[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78X6BBBZB4PD204TYBJ3E09":3,"skill-same:01M78X6BBBZB4PD204TYBJ3E09":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},"01M78X6BBBZB4PD204TYBJ3E09","pipelines-and-methods",null,"Plan and implement FlashRAG end-to-end RAG pipelines, quick-start demos, method reproductions, active\u002Freasoning\u002Fbranching\u002Fmultimodal pipelines, multi-turn prompts, and experiment-runner dry-runs without executing large models by default.","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\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pipelines-and-methods\ndescription: \"Plan and implement FlashRAG end-to-end RAG pipelines, quick-start\n  demos, method reproductions, active\u002Freasoning\u002Fbranching\u002Fmultimodal pipelines,\n  multi-turn prompts, and experiment-runner dry-runs without executing large\n  models by default.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# FlashRAG Pipelines and Methods\n\nUse this sub-skill when the task is about choosing or wiring FlashRAG pipelines, adapting quick-start demos, reproducing supported methods, planning multi-turn or multimodal workflows, or dry-checking an experiment configuration before any large model\u002Findex execution.\n\n## Route first\n\n- For standard text RAG, start with `SequentialPipeline` or `naive_run`; see [pipeline API](references\u002Fpipeline-api.md) and [quick-start\u002Fmulti-turn](references\u002Fquick-start-and-multiturn.md).\n- For method reproduction, map the requested method name to the experiment-runner recipe and prerequisites; see [method recipes](references\u002Fmethod-recipes.md).\n- For active, branching, adaptive, or reasoning RAG, select the pipeline by required control flow and model support; see [pipeline API](references\u002Fpipeline-api.md) and [multimodal\u002Freasoning](references\u002Fmultimodal-and-reasoning.md).\n- For multimodal RAG, check dataset modality, prompt template, multimodal retriever settings, generator capability, and hardware before running; see [multimodal\u002Freasoning](references\u002Fmultimodal-and-reasoning.md).\n- Before execution, run the bundled safe checker: `python skills\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods\u002Fscripts\u002Fvalidate_pipeline_config.py --config CONFIG.yaml --method METHOD --dry-run-plan`.\n- If a run fails or looks wrong, triage with [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Safety defaults\n\n- Do not execute model downloads, index building, vLLM server\u002Fmodel loading, or full benchmark runs unless explicitly requested.\n- Prefer `test_sample_num`, small `retrieval_topk`, short `generation_params`, and `do_eval=False` for smoke tests.\n- Treat model paths, corpus paths, index paths, cache paths, and output paths as user-provided runtime values; do not hard-code machine-specific paths in public instructions.\n- Keep low-level config schema details, index construction, generator\u002Frefiner internals, and metric\u002FUI work in their dedicated FlashRAG skill areas.\n","# FlashRAG Pipelines and Methods\n\nUse this sub-skill when the task is about choosing or wiring FlashRAG pipelines, adapting quick-start demos, reproducing supported methods, planning multi-turn or multimodal workflows, or dry-checking an experiment configuration before any large model\u002Findex execution.\n\n## Route first\n\n- For standard text RAG, start with `SequentialPipeline` or `naive_run`; see [pipeline API](references\u002Fpipeline-api.md) and [quick-start\u002Fmulti-turn](references\u002Fquick-start-and-multiturn.md).\n- For method reproduction, map the requested method name to the experiment-runner recipe and prerequisites; see [method recipes](references\u002Fmethod-recipes.md).\n- For active, branching, adaptive, or reasoning RAG, select the pipeline by required control flow and model support; see [pipeline API](references\u002Fpipeline-api.md) and [multimodal\u002Freasoning](references\u002Fmultimodal-and-reasoning.md).\n- For multimodal RAG, check dataset modality, prompt template, multimodal retriever settings, generator capability, and hardware before running; see [multimodal\u002Freasoning](references\u002Fmultimodal-and-reasoning.md).\n- Before execution, run the bundled safe checker: `python skills\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods\u002Fscripts\u002Fvalidate_pipeline_config.py --config CONFIG.yaml --method METHOD --dry-run-plan`.\n- If a run fails or looks wrong, triage with [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Safety defaults\n\n- Do not execute model downloads, index building, vLLM server\u002Fmodel loading, or full benchmark runs unless explicitly requested.\n- Prefer `test_sample_num`, small `retrieval_topk`, short `generation_params`, and `do_eval=False` for smoke tests.\n- Treat model paths, corpus paths, index paths, cache paths, and output paths as user-provided runtime values; do not hard-code machine-specific paths in public instructions.\n- Keep low-level config schema details, index construction, generator\u002Frefiner internals, and metric\u002FUI work in their dedicated FlashRAG skill areas.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods",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 pipelines-and-methods",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill pipelines-and-methods",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill pipelines-and-methods","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods\u002FSKILL.md",[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fmethod-recipes.md","REFERENCE","参考文档",6924,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods\u002Freferences\u002Fmethod-recipes.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmultimodal-and-reasoning.md",5259,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods\u002Freferences\u002Fmultimodal-and-reasoning.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fpipeline-api.md",7450,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods\u002Freferences\u002Fpipeline-api.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fquick-start-and-multiturn.md",4448,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods\u002Freferences\u002Fquick-start-and-multiturn.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftroubleshooting.md",5930,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods\u002Freferences\u002Ftroubleshooting.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fvalidate_pipeline_config.py","SCRIPT","脚本",22998,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fflashrag\u002Fsub-skills\u002Fpipelines-and-methods\u002Fscripts\u002Fvalidate_pipeline_config.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",[],[]]