[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79738CCSBQPW3RH0WPZ2WCB":3,"skill-same:01M79738CCSBQPW3RH0WPZ2WCB":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},"01M79738CCSBQPW3RH0WPZ2WCB","rollout-and-tools",null,"Use when modifying verl rollout engines, multi-turn agent loops, function tools, tool schemas, rollout traces, or generation-server flows.","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\u002Fverl\u002Fsub-skills\u002Frollout-and-tools\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rollout-and-tools\ndescription: \"Use when modifying verl rollout engines, multi-turn agent loops,\n  function tools, tool schemas, rollout traces, or generation-server flows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Rollout And Tools\n\nUse this sub-skill when the task touches verl rollout behavior rather than trainer optimizer policy: rollout backend config, async generation servers, multi-turn agent loops, tool calling, function-tool schema authoring, tokenization sanity checks, trace output, or rollout visualization.\n\n## Route The Task\n\n- For rollout backend choices and config fields, read [Rollout workflows](references\u002Frollout-workflows.md).\n- For `@function_tool`, `BaseTool`, schema loading, and tool dispatch, read [Tooling API](references\u002Ftooling-api.md).\n- For tokenization warnings, tool parser issues, trace volume, and viewer pitfalls, read [Troubleshooting](references\u002Ftroubleshooting.md).\n- To preflight a Python file used by `actor_rollout_ref.rollout.multi_turn.function_tool_path`, run [validate_function_tool.py](scripts\u002Fvalidate_function_tool.py).\n\n## Safe Defaults\n\n- Prefer `actor_rollout_ref.rollout.mode=async`; sync rollout mode is removed.\n- Use `actor_rollout_ref.rollout.multi_turn.enable=True` plus `actor_rollout_ref.rollout.agent.default_agent_loop=tool_agent` for built-in tool-calling loops.\n- Use function tools for stateless `fn(**parameters)` calls; use native `BaseTool` tools for lifecycle, per-trajectory state, sandbox resources, or `tools_kwargs`.\n- Keep `tokenization_sanity_check_mode=strict` until the model chat template has been validated; use `ignore_strippable` only for whitespace-only template drift.\n- Treat rollout viewer as an interactive diagnostic over generated JSONL rollout data, not as a required runtime dependency.\n\n## Verification Targets\n\n- CPU-safe candidates: function-tool registration\u002Freturn tests, `ToolAgentLoop._call_tool` error-handling tests, Qwen3 parser safety tests, and vLLM CLI argument parsing tests.\n- When changing multi-turn or tool parsing behavior, include a case where a malformed tool call returns a readable `ToolResponse` instead of crashing the loop.\n","# Rollout And Tools\n\nUse this sub-skill when the task touches verl rollout behavior rather than trainer optimizer policy: rollout backend config, async generation servers, multi-turn agent loops, tool calling, function-tool schema authoring, tokenization sanity checks, trace output, or rollout visualization.\n\n## Route The Task\n\n- For rollout backend choices and config fields, read [Rollout workflows](references\u002Frollout-workflows.md).\n- For `@function_tool`, `BaseTool`, schema loading, and tool dispatch, read [Tooling API](references\u002Ftooling-api.md).\n- For tokenization warnings, tool parser issues, trace volume, and viewer pitfalls, read [Troubleshooting](references\u002Ftroubleshooting.md).\n- To preflight a Python file used by `actor_rollout_ref.rollout.multi_turn.function_tool_path`, run [validate_function_tool.py](scripts\u002Fvalidate_function_tool.py).\n\n## Safe Defaults\n\n- Prefer `actor_rollout_ref.rollout.mode=async`; sync rollout mode is removed.\n- Use `actor_rollout_ref.rollout.multi_turn.enable=True` plus `actor_rollout_ref.rollout.agent.default_agent_loop=tool_agent` for built-in tool-calling loops.\n- Use function tools for stateless `fn(**parameters)` calls; use native `BaseTool` tools for lifecycle, per-trajectory state, sandbox resources, or `tools_kwargs`.\n- Keep `tokenization_sanity_check_mode=strict` until the model chat template has been validated; use `ignore_strippable` only for whitespace-only template drift.\n- Treat rollout viewer as an interactive diagnostic over generated JSONL rollout data, not as a required runtime dependency.\n\n## Verification Targets\n\n- CPU-safe candidates: function-tool registration\u002Freturn tests, `ToolAgentLoop._call_tool` error-handling tests, Qwen3 parser safety tests, and vLLM CLI argument parsing tests.\n- When changing multi-turn or tool parsing behavior, include a case where a malformed tool call returns a readable `ToolResponse` instead of crashing the loop.\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\u002Fverl\u002Fsub-skills\u002Frollout-and-tools",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 rollout-and-tools",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill rollout-and-tools",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill rollout-and-tools","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fverl\u002Fsub-skills\u002Frollout-and-tools\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Frollout-workflows.md","REFERENCE","参考文档",4550,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fverl\u002Fsub-skills\u002Frollout-and-tools\u002Freferences\u002Frollout-workflows.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftooling-api.md",4274,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fverl\u002Fsub-skills\u002Frollout-and-tools\u002Freferences\u002Ftooling-api.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",3606,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fverl\u002Fsub-skills\u002Frollout-and-tools\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fvalidate_function_tool.py","SCRIPT","脚本",3831,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fverl\u002Fsub-skills\u002Frollout-and-tools\u002Fscripts\u002Fvalidate_function_tool.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",[],[]]