[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792E1BCFD7TYDTD1XJFKHAM":3,"skill-same:01M792E1BCFD7TYDTD1XJFKHAM":52},{"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},"01M792E1BCFD7TYDTD1XJFKHAM","retrieval-client",null,"Guides PageIndexClient workspace persistence, document metadata, structure retrieval, page content lookup, and agentic RAG tools.","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\u002Fpage-index\u002Fsub-skills\u002Fretrieval-client\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: retrieval-client\ndescription: \"Guides PageIndexClient workspace persistence, document metadata,\n  structure retrieval, page content lookup, and agentic RAG tools.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Retrieval Client\n\nUse this sub-skill when the user mentions `PageIndexClient`, workspace directories, document ids, `get_document`, `get_document_structure`, `get_page_content`, cached JSON documents, or agentic vectorless RAG.\n\nDo not use it for initial tree construction unless the user specifically wants `PageIndexClient.index()`:\n\n- classic PDF tree extraction -> `..\u002Fpdf-indexing\u002F`\n- Flash PDF tree extraction -> `..\u002Fflash-indexing\u002F`\n- Markdown tree extraction -> `..\u002Fmarkdown-indexing\u002F`\n\n## Required context\n\nRead these shared references as needed:\n\n- `..\u002F..\u002Freferences\u002Fworkflows.md#workspace-retrieval-and-agentic-qa` for workflow recipes.\n- `..\u002F..\u002Freferences\u002Fapi-reference.md#retrieval-client-and-low-level-tools` for verified signatures.\n- `..\u002F..\u002Freferences\u002Fdata-formats.md#workspace-layout` for workspace JSON structure.\n- `..\u002F..\u002Freferences\u002Fconfiguration.md#credentials` for model key behavior.\n- `..\u002F..\u002Freferences\u002Ftroubleshooting.md#workspace-retrieval` for common retrieval failures.\n\n## Operating flow\n\n1. Create or load a workspace:\n\n   ```python\n   from pageindex import PageIndexClient\n\n   client = PageIndexClient(workspace=\"workspace\")\n   ```\n\n2. Index only when the user wants to build or refresh a document entry:\n\n   ```python\n   doc_id = client.index(\"document.pdf\")\n   ```\n\n   `index()` calls the PDF or Markdown tree builders and can require model credentials.\n\n3. Retrieve in the standard order for agent workflows:\n\n   ```python\n   print(client.get_document(doc_id))\n   print(client.get_document_structure(doc_id))\n   print(client.get_page_content(doc_id, \"5-7\"))\n   ```\n\n4. For an offline workspace smoke check, run `python scripts\u002Fworkspace_smoke.py` from this sub-skill directory.\n\n## Agentic RAG pattern\n\nThe repo's agentic demo pattern exposes three tools:\n\n- `get_document()` — confirm document metadata and page or line count.\n- `get_document_structure()` — inspect the tree without text fields.\n- `get_page_content(pages)` — fetch tight ranges such as `\"5-7\"` or `\"12\"`.\n\nKeep agent instructions strict:\n\n- Call metadata first.\n- Use structure to decide relevant ranges.\n- Fetch only tight ranges; never fetch the entire document by default.\n- Answer only from tool outputs.\n\nThe OpenAI Agents SDK route needs the optional `openai-agents` dependency plus the user's model credentials. Loading an existing workspace and calling retrieval helpers can be fully offline.\n\n## Common decisions\n\n- If a workspace JSON is corrupt, rebuild it by re-indexing or repair `_meta.json` plus the document JSON file.\n- If `get_page_content` errors, validate the page selector syntax before rerunning.\n- If a Markdown document is queried, explain that ranges refer to heading line numbers rather than PDF pages.\n- If the user wants improved extraction quality before retrieval, route back to the relevant indexing sub-skill.\n","# Retrieval Client\n\nUse this sub-skill when the user mentions `PageIndexClient`, workspace directories, document ids, `get_document`, `get_document_structure`, `get_page_content`, cached JSON documents, or agentic vectorless RAG.\n\nDo not use it for initial tree construction unless the user specifically wants `PageIndexClient.index()`:\n\n- classic PDF tree extraction -> `..\u002Fpdf-indexing\u002F`\n- Flash PDF tree extraction -> `..\u002Fflash-indexing\u002F`\n- Markdown tree extraction -> `..\u002Fmarkdown-indexing\u002F`\n\n## Required context\n\nRead these shared references as needed:\n\n- `..\u002F..\u002Freferences\u002Fworkflows.md#workspace-retrieval-and-agentic-qa` for workflow recipes.\n- `..\u002F..\u002Freferences\u002Fapi-reference.md#retrieval-client-and-low-level-tools` for verified signatures.\n- `..\u002F..\u002Freferences\u002Fdata-formats.md#workspace-layout` for workspace JSON structure.\n- `..\u002F..\u002Freferences\u002Fconfiguration.md#credentials` for model key behavior.\n- `..\u002F..\u002Freferences\u002Ftroubleshooting.md#workspace-retrieval` for common retrieval failures.\n\n## Operating flow\n\n1. Create or load a workspace:\n\n   ```python\n   from pageindex import PageIndexClient\n\n   client = PageIndexClient(workspace=\"workspace\")\n   ```\n\n2. Index only when the user wants to build or refresh a document entry:\n\n   ```python\n   doc_id = client.index(\"document.pdf\")\n   ```\n\n   `index()` calls the PDF or Markdown tree builders and can require model credentials.\n\n3. Retrieve in the standard order for agent workflows:\n\n   ```python\n   print(client.get_document(doc_id))\n   print(client.get_document_structure(doc_id))\n   print(client.get_page_content(doc_id, \"5-7\"))\n   ```\n\n4. For an offline workspace smoke check, run `python scripts\u002Fworkspace_smoke.py` from this sub-skill directory.\n\n## Agentic RAG pattern\n\nThe repo's agentic demo pattern exposes three tools:\n\n- `get_document()` — confirm document metadata and page or line count.\n- `get_document_structure()` — inspect the tree without text fields.\n- `get_page_content(pages)` — fetch tight ranges such as `\"5-7\"` or `\"12\"`.\n\nKeep agent instructions strict:\n\n- Call metadata first.\n- Use structure to decide relevant ranges.\n- Fetch only tight ranges; never fetch the entire document by default.\n- Answer only from tool outputs.\n\nThe OpenAI Agents SDK route needs the optional `openai-agents` dependency plus the user's model credentials. Loading an existing workspace and calling retrieval helpers can be fully offline.\n\n## Common decisions\n\n- If a workspace JSON is corrupt, rebuild it by re-indexing or repair `_meta.json` plus the document JSON file.\n- If `get_page_content` errors, validate the page selector syntax before rerunning.\n- If a Markdown document is queried, explain that ranges refer to heading line numbers rather than PDF pages.\n- If the user wants improved extraction quality before retrieval, route back to the relevant indexing sub-skill.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fpage-index\u002Fsub-skills\u002Fretrieval-client",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 retrieval-client",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill retrieval-client",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill retrieval-client","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpage-index\u002Fsub-skills\u002Fretrieval-client\u002FSKILL.md",[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"scripts\u002Fworkspace_smoke.py","SCRIPT","脚本",2352,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpage-index\u002Fsub-skills\u002Fretrieval-client\u002Fscripts\u002Fworkspace_smoke.py",[53,61,68,75,82,89],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"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":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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",[],[]]