[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XGNDJRR2HZ3APRCPXN2ZP":3,"skill-same:01M78XGNDJRR2HZ3APRCPXN2ZP":62},{"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},"01M78XGNDJRR2HZ3APRCPXN2ZP","search-indexing",null,"Operate and troubleshoot Gerev search, indexing, parsers, SQLite queues, ranking, and startup\u002Fstatus behavior.","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\u002Fgerev\u002Fsub-skills\u002Fsearch-indexing\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: search-indexing\ndescription: \"Operate and troubleshoot Gerev search, indexing, parsers, SQLite\n  queues, ranking, and startup\u002Fstatus behavior.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Gerev Search and Indexing\n\nUse this sub-skill when a task involves Gerev's search API, index maintenance, ranking stack, document parser helpers, SQLite-backed queues, or the startup\u002Fstatus behavior that makes search usable.\n\n## Best-fit tasks\n\n- Explain or debug `GET \u002Fapi\u002Fv1\u002Fsearch` results, empty result sets, slow ranking, answer snippets, parent\u002Fchild result nesting, or score interpretation.\n- Reason about BM25, Faiss, SentenceTransformer, CrossEncoder, and Transformers QA model interactions without opening the source checkout.\n- Inspect index persistence, SQLite queues, database\u002Findex file placement, and status counters.\n- Diagnose startup failures caused by model cache downloads, NLTK data, CUDA availability, storage permissions, singleton indexes, or the current PDF parser import defect.\n- Understand safe parser helper behavior for TXT, HTML, DOCX, PPTX, and PDF text extraction.\n\n## Start here\n\n1. Read [`search-indexing-stack.md`](references\u002Fsearch-indexing-stack.md) for the end-to-end flow, data model, parser map, queue behavior, index persistence, and startup\u002Fstatus route semantics.\n2. For failures, use [`troubleshooting.md`](references\u002Ftroubleshooting.md) first. It covers cold Hugging Face caches, NLTK `punkt`\u002F`punkt_tab`, CUDA fallback, storage path issues, stale indexes, queue stalls, and the known `split_PDF_into_paragraphs` import defect.\n3. When you have access to a Gerev checkout or storage directory, run the bundled [`inspect_search_indexing.py`](scripts\u002Finspect_search_indexing.py) read-only helper from this sub-skill directory or with the equivalent path to the bundled script:\n\n   ```bash\n   python scripts\u002Finspect_search_indexing.py --app-dir \u003Ccheckout>\u002Fapp --storage-dir \u003Cstorage-dir> --sqlite-details\n   ```\n\n   Omit `--storage-dir` to let the helper infer Docker versus home storage. Add `--json` for machine-readable output or `--strict` when a CI-style nonzero exit is useful.\n\n## High-signal routing checks\n\n- Search import\u002Fstartup touches model loading at import time through `models.py`; do not import the full app casually on a cold or offline host unless model caches are expected to exist.\n- `search_logic.py` calls `nltk.download('punkt')` at import time. A downloader warning can be nonfatal when tokenizer data is already present, but missing `punkt` or `punkt_tab` will break BM25 tokenization on modern NLTK.\n- `app\u002Fmain.py` startup must create `FaissIndex` and `Bm25Index` singletons before search is used; direct calls to `search_documents()` without startup can raise \"Index is not initialized\".\n- The current source contains an app-startup blocker: `indexing\u002Findex_documents.py` imports `split_PDF_into_paragraphs` from `parsers\u002Fpdf.py`, but `pdf.py` defines only `pdf_to_text` and `pdf_to_textV2`. Treat this as a source defect to document or fix only when the user authorizes code changes.\n- Search\u002Findex storage is under `\u002Fopt\u002Fstorage` in Docker-like mode and under a user home storage directory otherwise. Mismatched environment, user, or permissions can make the app appear to have no documents or no indexes.\n\n## Boundaries\n\nIncluded here: search query flow, BM25\u002FFaiss ranking, transformer model loading, NLTK data, parser helpers, SQLite index\u002Ftask queues, indexing background loop, SQLAlchemy search schemas, and the search\u002Fstatus\u002Fstartup parts of the FastAPI app.\n\nDo not use this sub-skill for connector credential setup, connector-specific API behavior, Docker image build\u002Frelease automation, or frontend UX changes except where those surfaces directly affect search\u002Fstatus interpretation.\n","# Gerev Search and Indexing\n\nUse this sub-skill when a task involves Gerev's search API, index maintenance, ranking stack, document parser helpers, SQLite-backed queues, or the startup\u002Fstatus behavior that makes search usable.\n\n## Best-fit tasks\n\n- Explain or debug `GET \u002Fapi\u002Fv1\u002Fsearch` results, empty result sets, slow ranking, answer snippets, parent\u002Fchild result nesting, or score interpretation.\n- Reason about BM25, Faiss, SentenceTransformer, CrossEncoder, and Transformers QA model interactions without opening the source checkout.\n- Inspect index persistence, SQLite queues, database\u002Findex file placement, and status counters.\n- Diagnose startup failures caused by model cache downloads, NLTK data, CUDA availability, storage permissions, singleton indexes, or the current PDF parser import defect.\n- Understand safe parser helper behavior for TXT, HTML, DOCX, PPTX, and PDF text extraction.\n\n## Start here\n\n1. Read [`search-indexing-stack.md`](references\u002Fsearch-indexing-stack.md) for the end-to-end flow, data model, parser map, queue behavior, index persistence, and startup\u002Fstatus route semantics.\n2. For failures, use [`troubleshooting.md`](references\u002Ftroubleshooting.md) first. It covers cold Hugging Face caches, NLTK `punkt`\u002F`punkt_tab`, CUDA fallback, storage path issues, stale indexes, queue stalls, and the known `split_PDF_into_paragraphs` import defect.\n3. When you have access to a Gerev checkout or storage directory, run the bundled [`inspect_search_indexing.py`](scripts\u002Finspect_search_indexing.py) read-only helper from this sub-skill directory or with the equivalent path to the bundled script:\n\n   ```bash\n   python scripts\u002Finspect_search_indexing.py --app-dir \u003Ccheckout>\u002Fapp --storage-dir \u003Cstorage-dir> --sqlite-details\n   ```\n\n   Omit `--storage-dir` to let the helper infer Docker versus home storage. Add `--json` for machine-readable output or `--strict` when a CI-style nonzero exit is useful.\n\n## High-signal routing checks\n\n- Search import\u002Fstartup touches model loading at import time through `models.py`; do not import the full app casually on a cold or offline host unless model caches are expected to exist.\n- `search_logic.py` calls `nltk.download('punkt')` at import time. A downloader warning can be nonfatal when tokenizer data is already present, but missing `punkt` or `punkt_tab` will break BM25 tokenization on modern NLTK.\n- `app\u002Fmain.py` startup must create `FaissIndex` and `Bm25Index` singletons before search is used; direct calls to `search_documents()` without startup can raise \"Index is not initialized\".\n- The current source contains an app-startup blocker: `indexing\u002Findex_documents.py` imports `split_PDF_into_paragraphs` from `parsers\u002Fpdf.py`, but `pdf.py` defines only `pdf_to_text` and `pdf_to_textV2`. Treat this as a source defect to document or fix only when the user authorizes code changes.\n- Search\u002Findex storage is under `\u002Fopt\u002Fstorage` in Docker-like mode and under a user home storage directory otherwise. Mismatched environment, user, or permissions can make the app appear to have no documents or no indexes.\n\n## Boundaries\n\nIncluded here: search query flow, BM25\u002FFaiss ranking, transformer model loading, NLTK data, parser helpers, SQLite index\u002Ftask queues, indexing background loop, SQLAlchemy search schemas, and the search\u002Fstatus\u002Fstartup parts of the FastAPI app.\n\nDo not use this sub-skill for connector credential setup, connector-specific API behavior, Docker image build\u002Frelease automation, or frontend UX changes except where those surfaces directly affect search\u002Fstatus interpretation.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fgerev\u002Fsub-skills\u002Fsearch-indexing",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 search-indexing",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill search-indexing",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill search-indexing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgerev\u002Fsub-skills\u002Fsearch-indexing\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fsearch-indexing-stack.md","REFERENCE","参考文档",11346,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgerev\u002Fsub-skills\u002Fsearch-indexing\u002Freferences\u002Fsearch-indexing-stack.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",7767,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgerev\u002Fsub-skills\u002Fsearch-indexing\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Finspect_search_indexing.py","SCRIPT","脚本",13095,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fgerev\u002Fsub-skills\u002Fsearch-indexing\u002Fscripts\u002Finspect_search_indexing.py",[63,71,78,85,92,99],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]