[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6H6JM1S2XWBZSYFTA45MSJP":3,"skill-same:01M6H6JM1S2XWBZSYFTA45MSJP":89},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M6H6JM1S2XWBZSYFTA45MSJP","gemini-computer-use",null,"Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.","0xharryriddle\u002Fcodex-field-kit","0xharryriddle","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F100945007?v=4","01M6H686JV0QKZYP2RWG6B2B8T","harryriddle","01M6H686PVZ8JGKWEG7B3GM5PD",3,"MIT","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Farchive\u002Fupstream\u002Fexamples\u002Fskills\u002Fgemini-computer-use\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"gemini","Computer Use","gemini computer use","use","computer","for","with","via","control","call","build","confirmation","model","loop","actions","browser","run","tasks","web","playwright","2026-11-10 10:12:30",false,"---\nname: gemini-computer-use\ndescription: Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.\n---\n\n# Gemini Computer Use\n\n## Quick start\n\n1. Source the env file and set your API key:\n\n   ```bash\n   cp env.example env.sh\n   $EDITOR env.sh\n   source env.sh\n   ```\n\n2. Create a virtual environment and install dependencies:\n\n   ```bash\n   python -m venv .venv\n   source .venv\u002Fbin\u002Factivate\n   pip install google-genai playwright\n   playwright install chromium\n   ```\n\n3. Run the agent script with a prompt:\n\n   ```bash\n   python scripts\u002Fcomputer_use_agent.py \\\n     --prompt \"Find the latest blog post title on example.com\" \\\n     --start-url \"https:\u002F\u002Fexample.com\" \\\n     --turn-limit 6\n   ```\n\n## Browser selection\n\n- Default: Playwright's bundled Chromium (no env vars required).\n- Choose a channel (Chrome\u002FEdge) with `COMPUTER_USE_BROWSER_CHANNEL`.\n- Use a custom Chromium-based executable (e.g., Brave) with `COMPUTER_USE_BROWSER_EXECUTABLE`.\n\nIf both are set, `COMPUTER_USE_BROWSER_EXECUTABLE` takes precedence.\n\n## Core workflow (agent loop)\n\n1. Capture a screenshot and send the user goal + screenshot to the model.\n2. Parse `function_call` actions in the response.\n3. Execute each action in Playwright.\n4. If a `safety_decision` is `require_confirmation`, prompt the user before executing.\n5. Send `function_response` objects containing the latest URL + screenshot.\n6. Repeat until the model returns only text (no actions) or you hit the turn limit.\n\n## Operational guidance\n\n- Run in a sandboxed browser profile or container.\n- Use `--exclude` to block risky actions you do not want the model to take.\n- Keep the viewport at 1440x900 unless you have a reason to change it.\n\n## Resources\n\n- Script: `scripts\u002Fcomputer_use_agent.py`\n- Reference notes: `references\u002Fgoogle-computer-use.md`\n- Env template: `env.example`\n","# Gemini Computer Use\n\n## Quick start\n\n1. Source the env file and set your API key:\n\n   ```bash\n   cp env.example env.sh\n   $EDITOR env.sh\n   source env.sh\n   ```\n\n2. Create a virtual environment and install dependencies:\n\n   ```bash\n   python -m venv .venv\n   source .venv\u002Fbin\u002Factivate\n   pip install google-genai playwright\n   playwright install chromium\n   ```\n\n3. Run the agent script with a prompt:\n\n   ```bash\n   python scripts\u002Fcomputer_use_agent.py \\\n     --prompt \"Find the latest blog post title on example.com\" \\\n     --start-url \"https:\u002F\u002Fexample.com\" \\\n     --turn-limit 6\n   ```\n\n## Browser selection\n\n- Default: Playwright's bundled Chromium (no env vars required).\n- Choose a channel (Chrome\u002FEdge) with `COMPUTER_USE_BROWSER_CHANNEL`.\n- Use a custom Chromium-based executable (e.g., Brave) with `COMPUTER_USE_BROWSER_EXECUTABLE`.\n\nIf both are set, `COMPUTER_USE_BROWSER_EXECUTABLE` takes precedence.\n\n## Core workflow (agent loop)\n\n1. Capture a screenshot and send the user goal + screenshot to the model.\n2. Parse `function_call` actions in the response.\n3. Execute each action in Playwright.\n4. If a `safety_decision` is `require_confirmation`, prompt the user before executing.\n5. Send `function_response` objects containing the latest URL + screenshot.\n6. Repeat until the model returns only text (no actions) or you hit the turn limit.\n\n## Operational guidance\n\n- Run in a sandboxed browser profile or container.\n- Use `--exclude` to block risky actions you do not want the model to take.\n- Keep the viewport at 1440x900 unless you have a reason to change it.\n\n## Resources\n\n- Script: `scripts\u002Fcomputer_use_agent.py`\n- Reference notes: `references\u002Fgoogle-computer-use.md`\n- Env template: `env.example`\n",{"name":5,"description":7},"main","6c13f6f4ac5a3bc1e6b78cd2bb1704f122c4a73e","archive\u002Fupstream\u002Fexamples\u002Fskills\u002Fgemini-computer-use",0,"https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit","https:\u002F\u002Fgithub.com\u002F0xharryriddle","https:\u002F\u002Fharryriddle.vercel.app","2026-04-11 11:49:51",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add 0xharryriddle\u002Fcodex-field-kit --skill gemini-computer-use",{"tool":63,"command":64},"bunx","bunx skills add 0xharryriddle\u002Fcodex-field-kit --skill gemini-computer-use",{"tool":66,"command":67},"pnpm","pnpm dlx skills add 0xharryriddle\u002Fcodex-field-kit --skill gemini-computer-use","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Farchive\u002Fupstream\u002Fexamples\u002Fskills\u002Fgemini-computer-use\u002FSKILL.md",true,[71,77,83],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"env.example","OTHER","其他",409,"https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Farchive\u002Fupstream\u002Fexamples\u002Fskills\u002Fgemini-computer-use\u002Fenv.example",{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fgoogle-computer-use.md","REFERENCE","参考文档",636,"https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Farchive\u002Fupstream\u002Fexamples\u002Fskills\u002Fgemini-computer-use\u002Freferences\u002Fgoogle-computer-use.md",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fcomputer_use_agent.py","SCRIPT","脚本",11557,"https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Farchive\u002Fupstream\u002Fexamples\u002Fskills\u002Fgemini-computer-use\u002Fscripts\u002Fcomputer_use_agent.py",[90,119,137,147,172,196],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":99,"publishedAt":44},"01M6H7ZKE6MR33HC84QZ1TA6MV","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-react-best-practices\u002FSKILL.md",[96],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[100,101,102,103,104,41,105,106,107,108,109,110,111,112,113,114,115,116,117,118],"react best practices","react","vercel react best practices","best practices","vercel","data fetching","triggers","pages","next","performance optimization","refactoring","Next.js","Optimization","code","guidelines","react components","components","performance","writing",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":44},"01M6H7ZGC2WK8SEKYHWDNTMDA9","swarm-planner","[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fswarm-planner\u002FSKILL.md",[],[126,127,128,129,130,131,132,133,134,29,135,136],"swarm","swarm planner","planner","parallel","multi-agent","only","execution","plans","dependency","multi","implementation",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":44},"01M6H7ZD93853RZCYQWH1D38TM","super-swarm-spark","Only to be triggered by explicit super-swarm-spark commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fsuper-swarm-spark\u002FSKILL.md",[],[144,126,145,131,146],"super swarm spark","spark","commands",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":44},"01M6H7Z987QBY49JCCPT953EAZ","role-creator","Create and install Codex custom agent roles in ~\u002F.codex\u002Fconfig.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Frole-creator\u002FSKILL.md",[],[154,155,156,157,158,159,160,161,162,163,164,36,165,166,167,168,169,170,171],"role","creator","role creator","keys","users","roles","toml","enforce","install","guide","instructions","developer","reasoning","generate","create","config","codex","files",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":179,"publishedAt":44},"01M6H7Z5TRPMDQ7YSZQXPN1G60","read-github","Read and search GitHub repository documentation via gitmcp.io MCP service.\n\n**WHEN TO USE:**\n- User provides a GitHub URL\n- User mentions a specific repo in owner\u002Frepo format\n- User asks \"what does this repo do?\", \"read the docs for X repo\", or similar\n- User wants to search code or docs within a repo","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fread-github\u002FSKILL.md",[178],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[180,181,182,113,183,184,185,186,29,187,188,31,189,190,191,27,192,193,194,195],"github","read github","read","documentation","docs","MCP","search","when to use","URL","io","service","do","user","repo","format","repository",{"skillNo":197,"name":128,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":201,"publishedAt":44},"01M6H7Z215CTKYJ4Y1X6EQWN6M","Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: \"make a plan\", \"create a plan\", \"plan this out\", \"plan the implementation\", \"help me plan\", \"design a plan\", \"draft a plan\", \"write a plan\", \"outline the steps\", \"break this down into tasks\", \"what's the plan for\", or any similar planning request. Also triggers on explicit \"\u002Fplanner\" or \"\u002Fplan\" commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fplanner\u002FSKILL.md",[],[128,202,29,203,30,204,106,133,146,205,206,27,207,208,209,210,211,168,41,212],"outline","atomic","sprints","draft","me","write","phased implementation","plan","help","planning","design"]