[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZAF0PEHFD6A4WBXKYVCHS":3,"skill-same:01M78ZAF0PEHFD6A4WBXKYVCHS":70},{"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},"01M78ZAF0PEHFD6A4WBXKYVCHS","document-pipeline",null,"Work with LightRAG document ingestion internals: parser routing, filename and process options, chunker selection, sidecars, multimodal analysis flow, doc-status metadata, and pipeline concurrency\u002Frefusal semantics.","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\u002Flightrag\u002Fsub-skills\u002Fdocument-pipeline\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: document-pipeline\ndescription: \"Work with LightRAG document ingestion internals: parser routing,\n  filename and process options, chunker selection, sidecars, multimodal analysis\n  flow, doc-status metadata, and pipeline concurrency\u002Frefusal semantics.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# LightRAG Document Pipeline\n\nUse this sub-skill when a task involves file\u002Ftext ingestion behavior, parser routing, process-option strings, chunker strategy selection, sidecar artifacts, multimodal analysis flow, doc-status state metadata, or upload\u002Fscan\u002Fdelete concurrency reasoning.\n\n## Route By Task\n\n- Choose parser engines, filename hints, `LIGHTRAG_PARSER` rules, process options, engine parameters, or chunk parameters with [parser-and-process-options](references\u002Fparser-and-process-options.md).\n- Compare `F` \u002F `R` \u002F `V` \u002F `P` chunking, understand sidecar artifacts, or reason about fallback\u002Fprovenance behavior with [chunking-and-sidecars](references\u002Fchunking-and-sidecars.md).\n- Explain why enqueue, scan, delete, or processing was refused or deferred using [pipeline-concurrency](references\u002Fpipeline-concurrency.md).\n- Diagnose unavailable parser services, invalid hints\u002Foptions, missing sidecars, doc-status failures, cancellation, or stale parse\u002Fchunk metadata with [troubleshooting](references\u002Ftroubleshooting.md).\n- Run [scripts\u002Fcheck_pipeline_symbols.py](scripts\u002Fcheck_pipeline_symbols.py) for a safe installed-package import and symbol\u002Fsignature check that does not call parser services, models, credentials, storages, or repository tests.\n\n## Boundaries\n\n- This sub-skill owns `apipeline_enqueue_documents`, `apipeline_process_enqueue_documents`, parse\u002Fanalyze\u002Fprocess staging, parser routing functions, `process_options`, `chunk_options`, sidecar contracts, multimodal sidecar chunks, doc-status metadata carry-over, and `pipeline_status` fields.\n- For direct `LightRAG` construction, `ainsert`, `aquery`, lifecycle, custom KG insertion, embeddings, cache, rerank, and generic library examples, route to `..\u002Fcore-rag\u002FSKILL.md`.\n- For API endpoint request\u002Fresponse details, upload route models, WebUI operation, auth, server startup, or deployment, route to `..\u002Fapi-server\u002FSKILL.md`.\n- For storage backend selection, database services, migrations, workspace isolation, or destructive storage operations, route to `..\u002Fstorage-backends\u002FSKILL.md`.\n- For LLM, VLM, embedding, reranker provider setup, credentials, and provider-specific parameters, route to `..\u002Fllm-providers\u002FSKILL.md`.\n\n## Non-Negotiables\n\n- Treat `process_options` as the exact per-document selector string: `i`, `t`, `e`, `!`, plus at most one chunk selector from `F` \u002F `R` \u002F `V` \u002F `P`.\n- Do not make reusable guidance depend on source-checkout paths, repository scripts, examples, docs, tests, or local environment locations.\n- Be explicit when a parser or modality path needs optional dependencies, an external parser service, embeddings, or VLM\u002FLLM roles; do not present those paths as always-available.\n- Preserve the concurrency contract: `busy` alone does not block enqueue, but `destructive_busy` and `scanning_exclusive` do.\n","# LightRAG Document Pipeline\n\nUse this sub-skill when a task involves file\u002Ftext ingestion behavior, parser routing, process-option strings, chunker strategy selection, sidecar artifacts, multimodal analysis flow, doc-status state metadata, or upload\u002Fscan\u002Fdelete concurrency reasoning.\n\n## Route By Task\n\n- Choose parser engines, filename hints, `LIGHTRAG_PARSER` rules, process options, engine parameters, or chunk parameters with [parser-and-process-options](references\u002Fparser-and-process-options.md).\n- Compare `F` \u002F `R` \u002F `V` \u002F `P` chunking, understand sidecar artifacts, or reason about fallback\u002Fprovenance behavior with [chunking-and-sidecars](references\u002Fchunking-and-sidecars.md).\n- Explain why enqueue, scan, delete, or processing was refused or deferred using [pipeline-concurrency](references\u002Fpipeline-concurrency.md).\n- Diagnose unavailable parser services, invalid hints\u002Foptions, missing sidecars, doc-status failures, cancellation, or stale parse\u002Fchunk metadata with [troubleshooting](references\u002Ftroubleshooting.md).\n- Run [scripts\u002Fcheck_pipeline_symbols.py](scripts\u002Fcheck_pipeline_symbols.py) for a safe installed-package import and symbol\u002Fsignature check that does not call parser services, models, credentials, storages, or repository tests.\n\n## Boundaries\n\n- This sub-skill owns `apipeline_enqueue_documents`, `apipeline_process_enqueue_documents`, parse\u002Fanalyze\u002Fprocess staging, parser routing functions, `process_options`, `chunk_options`, sidecar contracts, multimodal sidecar chunks, doc-status metadata carry-over, and `pipeline_status` fields.\n- For direct `LightRAG` construction, `ainsert`, `aquery`, lifecycle, custom KG insertion, embeddings, cache, rerank, and generic library examples, route to `..\u002Fcore-rag\u002FSKILL.md`.\n- For API endpoint request\u002Fresponse details, upload route models, WebUI operation, auth, server startup, or deployment, route to `..\u002Fapi-server\u002FSKILL.md`.\n- For storage backend selection, database services, migrations, workspace isolation, or destructive storage operations, route to `..\u002Fstorage-backends\u002FSKILL.md`.\n- For LLM, VLM, embedding, reranker provider setup, credentials, and provider-specific parameters, route to `..\u002Fllm-providers\u002FSKILL.md`.\n\n## Non-Negotiables\n\n- Treat `process_options` as the exact per-document selector string: `i`, `t`, `e`, `!`, plus at most one chunk selector from `F` \u002F `R` \u002F `V` \u002F `P`.\n- Do not make reusable guidance depend on source-checkout paths, repository scripts, examples, docs, tests, or local environment locations.\n- Be explicit when a parser or modality path needs optional dependencies, an external parser service, embeddings, or VLM\u002FLLM roles; do not present those paths as always-available.\n- Preserve the concurrency contract: `busy` alone does not block enqueue, but `destructive_busy` and `scanning_exclusive` do.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Flightrag\u002Fsub-skills\u002Fdocument-pipeline",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 document-pipeline",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill document-pipeline",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill document-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flightrag\u002Fsub-skills\u002Fdocument-pipeline\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fchunking-and-sidecars.md","REFERENCE","参考文档",6695,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flightrag\u002Fsub-skills\u002Fdocument-pipeline\u002Freferences\u002Fchunking-and-sidecars.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fparser-and-process-options.md",7750,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flightrag\u002Fsub-skills\u002Fdocument-pipeline\u002Freferences\u002Fparser-and-process-options.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fpipeline-concurrency.md",5485,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flightrag\u002Fsub-skills\u002Fdocument-pipeline\u002Freferences\u002Fpipeline-concurrency.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",5245,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flightrag\u002Fsub-skills\u002Fdocument-pipeline\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_pipeline_symbols.py","SCRIPT","脚本",4785,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flightrag\u002Fsub-skills\u002Fdocument-pipeline\u002Fscripts\u002Fcheck_pipeline_symbols.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]