexample.com\n```\n\nSee `references\u002Fbrowserbase-cloud-setup.md` for detailed setup.\n\n## Troubleshooting\n\n| Issue | Solution |\n|-------|----------|\n| Command not found | Run `npm install -g agent-browser` |\n| Chromium missing | Run `agent-browser install` |\n| Linux deps missing | Run `agent-browser install --with-deps` |\n| Session stale | Close browser: `agent-browser close` |\n| Element not found | Re-run `snapshot -i` after page changes |\n\n## Resources\n\n- [GitHub Repository](https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Fagent-browser)\n- [Official Documentation](https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Fagent-browser#readme)\n- [Browserbase Docs](https:\u002F\u002Fdocs.browserbase.com\u002F)\n","# agent-browser Skill\n\nBrowser automation CLI designed for AI agents. Uses \"snapshot + refs\" paradigm for 93% less context than Playwright MCP.\n\n## Quick Start\n\n```bash\n# Install globally\nnpm install -g agent-browser\n\n# Download Chromium (one-time)\nagent-browser install\n\n# Linux: include system deps\nagent-browser install --with-deps\n\n# Verify\nagent-browser --version\n```\n\n## Core Workflow\n\nThe 4-step pattern for all browser automation:\n\n```bash\n# 1. Navigate\nagent-browser open https:\u002F\u002Fexample.com\n\n# 2. Snapshot (get interactive elements with refs)\nagent-browser snapshot -i\n# Output: button \"Sign In\" @e1, textbox \"Email\" @e2, ...\n\n# 3. Interact using refs\nagent-browser fill @e2 \"user@example.com\"\nagent-browser click @e1\n\n# 4. Re-snapshot after page changes\nagent-browser snapshot -i\n```\n\n## When to Use (vs chrome-devtools)\n\n| Use agent-browser | Use chrome-devtools |\n|-------------------|---------------------|\n| Long autonomous AI sessions | Quick one-off screenshots |\n| Context-constrained workflows | Custom Puppeteer scripts needed |\n| Video recording for debugging | WebSocket full frame debugging |\n| Cloud browsers (Browserbase) | Existing workflow integration |\n| Multi-tab handling | Need Sharp auto-compression |\n| Self-verifying build loops | Session with auth injection |\n\n**Token efficiency:** ~280 chars\u002Fsnapshot vs 8K+ for Playwright MCP.\n\n## Command Reference\n\n### Navigation\n```bash\nagent-browser open \u003Curl>       # Navigate to URL\nagent-browser back             # Go back\nagent-browser forward          # Go forward\nagent-browser reload           # Reload page\nagent-browser close            # Close browser\n```\n\n### Analysis (Snapshot)\n```bash\nagent-browser snapshot         # Full accessibility tree\nagent-browser snapshot -i      # Interactive elements only (recommended)\nagent-browser snapshot -c      # Compact output\nagent-browser snapshot -d 3    # Limit depth\nagent-browser snapshot -s \"nav\" # Scope to CSS selector\n```\n\n### Interactions (use @refs from snapshot)\n```bash\nagent-browser click @e1        # Click element\nagent-browser dblclick @e1     # Double-click\nagent-browser fill @e2 \"text\"  # Clear and fill input\nagent-browser type @e2 \"text\"  # Type without clearing\nagent-browser press Enter      # Press key\nagent-browser hover @e1        # Hover over element\nagent-browser check @e3        # Check checkbox\nagent-browser uncheck @e3      # Uncheck checkbox\nagent-browser select @e4 \"opt\" # Select dropdown option\nagent-browser scroll @e1       # Scroll element into view\nagent-browser scroll down 500  # Scroll page by pixels\nagent-browser drag @e1 @e2     # Drag from e1 to e2\nagent-browser upload @e5 file.pdf  # Upload file\n```\n\n### Information Retrieval\n```bash\nagent-browser get text @e1     # Get text content\nagent-browser get html @e1     # Get HTML\nagent-browser get value @e2    # Get input value\nagent-browser get attr @e1 href  # Get attribute\nagent-browser get title        # Page title\nagent-browser get url          # Current URL\nagent-browser get count \"li\"   # Count elements\nagent-browser get box @e1      # Bounding box\n```\n\n### State Checks\n```bash\nagent-browser is visible @e1   # Check visibility\nagent-browser is enabled @e1   # Check if enabled\nagent-browser is checked @e3   # Check if checked\n```\n\n### Media\n```bash\nagent-browser screenshot           # Capture viewport\nagent-browser screenshot --full    # Full page\nagent-browser screenshot -o ss.png # Save to file\nagent-browser pdf -o page.pdf      # Export PDF\nagent-browser record start         # Start video recording\nagent-browser record stop          # Stop and save video\nagent-browser record restart       # Restart recording\n```\n\n### Wait Conditions\n```bash\nagent-browser wait @e1                    # Wait for element\nagent-browser wait --text \"Success\"       # Wait for text to appear\nagent-browser wait --url \"\u002Fdashboard\"     # Wait for URL pattern\nagent-browser wait --load                 # Wait for page load\nagent-browser wait --idle                 # Wait for network idle\nagent-browser wait --fn \"() => window.ready\"  # Wait for JS condition\n```\n\n### Browser Configuration\n```bash\nagent-browser viewport 1920 1080   # Set viewport size\nagent-browser device \"iPhone 14\"   # Emulate device\nagent-browser geolocation 40.7 -74.0  # Set geolocation\nagent-browser offline true         # Enable offline mode\nagent-browser headers '{\"X-Custom\":\"val\"}'  # Set headers\nagent-browser credentials user pass  # HTTP auth\nagent-browser color-scheme dark    # Set color scheme\n```\n\n### Storage Management\n```bash\nagent-browser cookies              # List cookies\nagent-browser cookies set name=val # Set cookie\nagent-browser cookies clear        # Clear cookies\nagent-browser storage local        # Get localStorage\nagent-browser storage session      # Get sessionStorage\nagent-browser state save auth.json # Save browser state\nagent-browser state load auth.json # Load browser state\n```\n\n### Network Control\n```bash\nagent-browser network route \"**\u002F*.jpg\" --abort    # Block requests\nagent-browser network route \"**\u002Fapi\u002F*\" --body '{\"data\":[]}'  # Mock response\nagent-browser network unroute \"**\u002F*.jpg\"          # Remove specific route\nagent-browser network requests                    # List intercepted requests\n```\n\n### Semantic Finding\n```bash\nagent-browser find role button           # Find by ARIA role\nagent-browser find text \"Submit\"         # Find by text content\nagent-browser find label \"Email\"         # Find by label\nagent-browser find placeholder \"Search\"  # Find by placeholder\nagent-browser find testid \"login-btn\"    # Find by data-testid\nagent-browser find first \"button\"        # First matching element\nagent-browser find last \"li\"             # Last matching element\nagent-browser find nth 2 \"li\"            # Nth element (0-indexed)\n```\n\n### Advanced\n```bash\nagent-browser tabs                 # List tabs\nagent-browser tab new              # New tab\nagent-browser tab 2                # Switch to tab\nagent-browser tab close            # Close current tab\nagent-browser frame 0              # Switch to frame\nagent-browser dialog accept        # Accept dialog\nagent-browser dialog dismiss       # Dismiss dialog\nagent-browser eval \"document.title\"  # Execute JS\nagent-browser highlight @e1        # Highlight element visually\nagent-browser mouse move 100 200   # Move mouse to coordinates\nagent-browser mouse down           # Mouse button down\nagent-browser mouse up             # Mouse button up\n```\n\n## Global Options\n\n| Option | Description |\n|--------|-------------|\n| `--session \u003Cname>` | Named session for parallel testing |\n| `--json` | JSON output for parsing |\n| `--headed` | Show browser window |\n| `--cdp \u003Cport>` | Connect via Chrome DevTools Protocol |\n| `-p \u003Cprovider>` | Cloud browser provider |\n| `--proxy \u003Curl>` | Proxy server |\n| `--headers \u003Cjson>` | Custom HTTP headers |\n| `--executable-path` | Custom browser binary |\n| `--extension \u003Cpath>` | Load browser extension |\n\n## Environment Variables\n\n| Variable | Description |\n|----------|-------------|\n| `AGENT_BROWSER_SESSION` | Default session name |\n| `AGENT_BROWSER_PROVIDER` | Cloud provider (e.g., browserbase) |\n| `AGENT_BROWSER_EXECUTABLE_PATH` | Browser binary location |\n| `AGENT_BROWSER_EXTENSIONS` | Comma-separated extension paths |\n| `AGENT_BROWSER_STREAM_PORT` | WebSocket streaming port |\n| `AGENT_BROWSER_HOME` | Custom installation directory |\n| `AGENT_BROWSER_PROFILE` | Browser profile directory |\n| `BROWSERBASE_API_KEY` | Browserbase API key |\n| `BROWSERBASE_PROJECT_ID` | Browserbase project ID |\n\n## Common Patterns\n\n### Form Submission\n```bash\nagent-browser open https:\u002F\u002Fexample.com\u002Flogin\nagent-browser snapshot -i\nagent-browser fill @e1 \"user@example.com\"\nagent-browser fill @e2 \"password123\"\nagent-browser click @e3  # Submit button\nagent-browser wait url \"\u002Fdashboard\"\n```\n\n### State Persistence (Auth)\n```bash\n# Save authenticated state\nagent-browser open https:\u002F\u002Fexample.com\u002Flogin\n# ... login steps ...\nagent-browser state save auth.json\n\n# Reuse in future sessions\nagent-browser state load auth.json\nagent-browser open https:\u002F\u002Fexample.com\u002Fdashboard\n```\n\n### Video Recording (Debugging)\n```bash\nagent-browser open https:\u002F\u002Fexample.com\nagent-browser record start\n# ... perform actions ...\nagent-browser record stop  # Saves to recording.webm\n```\n\n### Parallel Sessions\n```bash\n# Terminal 1\nagent-browser --session test1 open https:\u002F\u002Fexample.com\n\n# Terminal 2\nagent-browser --session test2 open https:\u002F\u002Fexample.com\n```\n\n## Cloud Browsers (Browserbase)\n\nFor CI\u002FCD or environments without local browser:\n\n```bash\n# Set credentials\nexport BROWSERBASE_API_KEY=\"your-api-key\"\nexport BROWSERBASE_PROJECT_ID=\"your-project-id\"\n\n# Use cloud browser\nagent-browser -p browserbase open https:\u002F\u002Fexample.com\n```\n\nSee `references\u002Fbrowserbase-cloud-setup.md` for detailed setup.\n\n## Troubleshooting\n\n| Issue | Solution |\n|-------|----------|\n| Command not found | Run `npm install -g agent-browser` |\n| Chromium missing | Run `agent-browser install` |\n| Linux deps missing | Run `agent-browser install --with-deps` |\n| Session stale | Close browser: `agent-browser close` |\n| Element not found | Re-run `snapshot -i` after page changes |\n\n## Resources\n\n- [GitHub Repository](https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Fagent-browser)\n- [Official Documentation](https:\u002F\u002Fgithub.com\u002Fvercel-labs\u002Fagent-browser#readme)\n- [Browserbase Docs](https:\u002F\u002Fdocs.browserbase.com\u002F)\n",{"name":5,"license":15,"description":7,"argument-hint":52},"[url or task]","main","564d425e7432c375e7fe7e0de9fc079d03078178",".claude\u002Fskills\u002Fagent-browser",4,"https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock","https:\u002F\u002Fgithub.com\u002Fyosnap","2026-05-20 17:03:32",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add yosnap\u002Fdevdock --skill \"ck:agent-browser\"",{"tool":66,"command":67},"bunx","bunx skills add yosnap\u002Fdevdock --skill \"ck:agent-browser\"",{"tool":69,"command":70},"pnpm","pnpm dlx skills add yosnap\u002Fdevdock --skill \"ck:agent-browser\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fagent-browser\u002FSKILL.md",true,[74,80,84],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002F.gitkeep","REFERENCE","参考文档",0,"https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fagent-browser\u002Freferences\u002F.gitkeep",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fagent-browser-vs-chrome-devtools.md",3832,"https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fagent-browser\u002Freferences\u002Fagent-browser-vs-chrome-devtools.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fbrowserbase-cloud-setup.md",4000,"https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fagent-browser\u002Freferences\u002Fbrowserbase-cloud-setup.md",[89,115,141,175,202,224],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":98,"publishedAt":47},"01M6GTDPSDZFE0XCFKBK39BT2J","ck:web-testing","Web testing with Playwright, Vitest, k6. E2E\u002Funit\u002Fintegration\u002Fload\u002Fsecurity\u002Fvisual\u002Fa11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.","https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fweb-testing\u002FSKILL.md",[95],{"categoryNo":96,"categoryName":97,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[39,99,100,101,102,103,44,104,29,105,106,107,37,108,109,110,111,112,113,114],"web","web testing","ck:web testing","security","gestures","core","k6","e2e","vitest","mobile","visual","type","web vitals","unit","load","cross-browser",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":47},"01M6GTDJ0QR9Z531TG8C3B2GN3","ck:web-frameworks","Build with Next.js (App Router, RSC, SSR, ISR), Turborepo monorepos. Use for React apps, server rendering, build optimization, caching strategies, shared dependencies.","MIT","https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fweb-frameworks\u002FSKILL.md",[],[99,123,124,125,126,127,128,129,130,131,37,132,133,134,135,136,137,138,139,140],"web frameworks","frameworks","ck:web frameworks","react","ssr","framework","server","turborepo","Optimization","router","next","caching","strategies","shared","feature","app","apps","rendering",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":155,"publishedAt":47},"01M6GTCPB9F326DAZ9RRXEB9J9","ck:ui-styling","Style UIs with shadcn\u002Fui components (Radix UI + Tailwind CSS). Use for accessible components, themes, dark mode, responsive layouts, design systems, color customization.","https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fui-styling\u002FSKILL.md",[147,150],{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":151,"categoryName":152,"taxonomyType":153,"taxonomyTypeDesc":154},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[156,157,158,159,160,161,162,163,164,165,166,167,37,168,169,170,171,172,173,174],"ui styling","ui","styling","ck:ui styling","design","css","components","component","design systems","shadcn","Tailwind","radix ui","responsive","layout","dark mode","ui components","themes","color","mode",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":184,"publishedAt":47},"01M6GTCF8WB87S84M4EQZVCRDG","ck:threejs","Build 3D web apps with Three.js (WebGL\u002FWebGPU). 556 searchable examples, 60 API classes, 20 use cases. Actions: create 3D scene, load model, add animation, implement physics, build VR\u002FXR. Topics: GLTF loader, PBR materials, particle effects, shadows, post-processing, compute shaders, TSL. Integrations: WebGPU, physics engines, spatial audio.","https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fthreejs\u002FSKILL.md",[181],{"categoryNo":182,"categoryName":183,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[185,177,186,187,188,189,190,191,192,193,194,195,196,197,137,139,198,199,200,201],"threejs","webgpu","create","shaders","actions","api","Animation","3D","Audio","model","integrations","three","physics","add","processing","post-processing","vr",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":47},"01M6GTBBA0E5D1CVZZTFG4HPV3","ck:sequential-thinking","Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition, course correction.","https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fsequential-thinking\u002FSKILL.md",[],[209,210,211,212,213,214,215,216,217,37,218,219,220,221,222,223],"sequential thinking","thinking","ck:sequential thinking","planning","reasoning","verification","hypothesis","analysis","analyze","decomposition","problem","multi","with","course","revision",{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":233,"publishedAt":47},"01M6GTB26Y169PZFEX59Q9KM7F","ck:research","Research technical solutions, analyze architectures, gather requirements thoroughly. Use for technology evaluation, best practices research, solution design, scalability\u002Fsecurity\u002Fmaintainability analysis.","https:\u002F\u002Fgithub.com\u002Fyosnap\u002Fdevdock\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fresearch\u002FSKILL.md",[230],{"categoryNo":231,"categoryName":232,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[234,226,160,102,235,236,216,217,237,37,238,239,240,241,242],"research","best practices","Evaluation","technical","scalability","technology","requirements","maintainability","architectures"]