[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YTFGE0EXEYZDVBDS46RZK":3,"skill-same:01M78YTFGE0EXEYZDVBDS46RZK":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},"01M78YTFGE0EXEYZDVBDS46RZK","rag-core",null,"Build and troubleshoot programmatic Kotaemon RAG pipelines with core components, documents, indexes, retrieval, reranking, QA, reasoning, and citations.","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\u002Fkotaemon\u002Fsub-skills\u002Frag-core\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rag-core\ndescription: \"Build and troubleshoot programmatic Kotaemon RAG pipelines with\n  core components, documents, indexes, retrieval, reranking, QA, reasoning, and\n  citations.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Kotaemon RAG Core\n\nUse this sub-skill when an agent needs to compose or debug Kotaemon's programmatic RAG layer: component graphs, document schemas, vector indexing\u002Fretrieval, reranking, evidence formatting, prompt templates, reasoning chains, QA output metadata, and citation traces.\n\nRoute elsewhere when the task is primarily:\n\n- App setup, `.env`, `flowsettings.py`, Gradio login, Docker, PDF.js, or migration operations: use `app-deployment`.\n- Model credentials, provider endpoints, local LLM servers, embedding model setup, reranker provider setup, or GraphRAG provider toggles: use `model-providers`.\n- Loading\u002Fparsing\u002Fsplitting source files, OCR, table extraction, or parser optional dependencies: use `document-ingestion`.\n- ktem app extensions, custom pages, flow registration, templates, or plugin UI work: use `extensions`.\n\n## Start Here\n\n1. Identify the layer: schema\u002Fcomponent contract, indexing, retrieval, reranking, QA\u002Fcitation, prompt\u002Freasoning, or storage abstraction.\n2. Use `references\u002Fapi-reference.md` for class contracts and import paths.\n3. Use `references\u002Frag-workflows.md` for composition patterns and metadata-preserving examples.\n4. Use `references\u002Ftroubleshooting.md` for common failure modes before changing provider or ingestion code.\n5. Run `scripts\u002Finspect_pipeline_components.py --repo-root \u003Crepo>` when source or environment drift is suspected.\n\n## Core Mental Model\n\n- `BaseComponent` is the composable unit. Implement `run(...)`; call components directly with `component(...)` for normal execution. `invoke`, `stream`, and async variants exist for components that implement them, but `run` is the common subclass contract.\n- `Document` carries `content`, `text`, `metadata`, optional `source`, and optional `channel`. `RetrievedDocument` extends it with `score` and `retrieval_metadata`.\n- `VectorIndexing` embeds documents, writes vectors to a `BaseVectorStore`, and optionally stores full `Document` objects in a `BaseDocumentStore`.\n- `VectorRetrieval` embeds the query, fetches ids\u002Fscores from the vector store, loads documents from the docstore, returns `RetrievedDocument` objects, and can apply rerankers.\n- QA flows convert retrieved documents to evidence text, generate answers, and attach metadata such as `citation`, `qa_score`, `mindmap`, and `citation_viz`.\n\n## Difficult Cases\n\n- Low-confidence cited answer: trace `RetrievedDocument.score`, `retrieval_metadata`, reranker output, `qa_score`, and citation spans through `references\u002Frag-workflows.md`; route provider scoring failures to `..\u002Fmodel-providers\u002FSKILL.md` and parser evidence gaps to `..\u002Fdocument-ingestion\u002FSKILL.md`.\n- Custom component pipeline loses metadata: check the `BaseComponent.run(...)` boundary, preserve `Document.metadata` when transforming chunks, and use `scripts\u002Finspect_pipeline_components.py` to confirm the expected schema\u002Findex classes are present.\n\n## Bundled References\n\n- `references\u002Fapi-reference.md` - core classes, import paths, method contracts, and metadata expectations.\n- `references\u002Frag-workflows.md` - indexing\u002Fretrieval\u002FQA wiring patterns, prompt and reasoning usage, and safe introspection.\n- `references\u002Ftroubleshooting.md` - provider object, embedding\u002Fvectorstore mismatch, empty retrieval, metadata loss, citation confidence, prompt variables, missing reranker, and call-style failures.\n\n## Bundled Script\n\n```bash\npython skills\u002Fkotaemon\u002Fsub-skills\u002Frag-core\u002Fscripts\u002Finspect_pipeline_components.py --repo-root \u003Crepo-root>\n```\n\nThe inspector attempts import-light discovery for key Kotaemon modules, then falls back to AST parsing if imports fail because optional provider dependencies are absent. It reports public classes\u002Ffunctions, base classes, method names, signatures when available, and the discovery mode used per module.\n","# Kotaemon RAG Core\n\nUse this sub-skill when an agent needs to compose or debug Kotaemon's programmatic RAG layer: component graphs, document schemas, vector indexing\u002Fretrieval, reranking, evidence formatting, prompt templates, reasoning chains, QA output metadata, and citation traces.\n\nRoute elsewhere when the task is primarily:\n\n- App setup, `.env`, `flowsettings.py`, Gradio login, Docker, PDF.js, or migration operations: use `app-deployment`.\n- Model credentials, provider endpoints, local LLM servers, embedding model setup, reranker provider setup, or GraphRAG provider toggles: use `model-providers`.\n- Loading\u002Fparsing\u002Fsplitting source files, OCR, table extraction, or parser optional dependencies: use `document-ingestion`.\n- ktem app extensions, custom pages, flow registration, templates, or plugin UI work: use `extensions`.\n\n## Start Here\n\n1. Identify the layer: schema\u002Fcomponent contract, indexing, retrieval, reranking, QA\u002Fcitation, prompt\u002Freasoning, or storage abstraction.\n2. Use `references\u002Fapi-reference.md` for class contracts and import paths.\n3. Use `references\u002Frag-workflows.md` for composition patterns and metadata-preserving examples.\n4. Use `references\u002Ftroubleshooting.md` for common failure modes before changing provider or ingestion code.\n5. Run `scripts\u002Finspect_pipeline_components.py --repo-root \u003Crepo>` when source or environment drift is suspected.\n\n## Core Mental Model\n\n- `BaseComponent` is the composable unit. Implement `run(...)`; call components directly with `component(...)` for normal execution. `invoke`, `stream`, and async variants exist for components that implement them, but `run` is the common subclass contract.\n- `Document` carries `content`, `text`, `metadata`, optional `source`, and optional `channel`. `RetrievedDocument` extends it with `score` and `retrieval_metadata`.\n- `VectorIndexing` embeds documents, writes vectors to a `BaseVectorStore`, and optionally stores full `Document` objects in a `BaseDocumentStore`.\n- `VectorRetrieval` embeds the query, fetches ids\u002Fscores from the vector store, loads documents from the docstore, returns `RetrievedDocument` objects, and can apply rerankers.\n- QA flows convert retrieved documents to evidence text, generate answers, and attach metadata such as `citation`, `qa_score`, `mindmap`, and `citation_viz`.\n\n## Difficult Cases\n\n- Low-confidence cited answer: trace `RetrievedDocument.score`, `retrieval_metadata`, reranker output, `qa_score`, and citation spans through `references\u002Frag-workflows.md`; route provider scoring failures to `..\u002Fmodel-providers\u002FSKILL.md` and parser evidence gaps to `..\u002Fdocument-ingestion\u002FSKILL.md`.\n- Custom component pipeline loses metadata: check the `BaseComponent.run(...)` boundary, preserve `Document.metadata` when transforming chunks, and use `scripts\u002Finspect_pipeline_components.py` to confirm the expected schema\u002Findex classes are present.\n\n## Bundled References\n\n- `references\u002Fapi-reference.md` - core classes, import paths, method contracts, and metadata expectations.\n- `references\u002Frag-workflows.md` - indexing\u002Fretrieval\u002FQA wiring patterns, prompt and reasoning usage, and safe introspection.\n- `references\u002Ftroubleshooting.md` - provider object, embedding\u002Fvectorstore mismatch, empty retrieval, metadata loss, citation confidence, prompt variables, missing reranker, and call-style failures.\n\n## Bundled Script\n\n```bash\npython skills\u002Fkotaemon\u002Fsub-skills\u002Frag-core\u002Fscripts\u002Finspect_pipeline_components.py --repo-root \u003Crepo-root>\n```\n\nThe inspector attempts import-light discovery for key Kotaemon modules, then falls back to AST parsing if imports fail because optional provider dependencies are absent. It reports public classes\u002Ffunctions, base classes, method names, signatures when available, and the discovery mode used per module.\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\u002Fkotaemon\u002Fsub-skills\u002Frag-core",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 rag-core",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill rag-core",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill rag-core","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkotaemon\u002Fsub-skills\u002Frag-core\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",13897,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkotaemon\u002Fsub-skills\u002Frag-core\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frag-workflows.md",10832,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkotaemon\u002Fsub-skills\u002Frag-core\u002Freferences\u002Frag-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",9967,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkotaemon\u002Fsub-skills\u002Frag-core\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Finspect_pipeline_components.py","SCRIPT","脚本",15148,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkotaemon\u002Fsub-skills\u002Frag-core\u002Fscripts\u002Finspect_pipeline_components.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",[],[]]