[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7956DPVE6GNMNSAVZVCBCZ8":3,"skill-same:01M7956DPVE6GNMNSAVZVCBCZ8":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},"01M7956DPVE6GNMNSAVZVCBCZ8","cli-and-ui",null,"Use smolagents command-line entry points, browser automation CLI, Gradio UI helpers, and lightweight web-server patterns. Use when a task mentions smolagent, webagent, interactive CLI mode, CLI flags, GradioUI, launch_gradio_demo, browser agent demos, or serving a smolagents chat UI.","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\u002Fsmolagents\u002Fsub-skills\u002Fcli-and-ui\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cli-and-ui\ndescription: \"Use smolagents command-line entry points, browser automation CLI,\n  Gradio UI helpers, and lightweight web-server patterns. Use when a task\n  mentions smolagent, webagent, interactive CLI mode, CLI flags, GradioUI,\n  launch_gradio_demo, browser agent demos, or serving a smolagents chat UI.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# CLI And UI\n\nUse this sub-skill when the user wants to run smolagents from a terminal or expose an already-designed agent through a local UI\u002Fserver.\n\n## Route First\n\n- For agent construction, `CodeAgent` vs `ToolCallingAgent`, model objects, managed agents, and tool definitions, route to the sibling agent\u002Fmodel\u002Ftool sub-skills.\n- For sandbox executors, remote execution backends, import allow-lists, and security hardening beyond the CLI `--imports` flag, route to `execution-and-safety`.\n- For this sub-skill, focus on command syntax, UI wrapping, optional extras, browser\u002FUI dependencies, and troubleshooting terminal or serving failures.\n\n## Core Entry Points\n\n- `smolagent` is the general CLI for running a `CodeAgent` or `ToolCallingAgent` from a prompt or an interactive setup wizard.\n- `webagent` is a specialized browser-automation CLI that starts a Selenium\u002FHelium Chrome session and runs a vision-capable `CodeAgent` with screenshot callbacks.\n- `GradioUI` wraps a `MultiStepAgent` in a streaming Gradio chat interface with optional multimodal file upload.\n- `launch_gradio_demo(tool)` launches a Gradio `Interface` for a single `Tool` whose `inputs` and `output_type` are defined; use `GradioUI` for full agent chat UIs.\n- Server examples are adaptation patterns: run the blocking `agent.run(...)` call off the async event loop and disconnect external tool clients during shutdown.\n\n## Safe Discovery\n\nBefore running model-backed tasks, use safe help checks:\n\n```bash\npython sub-skills\u002Fcli-and-ui\u002Fscripts\u002Fprint_cli_help.py --command smolagent\npython sub-skills\u002Fcli-and-ui\u002Fscripts\u002Fprint_cli_help.py --command webagent\nsmolagent --help\nwebagent --help\n```\n\nIf console scripts are unavailable but the package imports, try module-level help:\n\n```bash\npython -m smolagents.cli --help\npython -m smolagents.vision_web_browser --help\n```\n\n## Common Workflows\n\n- Run a direct CLI prompt with `smolagent \"your task\" --model-type InferenceClientModel --model-id Qwen\u002FQwen3-Next-80B-A3B-Thinking --tools web_search`.\n- Start the guided wizard with bare `smolagent`; it prompts for action type, tools, model settings, optional API fields, additional imports, and final task.\n- Use `--action-type code` for a code-writing `CodeAgent`; use `--action-type tool_calling` for a `ToolCallingAgent`.\n- Use `webagent \"browser task\" --model-type LiteLLMModel --model-id gpt-4o` only when browser, model, and optional vision dependencies are installed and a Chrome\u002FWebDriver stack is usable.\n- Wrap a configured agent with `GradioUI(agent, file_upload_folder=\"uploads\", reset_agent_memory=True).launch(share=False)` for a local chat UI.\n\n## References\n\n- See [CLI reference](references\u002Fcli-reference.md) for command names, flags, defaults, and behavior.\n- See [UI workflows](references\u002Fui-workflows.md) for `GradioUI`, streaming, file upload, server adaptation, and monitoring notes.\n- See [troubleshooting](references\u002Ftroubleshooting.md) for missing scripts, optional extras, invalid model\u002Ftool flags, and browser failures.\n","# CLI And UI\n\nUse this sub-skill when the user wants to run smolagents from a terminal or expose an already-designed agent through a local UI\u002Fserver.\n\n## Route First\n\n- For agent construction, `CodeAgent` vs `ToolCallingAgent`, model objects, managed agents, and tool definitions, route to the sibling agent\u002Fmodel\u002Ftool sub-skills.\n- For sandbox executors, remote execution backends, import allow-lists, and security hardening beyond the CLI `--imports` flag, route to `execution-and-safety`.\n- For this sub-skill, focus on command syntax, UI wrapping, optional extras, browser\u002FUI dependencies, and troubleshooting terminal or serving failures.\n\n## Core Entry Points\n\n- `smolagent` is the general CLI for running a `CodeAgent` or `ToolCallingAgent` from a prompt or an interactive setup wizard.\n- `webagent` is a specialized browser-automation CLI that starts a Selenium\u002FHelium Chrome session and runs a vision-capable `CodeAgent` with screenshot callbacks.\n- `GradioUI` wraps a `MultiStepAgent` in a streaming Gradio chat interface with optional multimodal file upload.\n- `launch_gradio_demo(tool)` launches a Gradio `Interface` for a single `Tool` whose `inputs` and `output_type` are defined; use `GradioUI` for full agent chat UIs.\n- Server examples are adaptation patterns: run the blocking `agent.run(...)` call off the async event loop and disconnect external tool clients during shutdown.\n\n## Safe Discovery\n\nBefore running model-backed tasks, use safe help checks:\n\n```bash\npython sub-skills\u002Fcli-and-ui\u002Fscripts\u002Fprint_cli_help.py --command smolagent\npython sub-skills\u002Fcli-and-ui\u002Fscripts\u002Fprint_cli_help.py --command webagent\nsmolagent --help\nwebagent --help\n```\n\nIf console scripts are unavailable but the package imports, try module-level help:\n\n```bash\npython -m smolagents.cli --help\npython -m smolagents.vision_web_browser --help\n```\n\n## Common Workflows\n\n- Run a direct CLI prompt with `smolagent \"your task\" --model-type InferenceClientModel --model-id Qwen\u002FQwen3-Next-80B-A3B-Thinking --tools web_search`.\n- Start the guided wizard with bare `smolagent`; it prompts for action type, tools, model settings, optional API fields, additional imports, and final task.\n- Use `--action-type code` for a code-writing `CodeAgent`; use `--action-type tool_calling` for a `ToolCallingAgent`.\n- Use `webagent \"browser task\" --model-type LiteLLMModel --model-id gpt-4o` only when browser, model, and optional vision dependencies are installed and a Chrome\u002FWebDriver stack is usable.\n- Wrap a configured agent with `GradioUI(agent, file_upload_folder=\"uploads\", reset_agent_memory=True).launch(share=False)` for a local chat UI.\n\n## References\n\n- See [CLI reference](references\u002Fcli-reference.md) for command names, flags, defaults, and behavior.\n- See [UI workflows](references\u002Fui-workflows.md) for `GradioUI`, streaming, file upload, server adaptation, and monitoring notes.\n- See [troubleshooting](references\u002Ftroubleshooting.md) for missing scripts, optional extras, invalid model\u002Ftool flags, and browser failures.\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\u002Fsmolagents\u002Fsub-skills\u002Fcli-and-ui",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 cli-and-ui",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill cli-and-ui",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill cli-and-ui","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fcli-and-ui\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcli-reference.md","REFERENCE","参考文档",4664,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fcli-and-ui\u002Freferences\u002Fcli-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",4187,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fcli-and-ui\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fui-workflows.md",4296,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fcli-and-ui\u002Freferences\u002Fui-workflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fprint_cli_help.py","SCRIPT","脚本",1880,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsmolagents\u002Fsub-skills\u002Fcli-and-ui\u002Fscripts\u002Fprint_cli_help.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",[],[]]