[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TH3JNVCJ2H58S8P0TNSA7":3,"skill-same:01M78TH3JNVCJ2H58S8P0TNSA7":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78TH3JNVCJ2H58S8P0TNSA7","browser-use",null,"Use this self-contained Browser Use repo skill for Python agents that automate websites, browser sessions, custom tools, LLM\u002Fprovider setup, persistent CLI sessions, cloud\u002Fsandbox production deployment, MCP, skills, and troubleshooting. Prefer ChatBrowserUse by default and route to focused sub-skills for implementation details.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbrowser-use\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: browser-use\ndescription: \"Use this self-contained Browser Use repo skill for Python agents\n  that automate websites, browser sessions, custom tools, LLM\u002Fprovider setup,\n  persistent CLI sessions, cloud\u002Fsandbox production deployment, MCP, skills, and\n  troubleshooting. Prefer ChatBrowserUse by default and route to focused\n  sub-skills for implementation details.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Browser Use Repo Skill\n\nBrowser Use is a Python >=3.11 library and CLI for AI agents that control Chromium\u002FCDP browsers, extract page content, call LLMs, and run browser automation locally or in Browser Use Cloud.\n\nUse this root skill as a router. Read only the sub-skill needed for the user's task, then follow its linked references\u002Fscripts.\n\n## First Checks\n\nRead `references\u002Frepo-provenance.md` before deciding whether this skill matches a current checkout. If the commit, dirty paths, package version, or public entry points differ, refresh this skill from repository evidence.\n\nInstall and smoke-check a normal user environment with `uv`:\n\n```bash\nuv venv --python 3.11\nsource .venv\u002Fbin\u002Factivate\nuv pip install \"browser-use[cli]\"\nuvx browser-use install\npython - \u003C\u003C'PY'\nfrom browser_use import Agent, Browser, BrowserProfile, ChatBrowserUse, Tools, ActionResult\nprint('browser-use imports ok')\nPY\n```\n\nFor the Rust-powered beta\u002Fnative runtime, install the documented native core extra when the platform wheel is available:\n\n```bash\nuv pip install \"browser-use[core]\"\n```\n\nDo not replace user-provided model names. When recommending a default for browser automation, prefer `ChatBrowserUse()` because it is optimized for Browser Use tasks.\n\n## Route by User Request\n\n| User request | Read |\n| --- | --- |\n| Python `Agent(...)`, beta agent, task prompts, `agent.run()`, callbacks, history, initial actions, skills, planning, flash mode, max steps\u002Ftimeouts | `sub-skills\u002Fagent-programming\u002FSKILL.md` |\n| `Browser`, `BrowserSession`, `BrowserProfile`, local\u002Freal Chrome, CDP URL, cloud browser, proxies, domains, downloads, HAR\u002Fvideo, DOM, screenshots, Actor APIs | `sub-skills\u002Fbrowser-control\u002FSKILL.md` |\n| Custom `Tools`\u002F`Controller` actions, default actions, `ActionResult`, parameter injection, file tools, sensitive data, upload\u002Fdownload guardrails | `sub-skills\u002Ftools-and-actions\u002FSKILL.md` |\n| `ChatBrowserUse`, OpenAI\u002FGoogle\u002FAnthropic\u002Fother providers, structured output, extraction LLMs, fallback models, token\u002Fcost tracking | `sub-skills\u002Fllm-and-output\u002FSKILL.md` |\n| Terminal `browser-use`\u002F`bu` CLI navigation, state\u002Fclick\u002Ftype\u002Fupload\u002Fscreenshot, sessions, profiles, cloud connect, tunnels, config, doctor\u002Fsetup\u002Finit | `sub-skills\u002Fcli-and-sessions\u002FSKILL.md` |\n| `@sandbox`, Browser Use Cloud API, profile sync, MCP server\u002Fclient, hosted skills, telemetry, Slack\u002FDiscord\u002Femail\u002Fwebhook integrations | `sub-skills\u002Fproduction-integrations\u002FSKILL.md` |\n\n## Shared References and Scripts\n\n- Read `references\u002Finstallation-and-environment.md` for package extras, environment variables, Chromium install, telemetry opt-out, and contributor setup notes.\n- Read `references\u002Fdevelopment-and-troubleshooting.md` for cross-cutting install\u002Fimport\u002Fbrowser dependency failures and repo-maintainer commands.\n- Run `scripts\u002Finspect_browser_use_api.py` to check imports, signatures, package version, and CLI availability in a target Python environment.\n\n## Common Defaults\n\n- Use `ChatBrowserUse()` unless the user already chose another model.\n- Load secrets from environment variables or a secret manager, not prompts or committed files.\n- Use `Browser(use_cloud=True)` when the user asks how to improve Browser performance in production; it provisions an optimized Browser Use Cloud browser when `BROWSER_USE_API_KEY` is set.\n- Add `allowed_domains` when the workflow handles credentials, private data, uploads, or authenticated sessions.\n- Use Pydantic v2 models for structured outputs and custom action schemas.\n- Use `uv` for development and installation commands.\n\n## Minimal Python Agent\n\n```python\nimport asyncio\nfrom browser_use import Agent, ChatBrowserUse\n\nasync def main():\n    agent = Agent(task=\"Find the top Hacker News story title\", llm=ChatBrowserUse())\n    history = await agent.run(max_steps=20)\n    print(history.final_result())\n\nasyncio.run(main())\n```\n\n## Minimal Browser Configuration\n\n```python\nfrom browser_use import Browser\n\nbrowser = Browser(\n    headless=False,\n    allowed_domains=[\"*.example.com\"],\n)\n```\n\nFor production performance and stealth:\n\n```python\nfrom browser_use import Browser\nbrowser = Browser(use_cloud=True)\n```\n\n## Minimal Custom Tool\n\n```python\nfrom browser_use import ActionResult, BrowserSession, Tools\n\ntools = Tools()\n\n@tools.action(\"Ask a human for a one-time approval code\")\nasync def ask_code(question: str, browser_session: BrowserSession) -> ActionResult:\n    return ActionResult(extracted_content=\"Human approval required; pause and ask the user.\")\n```\n\nThe injected browser parameter must be named exactly `browser_session` with type `BrowserSession`.\n\n## Minimal CLI Workflow\n\n```bash\nbrowser-use doctor\nbrowser-use open https:\u002F\u002Fexample.com\nbrowser-use state\nbrowser-use screenshot page.png\nbrowser-use close\n```\n\nUse `--session NAME` for multiple independent browser sessions and `cloud connect` when a cloud browser is required.\n\n## What Not to Do\n\n- Do not point future agents to source checkout examples, tests, docs, or scripts as runtime dependencies; use this skill's bundled references and scripts.\n- Do not put API keys, local profile paths, cookies, or cloud profile secrets in code snippets.\n- Do not run native examples\u002Ftests that need live websites, API keys, accounts, downloads, or browsers unless the user explicitly approves the side effects.\n- Do not install broad extras like `[all]` unless the user's task truly needs them.\n","# Browser Use Repo Skill\n\nBrowser Use is a Python >=3.11 library and CLI for AI agents that control Chromium\u002FCDP browsers, extract page content, call LLMs, and run browser automation locally or in Browser Use Cloud.\n\nUse this root skill as a router. Read only the sub-skill needed for the user's task, then follow its linked references\u002Fscripts.\n\n## First Checks\n\nRead `references\u002Frepo-provenance.md` before deciding whether this skill matches a current checkout. If the commit, dirty paths, package version, or public entry points differ, refresh this skill from repository evidence.\n\nInstall and smoke-check a normal user environment with `uv`:\n\n```bash\nuv venv --python 3.11\nsource .venv\u002Fbin\u002Factivate\nuv pip install \"browser-use[cli]\"\nuvx browser-use install\npython - \u003C\u003C'PY'\nfrom browser_use import Agent, Browser, BrowserProfile, ChatBrowserUse, Tools, ActionResult\nprint('browser-use imports ok')\nPY\n```\n\nFor the Rust-powered beta\u002Fnative runtime, install the documented native core extra when the platform wheel is available:\n\n```bash\nuv pip install \"browser-use[core]\"\n```\n\nDo not replace user-provided model names. When recommending a default for browser automation, prefer `ChatBrowserUse()` because it is optimized for Browser Use tasks.\n\n## Route by User Request\n\n| User request | Read |\n| --- | --- |\n| Python `Agent(...)`, beta agent, task prompts, `agent.run()`, callbacks, history, initial actions, skills, planning, flash mode, max steps\u002Ftimeouts | `sub-skills\u002Fagent-programming\u002FSKILL.md` |\n| `Browser`, `BrowserSession`, `BrowserProfile`, local\u002Freal Chrome, CDP URL, cloud browser, proxies, domains, downloads, HAR\u002Fvideo, DOM, screenshots, Actor APIs | `sub-skills\u002Fbrowser-control\u002FSKILL.md` |\n| Custom `Tools`\u002F`Controller` actions, default actions, `ActionResult`, parameter injection, file tools, sensitive data, upload\u002Fdownload guardrails | `sub-skills\u002Ftools-and-actions\u002FSKILL.md` |\n| `ChatBrowserUse`, OpenAI\u002FGoogle\u002FAnthropic\u002Fother providers, structured output, extraction LLMs, fallback models, token\u002Fcost tracking | `sub-skills\u002Fllm-and-output\u002FSKILL.md` |\n| Terminal `browser-use`\u002F`bu` CLI navigation, state\u002Fclick\u002Ftype\u002Fupload\u002Fscreenshot, sessions, profiles, cloud connect, tunnels, config, doctor\u002Fsetup\u002Finit | `sub-skills\u002Fcli-and-sessions\u002FSKILL.md` |\n| `@sandbox`, Browser Use Cloud API, profile sync, MCP server\u002Fclient, hosted skills, telemetry, Slack\u002FDiscord\u002Femail\u002Fwebhook integrations | `sub-skills\u002Fproduction-integrations\u002FSKILL.md` |\n\n## Shared References and Scripts\n\n- Read `references\u002Finstallation-and-environment.md` for package extras, environment variables, Chromium install, telemetry opt-out, and contributor setup notes.\n- Read `references\u002Fdevelopment-and-troubleshooting.md` for cross-cutting install\u002Fimport\u002Fbrowser dependency failures and repo-maintainer commands.\n- Run `scripts\u002Finspect_browser_use_api.py` to check imports, signatures, package version, and CLI availability in a target Python environment.\n\n## Common Defaults\n\n- Use `ChatBrowserUse()` unless the user already chose another model.\n- Load secrets from environment variables or a secret manager, not prompts or committed files.\n- Use `Browser(use_cloud=True)` when the user asks how to improve Browser performance in production; it provisions an optimized Browser Use Cloud browser when `BROWSER_USE_API_KEY` is set.\n- Add `allowed_domains` when the workflow handles credentials, private data, uploads, or authenticated sessions.\n- Use Pydantic v2 models for structured outputs and custom action schemas.\n- Use `uv` for development and installation commands.\n\n## Minimal Python Agent\n\n```python\nimport asyncio\nfrom browser_use import Agent, ChatBrowserUse\n\nasync def main():\n    agent = Agent(task=\"Find the top Hacker News story title\", llm=ChatBrowserUse())\n    history = await agent.run(max_steps=20)\n    print(history.final_result())\n\nasyncio.run(main())\n```\n\n## Minimal Browser Configuration\n\n```python\nfrom browser_use import Browser\n\nbrowser = Browser(\n    headless=False,\n    allowed_domains=[\"*.example.com\"],\n)\n```\n\nFor production performance and stealth:\n\n```python\nfrom browser_use import Browser\nbrowser = Browser(use_cloud=True)\n```\n\n## Minimal Custom Tool\n\n```python\nfrom browser_use import ActionResult, BrowserSession, Tools\n\ntools = Tools()\n\n@tools.action(\"Ask a human for a one-time approval code\")\nasync def ask_code(question: str, browser_session: BrowserSession) -> ActionResult:\n    return ActionResult(extracted_content=\"Human approval required; pause and ask the user.\")\n```\n\nThe injected browser parameter must be named exactly `browser_session` with type `BrowserSession`.\n\n## Minimal CLI Workflow\n\n```bash\nbrowser-use doctor\nbrowser-use open https:\u002F\u002Fexample.com\nbrowser-use state\nbrowser-use screenshot page.png\nbrowser-use close\n```\n\nUse `--session NAME` for multiple independent browser sessions and `cloud connect` when a cloud browser is required.\n\n## What Not to Do\n\n- Do not point future agents to source checkout examples, tests, docs, or scripts as runtime dependencies; use this skill's bundled references and scripts.\n- Do not put API keys, local profile paths, cookies, or cloud profile secrets in code snippets.\n- Do not run native examples\u002Ftests that need live websites, API keys, accounts, downloads, or browsers unless the user explicitly approves the side effects.\n- Do not install broad extras like `[all]` unless the user's task truly needs them.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fbrowser-use",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill browser-use",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill browser-use",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill browser-use","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbrowser-use\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdevelopment-and-troubleshooting.md","REFERENCE","参考文档",2582,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbrowser-use\u002Freferences\u002Fdevelopment-and-troubleshooting.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Finstallation-and-environment.md",2389,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbrowser-use\u002Freferences\u002Finstallation-and-environment.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-provenance.md",2917,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbrowser-use\u002Freferences\u002Frepo-provenance.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frepo-routing-metadata.json",504,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbrowser-use\u002Freferences\u002Frepo-routing-metadata.json",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Finspect_browser_use_api.py","SCRIPT","脚本",2602,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbrowser-use\u002Fscripts\u002Finspect_browser_use_api.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]