[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792F5TYK8D1R2H33AYMSRNV":3,"skill-same:01M792F5TYK8D1R2H33AYMSRNV":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},"01M792F5TYK8D1R2H33AYMSRNV","agentic-rag",null,"Use PaperQA's Python API for agentic and manual scientific RAG over Docs, Doc, Text, ask, agent_query, evidence retrieval, answers, callbacks, and async boundaries.","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\u002Fpaper-qa\u002Fsub-skills\u002Fagentic-rag\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agentic-rag\ndescription: \"Use PaperQA's Python API for agentic and manual scientific RAG\n  over Docs, Doc, Text, ask, agent_query, evidence retrieval, answers,\n  callbacks, and async boundaries.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# PaperQA Agentic RAG API\n\nUse this sub-skill when the task is to run PaperQA from Python: build `Docs`, add `Doc`\u002F`Text` objects or local files\u002Ftexts, retrieve evidence with `Docs.aget_evidence`, generate answers with `Docs.aquery`, or use `ask`\u002F`agent_query` with fake or ToolSelector agents.\n\n## Route here for\n\n- Manual `Docs` workflows: `aadd`, `aadd_file`, `aadd_url`, `aadd_texts`, `aget_evidence`, `aquery`.\n- Agent workflows: `ask`, `agent_query`, `agent_type=\"fake\"`, default `ToolSelector`, agent callbacks, answer\u002Fsession\u002Fstatus outputs.\n- No-network object smokes and pre-chunked text ingestion with deferred embeddings.\n- Understanding `PQASession`, `Context`, `AnswerResponse`, citations, references, and source\u002Fcontext outputs.\n\n## Route elsewhere\n\n- CLI commands, index build\u002Fsearch\u002Freuse, `pqa ask\u002Fsearch\u002Findex`, manifests: [cli-and-indexing](..\u002Fcli-and-indexing\u002FSKILL.md).\n- Parser choice, PDF\u002Fmedia\u002FOffice\u002Fcode parsing details, impossible\u002Fcorrupt documents: [docs-and-parsing](..\u002Fdocs-and-parsing\u002FSKILL.md).\n- Provider\u002Fmodel\u002Fsettings tuning, local embeddings, Qdrant, prompts beyond API usage: [settings-and-configuration](..\u002Fsettings-and-configuration\u002FSKILL.md).\n- Metadata clients, DOI\u002Ftitle hydration, OpenReview\u002FZotero\u002FClinicalTrials sources: [metadata-and-sources](..\u002Fmetadata-and-sources\u002FSKILL.md).\n\n## Start with the bundled references\n\n1. Check verified signatures and return shapes in [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n2. Use self-contained recipes in [references\u002Fworkflows.md](references\u002Fworkflows.md).\n3. Diagnose common runtime failures with [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n4. For a safe no-network smoke, run [scripts\u002Fsmoke_docs_objects.py](scripts\u002Fsmoke_docs_objects.py) with `--help`, then `smoke`.\n\n## Operating cautions\n\n- Prefer async APIs (`await docs.aadd_texts(...)`, `await docs.aquery(...)`) in notebooks, web servers, and other running event loops.\n- Passing a citation and disabling metadata hydration avoids citation-inference LLM calls and metadata-provider network calls during manual file addition.\n- `Settings(parsing={\"defer_embedding\": True})` defers embeddings at ingest; retrieval\u002Fanswering can still call the configured embedding and LLM providers.\n- The no-network smoke only proves installed object\u002FAPI construction; it does not validate provider credentials, embeddings, parsing quality, or answer quality.\n","# PaperQA Agentic RAG API\n\nUse this sub-skill when the task is to run PaperQA from Python: build `Docs`, add `Doc`\u002F`Text` objects or local files\u002Ftexts, retrieve evidence with `Docs.aget_evidence`, generate answers with `Docs.aquery`, or use `ask`\u002F`agent_query` with fake or ToolSelector agents.\n\n## Route here for\n\n- Manual `Docs` workflows: `aadd`, `aadd_file`, `aadd_url`, `aadd_texts`, `aget_evidence`, `aquery`.\n- Agent workflows: `ask`, `agent_query`, `agent_type=\"fake\"`, default `ToolSelector`, agent callbacks, answer\u002Fsession\u002Fstatus outputs.\n- No-network object smokes and pre-chunked text ingestion with deferred embeddings.\n- Understanding `PQASession`, `Context`, `AnswerResponse`, citations, references, and source\u002Fcontext outputs.\n\n## Route elsewhere\n\n- CLI commands, index build\u002Fsearch\u002Freuse, `pqa ask\u002Fsearch\u002Findex`, manifests: [cli-and-indexing](..\u002Fcli-and-indexing\u002FSKILL.md).\n- Parser choice, PDF\u002Fmedia\u002FOffice\u002Fcode parsing details, impossible\u002Fcorrupt documents: [docs-and-parsing](..\u002Fdocs-and-parsing\u002FSKILL.md).\n- Provider\u002Fmodel\u002Fsettings tuning, local embeddings, Qdrant, prompts beyond API usage: [settings-and-configuration](..\u002Fsettings-and-configuration\u002FSKILL.md).\n- Metadata clients, DOI\u002Ftitle hydration, OpenReview\u002FZotero\u002FClinicalTrials sources: [metadata-and-sources](..\u002Fmetadata-and-sources\u002FSKILL.md).\n\n## Start with the bundled references\n\n1. Check verified signatures and return shapes in [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n2. Use self-contained recipes in [references\u002Fworkflows.md](references\u002Fworkflows.md).\n3. Diagnose common runtime failures with [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n4. For a safe no-network smoke, run [scripts\u002Fsmoke_docs_objects.py](scripts\u002Fsmoke_docs_objects.py) with `--help`, then `smoke`.\n\n## Operating cautions\n\n- Prefer async APIs (`await docs.aadd_texts(...)`, `await docs.aquery(...)`) in notebooks, web servers, and other running event loops.\n- Passing a citation and disabling metadata hydration avoids citation-inference LLM calls and metadata-provider network calls during manual file addition.\n- `Settings(parsing={\"defer_embedding\": True})` defers embeddings at ingest; retrieval\u002Fanswering can still call the configured embedding and LLM providers.\n- The no-network smoke only proves installed object\u002FAPI construction; it does not validate provider credentials, embeddings, parsing quality, or answer quality.\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\u002Fpaper-qa\u002Fsub-skills\u002Fagentic-rag",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 agentic-rag",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill agentic-rag",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill agentic-rag","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaper-qa\u002Fsub-skills\u002Fagentic-rag\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",12218,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaper-qa\u002Fsub-skills\u002Fagentic-rag\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",10833,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaper-qa\u002Fsub-skills\u002Fagentic-rag\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",12624,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaper-qa\u002Fsub-skills\u002Fagentic-rag\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fsmoke_docs_objects.py","SCRIPT","脚本",5379,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaper-qa\u002Fsub-skills\u002Fagentic-rag\u002Fscripts\u002Fsmoke_docs_objects.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",[],[]]