[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YVT8G29VFV641G55GYE7J":3,"skill-same:01M78YVT8G29VFV641G55GYE7J":67},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78YVT8G29VFV641G55GYE7J","browser-drivers",null,"Select, configure, and troubleshoot LaVague Selenium and Playwright browser drivers safely.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fbrowser-drivers\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: browser-drivers\ndescription: \"Select, configure, and troubleshoot LaVague Selenium and\n  Playwright browser drivers safely.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# LaVague browser drivers\n\nUse this sub-skill when the task is to choose or configure a LaVague browser driver, verify browser runtime availability, connect an existing browser\u002Fsession, or diagnose Selenium\u002FPlaywright browser failures.\n\n## Route here for\n\n- Choosing `SeleniumDriver` versus `PlaywrightDriver` for a LaVague `ActionEngine` or `WebAgent`.\n- Configuring `headless`, viewport size, `user_data_dir`, custom Selenium options, driver injection, or Playwright page factories.\n- Diagnosing missing Chrome\u002FChromedriver, missing Playwright browser binaries, GUI\u002Fheadless mismatches, tabs, iframes, scrolling, screenshots, or Browserbase remote Selenium setup.\n\n## Route elsewhere\n\n- `WorldModel`, `ActionEngine`, `WebAgent`, agent logging, token counting, and normal `agent.run()` patterns: route to `..\u002Fcore-web-agent\u002F`.\n- Provider contexts, OpenAI\u002FGemini\u002FAnthropic\u002FFireworks credentials, embeddings, and retrievers: route to `..\u002Fcontexts-and-retrievers\u002F`.\n- Gradio, `agent.demo()`, Chrome extension server, websocket driver server, or `lavague-serve`: route to `..\u002Fserver-extension-gradio\u002F`.\n- QA generation or benchmark runner CLI behavior: route to `..\u002Fqa-and-test-runner\u002F`.\n\n## Start points\n\n1. Read [references\u002Fdriver-reference.md](references\u002Fdriver-reference.md) for constructor signatures, driver capabilities, and feature support boundaries.\n2. Use [references\u002Fbrowser-workflows.md](references\u002Fbrowser-workflows.md) for copyable Selenium\u002FPlaywright setup patterns, existing-session recipes, iframe\u002Ftab\u002Fscan behavior, and Browserbase notes.\n3. Use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when browser construction fails, Playwright binaries are missing, headless\u002Fheaded behavior is wrong, or a page with CAPTCHAs\u002Fpop-ups\u002Fiframes\u002Ftabs stalls.\n4. Run the safe probe before spending browser\u002FAPI time:\n\n```bash\npython sub-skills\u002Fbrowser-drivers\u002Fscripts\u002Flavague_driver_probe.py\n```\n\nThe probe checks imports and local browser binary hints by default. It does **not** launch a browser unless `--construct` is provided.\n\n## Driver choice in one minute\n\n- Prefer `SeleniumDriver` for the widest LaVague feature coverage: default install path, iframes, multiple tabs, element highlighting, scrolling, dropdowns, custom Selenium options, and Browserbase remote connection.\n- Use `PlaywrightDriver` only when the caller specifically wants Playwright or already has a Playwright page\u002Fcontext. Treat it as a smaller feature surface: do not promise Selenium feature parity, remote Browserbase support, or complete tab\u002Fheadless-agent behavior without a local verification run.\n- Both driver constructors create a browser\u002Fpage immediately. If the task only asks whether the environment is ready, run the bundled probe without `--construct` first.\n\n## Minimal usage patterns\n\nSelenium default:\n\n```python\nfrom lavague.core import ActionEngine, WorldModel\nfrom lavague.core.agents import WebAgent\nfrom lavague.drivers.selenium import SeleniumDriver\n\ndriver = SeleniumDriver(headless=True)\naction_engine = ActionEngine(driver)\nagent = WebAgent(WorldModel(), action_engine)\n# agent.get(url); agent.run(objective) belongs to the core-web-agent workflow.\n```\n\nPlaywright selection:\n\n```python\nfrom lavague.core import ActionEngine\nfrom lavague.drivers.playwright import PlaywrightDriver\n\ndriver = PlaywrightDriver(headless=True)\naction_engine = ActionEngine(driver)\n```\n\nExisting Chrome session for CAPTCHA\u002Flogin-heavy sites:\n\n```python\nfrom lavague.drivers.selenium import SeleniumDriver\n\ndriver = SeleniumDriver(headless=False, user_data_dir=\"\u002Fpath\u002Fto\u002Fchrome-profile\")\n```\n\nDo not hard-code profile paths or credentials in reusable scripts. Ask the caller for an explicit path at runtime.\n\n## Safety defaults\n\n- Default probes and recipes here avoid model provider calls, downloads, public-site navigation, persistent servers, and browser launch.\n- `--construct` in the bundled probe is the explicit opt-in for browser launch. Passing `--url` may navigate to that URL; omit it for a blank-page construction check.\n- Browser examples can still require GUI support, browser binaries, matching drivers, provider credentials, and network access when escalated into full agent execution.\n","# LaVague browser drivers\n\nUse this sub-skill when the task is to choose or configure a LaVague browser driver, verify browser runtime availability, connect an existing browser\u002Fsession, or diagnose Selenium\u002FPlaywright browser failures.\n\n## Route here for\n\n- Choosing `SeleniumDriver` versus `PlaywrightDriver` for a LaVague `ActionEngine` or `WebAgent`.\n- Configuring `headless`, viewport size, `user_data_dir`, custom Selenium options, driver injection, or Playwright page factories.\n- Diagnosing missing Chrome\u002FChromedriver, missing Playwright browser binaries, GUI\u002Fheadless mismatches, tabs, iframes, scrolling, screenshots, or Browserbase remote Selenium setup.\n\n## Route elsewhere\n\n- `WorldModel`, `ActionEngine`, `WebAgent`, agent logging, token counting, and normal `agent.run()` patterns: route to `..\u002Fcore-web-agent\u002F`.\n- Provider contexts, OpenAI\u002FGemini\u002FAnthropic\u002FFireworks credentials, embeddings, and retrievers: route to `..\u002Fcontexts-and-retrievers\u002F`.\n- Gradio, `agent.demo()`, Chrome extension server, websocket driver server, or `lavague-serve`: route to `..\u002Fserver-extension-gradio\u002F`.\n- QA generation or benchmark runner CLI behavior: route to `..\u002Fqa-and-test-runner\u002F`.\n\n## Start points\n\n1. Read [references\u002Fdriver-reference.md](references\u002Fdriver-reference.md) for constructor signatures, driver capabilities, and feature support boundaries.\n2. Use [references\u002Fbrowser-workflows.md](references\u002Fbrowser-workflows.md) for copyable Selenium\u002FPlaywright setup patterns, existing-session recipes, iframe\u002Ftab\u002Fscan behavior, and Browserbase notes.\n3. Use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when browser construction fails, Playwright binaries are missing, headless\u002Fheaded behavior is wrong, or a page with CAPTCHAs\u002Fpop-ups\u002Fiframes\u002Ftabs stalls.\n4. Run the safe probe before spending browser\u002FAPI time:\n\n```bash\npython sub-skills\u002Fbrowser-drivers\u002Fscripts\u002Flavague_driver_probe.py\n```\n\nThe probe checks imports and local browser binary hints by default. It does **not** launch a browser unless `--construct` is provided.\n\n## Driver choice in one minute\n\n- Prefer `SeleniumDriver` for the widest LaVague feature coverage: default install path, iframes, multiple tabs, element highlighting, scrolling, dropdowns, custom Selenium options, and Browserbase remote connection.\n- Use `PlaywrightDriver` only when the caller specifically wants Playwright or already has a Playwright page\u002Fcontext. Treat it as a smaller feature surface: do not promise Selenium feature parity, remote Browserbase support, or complete tab\u002Fheadless-agent behavior without a local verification run.\n- Both driver constructors create a browser\u002Fpage immediately. If the task only asks whether the environment is ready, run the bundled probe without `--construct` first.\n\n## Minimal usage patterns\n\nSelenium default:\n\n```python\nfrom lavague.core import ActionEngine, WorldModel\nfrom lavague.core.agents import WebAgent\nfrom lavague.drivers.selenium import SeleniumDriver\n\ndriver = SeleniumDriver(headless=True)\naction_engine = ActionEngine(driver)\nagent = WebAgent(WorldModel(), action_engine)\n# agent.get(url); agent.run(objective) belongs to the core-web-agent workflow.\n```\n\nPlaywright selection:\n\n```python\nfrom lavague.core import ActionEngine\nfrom lavague.drivers.playwright import PlaywrightDriver\n\ndriver = PlaywrightDriver(headless=True)\naction_engine = ActionEngine(driver)\n```\n\nExisting Chrome session for CAPTCHA\u002Flogin-heavy sites:\n\n```python\nfrom lavague.drivers.selenium import SeleniumDriver\n\ndriver = SeleniumDriver(headless=False, user_data_dir=\"\u002Fpath\u002Fto\u002Fchrome-profile\")\n```\n\nDo not hard-code profile paths or credentials in reusable scripts. Ask the caller for an explicit path at runtime.\n\n## Safety defaults\n\n- Default probes and recipes here avoid model provider calls, downloads, public-site navigation, persistent servers, and browser launch.\n- `--construct` in the bundled probe is the explicit opt-in for browser launch. Passing `--url` may navigate to that URL; omit it for a blank-page construction check.\n- Browser examples can still require GUI support, browser binaries, matching drivers, provider credentials, and network access when escalated into full agent execution.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fbrowser-drivers",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill browser-drivers",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill browser-drivers",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill browser-drivers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fbrowser-drivers\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fbrowser-workflows.md","REFERENCE","参考文档",8884,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fbrowser-drivers\u002Freferences\u002Fbrowser-workflows.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdriver-reference.md",7949,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fbrowser-drivers\u002Freferences\u002Fdriver-reference.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",8323,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fbrowser-drivers\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Flavague_driver_probe.py","SCRIPT","脚本",12717,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fla-vague\u002Fsub-skills\u002Fbrowser-drivers\u002Fscripts\u002Flavague_driver_probe.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]