[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794E5DPPWE8BTH2BB8DRQ9Q":3,"skill-same:01M794E5DPPWE8BTH2BB8DRQ9Q":74},{"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},"01M794E5DPPWE8BTH2BB8DRQ9Q","task-authoring",null,"Author RoboTwin tasks, task configs, language templates, and safe instruction-expansion workflows.","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\u002Frobotwin\u002Fsub-skills\u002Ftask-authoring\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: task-authoring\ndescription: \"Author RoboTwin tasks, task configs, language templates, and safe\n  instruction-expansion workflows.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# RoboTwin task authoring\n\nUse this sub-skill when a user asks to add or modify a RoboTwin task, create a task configuration, edit language instructions, expand per-episode instructions, or understand the repository's LLM\u002Fcode-generation utilities. If you only have the generated skill tree, use the root [workspace bootstrapper](..\u002F..\u002Freferences\u002Fworkspace-bootstrap.md) first to materialize a pinned public workspace before editing runtime files.\n\n## Route first\n\n1. Work in the user's RoboTwin workspace. Runtime files here describe relative workspace files such as `envs\u002F\u003Ctask_name>.py`, `description\u002Ftask_instruction\u002F\u003Ctask_name>.json`, and `env_cfg\u002Ftask_config\u002F\u003Cconfig_name>.yml`; do not edit this generated skill tree unless the user is updating the skill itself.\n2. Decide whether the request can be deterministic. Prefer manual edits plus the bundled safe scripts below. Do not invoke Azure, OpenAI-compatible, DeepSeek, Moonshot, or other hosted model APIs unless the user explicitly asks and provides credentials.\n3. For SAPIEN scene setup, `Base_Task`, actor\u002Faction helpers, robot\u002Fcamera details, or render checks, route to [simulation-core](..\u002Fsimulation-core\u002FSKILL.md). For demonstration collection, HDF5 layout, downloads, and conversion, route to [data-pipeline](..\u002Fdata-pipeline\u002FSKILL.md).\n\n## Main workflows\n\n- **Task class and config authoring:** read [task-definition-workflow.md](references\u002Ftask-definition-workflow.md), then use [scripts\u002Fcreate_task_config.py](scripts\u002Fcreate_task_config.py) when a safe config scaffold is useful.\n- **Language templates and per-episode expansion:** read [language-instructions.md](references\u002Flanguage-instructions.md), then use [scripts\u002Fgenerate_episode_instructions.py](scripts\u002Fgenerate_episode_instructions.py) for deterministic local expansion.\n- **Credential-bound generation utilities:** read [credentialed-generation.md](references\u002Fcredentialed-generation.md) before explaining or running any LLM-backed task\u002Fobject\u002Fcode generator.\n- **Failure diagnosis:** read [troubleshooting.md](references\u002Ftroubleshooting.md) before changing assets, imports, generated code, or credential settings.\n\n## Guardrails\n\n- Keep canonical task implementations in `envs\u002F\u003Ctask_name>.py`; treat `envs_gen\u002Fgpt_\u003Ctask_name>.py` as generated scratch code until manually reviewed and simulation-validated.\n- Keep `play_once()` placeholder output synchronized with instruction templates. If `play_once()` returns `{\"{A}\": ..., \"{a}\": ...}`, every non-arm placeholder required by a template must be present in that `info` mapping.\n- Do not assume RoboTwin is importable as an installed pip package. Many workflows expect commands to run from the RoboTwin workspace with local relative paths.\n- Asset setup matters: top-level `envs` imports can fail before `assets\u002Fobjects\u002Fobjaverse\u002Flist.json` and other assets are present, especially when cluttered-table utilities are imported.\n","# RoboTwin task authoring\n\nUse this sub-skill when a user asks to add or modify a RoboTwin task, create a task configuration, edit language instructions, expand per-episode instructions, or understand the repository's LLM\u002Fcode-generation utilities. If you only have the generated skill tree, use the root [workspace bootstrapper](..\u002F..\u002Freferences\u002Fworkspace-bootstrap.md) first to materialize a pinned public workspace before editing runtime files.\n\n## Route first\n\n1. Work in the user's RoboTwin workspace. Runtime files here describe relative workspace files such as `envs\u002F\u003Ctask_name>.py`, `description\u002Ftask_instruction\u002F\u003Ctask_name>.json`, and `env_cfg\u002Ftask_config\u002F\u003Cconfig_name>.yml`; do not edit this generated skill tree unless the user is updating the skill itself.\n2. Decide whether the request can be deterministic. Prefer manual edits plus the bundled safe scripts below. Do not invoke Azure, OpenAI-compatible, DeepSeek, Moonshot, or other hosted model APIs unless the user explicitly asks and provides credentials.\n3. For SAPIEN scene setup, `Base_Task`, actor\u002Faction helpers, robot\u002Fcamera details, or render checks, route to [simulation-core](..\u002Fsimulation-core\u002FSKILL.md). For demonstration collection, HDF5 layout, downloads, and conversion, route to [data-pipeline](..\u002Fdata-pipeline\u002FSKILL.md).\n\n## Main workflows\n\n- **Task class and config authoring:** read [task-definition-workflow.md](references\u002Ftask-definition-workflow.md), then use [scripts\u002Fcreate_task_config.py](scripts\u002Fcreate_task_config.py) when a safe config scaffold is useful.\n- **Language templates and per-episode expansion:** read [language-instructions.md](references\u002Flanguage-instructions.md), then use [scripts\u002Fgenerate_episode_instructions.py](scripts\u002Fgenerate_episode_instructions.py) for deterministic local expansion.\n- **Credential-bound generation utilities:** read [credentialed-generation.md](references\u002Fcredentialed-generation.md) before explaining or running any LLM-backed task\u002Fobject\u002Fcode generator.\n- **Failure diagnosis:** read [troubleshooting.md](references\u002Ftroubleshooting.md) before changing assets, imports, generated code, or credential settings.\n\n## Guardrails\n\n- Keep canonical task implementations in `envs\u002F\u003Ctask_name>.py`; treat `envs_gen\u002Fgpt_\u003Ctask_name>.py` as generated scratch code until manually reviewed and simulation-validated.\n- Keep `play_once()` placeholder output synchronized with instruction templates. If `play_once()` returns `{\"{A}\": ..., \"{a}\": ...}`, every non-arm placeholder required by a template must be present in that `info` mapping.\n- Do not assume RoboTwin is importable as an installed pip package. Many workflows expect commands to run from the RoboTwin workspace with local relative paths.\n- Asset setup matters: top-level `envs` imports can fail before `assets\u002Fobjects\u002Fobjaverse\u002Flist.json` and other assets are present, especially when cluttered-table utilities are imported.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Frobotwin\u002Fsub-skills\u002Ftask-authoring",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 task-authoring",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill task-authoring",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill task-authoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frobotwin\u002Fsub-skills\u002Ftask-authoring\u002FSKILL.md",[46,52,56,60,64,70],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcredentialed-generation.md","REFERENCE","参考文档",5267,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frobotwin\u002Fsub-skills\u002Ftask-authoring\u002Freferences\u002Fcredentialed-generation.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Flanguage-instructions.md",6803,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frobotwin\u002Fsub-skills\u002Ftask-authoring\u002Freferences\u002Flanguage-instructions.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftask-definition-workflow.md",8161,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frobotwin\u002Fsub-skills\u002Ftask-authoring\u002Freferences\u002Ftask-definition-workflow.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",6372,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frobotwin\u002Fsub-skills\u002Ftask-authoring\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcreate_task_config.py","SCRIPT","脚本",8362,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frobotwin\u002Fsub-skills\u002Ftask-authoring\u002Fscripts\u002Fcreate_task_config.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fgenerate_episode_instructions.py",14926,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frobotwin\u002Fsub-skills\u002Ftask-authoring\u002Fscripts\u002Fgenerate_episode_instructions.py",[75,83,90,97,104,111],{"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":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]