[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796HCAHAW64AHRECTM69PTQ":3,"skill-same:01M796HCAHAW64AHRECTM69PTQ":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},"01M796HCAHAW64AHRECTM69PTQ","pipeline-programming",null,"Build, run, batch, debug, and smoke-check Towhee custom pipelines with pipe.input, RuntimePipeline, AutoConfig, and AutoPipes.","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\u002Ftowhee\u002Fsub-skills\u002Fpipeline-programming\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pipeline-programming\ndescription: \"Build, run, batch, debug, and smoke-check Towhee custom pipelines\n  with pipe.input, RuntimePipeline, AutoConfig, and AutoPipes.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Towhee pipeline programming\n\nUse this sub-skill when the user needs to define or diagnose a Towhee custom pipeline with `pipe.input(...)`, chained node methods, `output(...)`, `RuntimePipeline.__call__`, `batch(...)`, `debug(...)`, or `flush()`. It also covers safe, local-only checks for `AutoConfig` and network-aware guidance for `AutoPipes.pipeline(...)`.\n\n## Fast routing\n\n1. For pipeline node syntax, callable contracts, schemas, `RuntimePipeline`, `batch`, `flush`, `AutoConfig`, and `AutoPipes`, use [Pipeline API](references\u002Fpipeline-api.md).\n2. For profiler\u002Ftracer usage, debug result inspection, include\u002Fexclude filtering, and batch debug, use [Debugging and profiling](references\u002Fdebugging-and-profiling.md).\n3. For failures involving schema names, missing output columns, `debug()` flags, Hub\u002Fcache\u002Fnetwork misses, or optional Hub operator downloads, use [Troubleshooting](references\u002Ftroubleshooting.md).\n4. For a no-network smoke check in the target environment, run [pipeline_smoke.py](scripts\u002Fpipeline_smoke.py) with `--verbose` when useful.\n\n## Scope boundaries\n\n- Stay here for custom pipeline construction, local lambda\u002Fcallable nodes, node semantics, runtime execution, batch\u002Fdebug\u002Fflush, `AutoConfig.*`, and `AutoPipes.pipeline` selection caveats.\n- Route operator template creation, Hub operator packaging, `ops` registration patterns, and CLI operator scaffolding to `operator-hub-and-cli`.\n- Route HTTP\u002FGRPC services, Docker, Triton server startup, `towhee server`, and deployment packaging to `serving-and-triton`.\n- Route `DataCollection` display, entity\u002Ftype wrappers, serializers, and data loader details to `data-utilities`.\n- Route model training, `Trainer`, and `NNOperator.train\u002Fsetup_trainer` workflows to `training-and-models`.\n\n## Default safe workflow\n\n```bash\npython scripts\u002Fpipeline_smoke.py --verbose\n```\n\nIf the smoke check fails at import time, fix the active Python environment before attempting Hub, model, Triton, or deployment workflows. If the smoke check passes, prefer lambda\u002Fcallable pipelines for quick local diagnosis before introducing Hub operators that may download code, models, or optional dependencies.\n","# Towhee pipeline programming\n\nUse this sub-skill when the user needs to define or diagnose a Towhee custom pipeline with `pipe.input(...)`, chained node methods, `output(...)`, `RuntimePipeline.__call__`, `batch(...)`, `debug(...)`, or `flush()`. It also covers safe, local-only checks for `AutoConfig` and network-aware guidance for `AutoPipes.pipeline(...)`.\n\n## Fast routing\n\n1. For pipeline node syntax, callable contracts, schemas, `RuntimePipeline`, `batch`, `flush`, `AutoConfig`, and `AutoPipes`, use [Pipeline API](references\u002Fpipeline-api.md).\n2. For profiler\u002Ftracer usage, debug result inspection, include\u002Fexclude filtering, and batch debug, use [Debugging and profiling](references\u002Fdebugging-and-profiling.md).\n3. For failures involving schema names, missing output columns, `debug()` flags, Hub\u002Fcache\u002Fnetwork misses, or optional Hub operator downloads, use [Troubleshooting](references\u002Ftroubleshooting.md).\n4. For a no-network smoke check in the target environment, run [pipeline_smoke.py](scripts\u002Fpipeline_smoke.py) with `--verbose` when useful.\n\n## Scope boundaries\n\n- Stay here for custom pipeline construction, local lambda\u002Fcallable nodes, node semantics, runtime execution, batch\u002Fdebug\u002Fflush, `AutoConfig.*`, and `AutoPipes.pipeline` selection caveats.\n- Route operator template creation, Hub operator packaging, `ops` registration patterns, and CLI operator scaffolding to `operator-hub-and-cli`.\n- Route HTTP\u002FGRPC services, Docker, Triton server startup, `towhee server`, and deployment packaging to `serving-and-triton`.\n- Route `DataCollection` display, entity\u002Ftype wrappers, serializers, and data loader details to `data-utilities`.\n- Route model training, `Trainer`, and `NNOperator.train\u002Fsetup_trainer` workflows to `training-and-models`.\n\n## Default safe workflow\n\n```bash\npython scripts\u002Fpipeline_smoke.py --verbose\n```\n\nIf the smoke check fails at import time, fix the active Python environment before attempting Hub, model, Triton, or deployment workflows. If the smoke check passes, prefer lambda\u002Fcallable pipelines for quick local diagnosis before introducing Hub operators that may download code, models, or optional dependencies.\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\u002Ftowhee\u002Fsub-skills\u002Fpipeline-programming",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 pipeline-programming",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill pipeline-programming",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill pipeline-programming","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftowhee\u002Fsub-skills\u002Fpipeline-programming\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdebugging-and-profiling.md","REFERENCE","参考文档",4891,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftowhee\u002Fsub-skills\u002Fpipeline-programming\u002Freferences\u002Fdebugging-and-profiling.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fpipeline-api.md",11304,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftowhee\u002Fsub-skills\u002Fpipeline-programming\u002Freferences\u002Fpipeline-api.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",6275,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftowhee\u002Fsub-skills\u002Fpipeline-programming\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fpipeline_smoke.py","SCRIPT","脚本",4228,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftowhee\u002Fsub-skills\u002Fpipeline-programming\u002Fscripts\u002Fpipeline_smoke.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",[],[]]