[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FABJSQ5BWG7DYPG1RTNGSD":3,"skill-same:01M7FABJSQ5BWG7DYPG1RTNGSD":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7FABJSQ5BWG7DYPG1RTNGSD","api-and-indexing",null,"Build, update, search, filter, and safely manage LEANN indexes through the Python API, including precomputed embeddings and hybrid or grep retrieval.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Fapi-and-indexing\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: api-and-indexing\ndescription: \"Build, update, search, filter, and safely manage LEANN indexes\n  through the Python API, including precomputed embeddings and hybrid or grep\n  retrieval.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# LEANN API and Indexing\n\nUse this sub-skill for the Python lifecycle around `LeannBuilder`,\n`LeannSearcher`, passage metadata, precomputed vectors, low-level updates,\nmetadata filters, BM25\u002Fvector fusion, grep retrieval, and resource cleanup.\n\n## Route by task\n\n- Verify constructors, method signatures, defaults, result fields, and artifact\n  names in [API reference](references\u002Fapi-reference.md).\n- Implement a new build, precomputed-vector build, update, staged replacement,\n  or cleanup flow with [indexing and search workflows](references\u002Findexing-and-search-workflows.md).\n- Configure post-search metadata filters, pure BM25, hybrid retrieval, or grep\n  with [metadata, hybrid, and grep](references\u002Fmetadata-hybrid-and-grep.md).\n- Diagnose bad base paths, missing artifacts, dimension or ID mismatches,\n  update duplication, BM25\u002Fgrep failures, and daemon cleanup with\n  [troubleshooting](references\u002Ftroubleshooting.md).\n- Prove a local installation and HNSW backend without a model download by\n  running the bundled [precomputed-index smoke](scripts\u002Fprecomputed_index_smoke.py).\n\n## Operating rules\n\n1. Treat `index_path` as a **base path**, not as the `.meta.json`, `.index`, or\n   passage file. Keep every sibling artifact together.\n2. Use a new staging directory for builds and critical updates. Validate it,\n   then publish the whole directory; never overwrite unrelated files or delete\n   a parent directory in response to an error message.\n3. Give every passage a unique string ID. For precomputed arrays, make the\n   passage IDs and supplied vector IDs identical and order-aligned.\n4. Set build and query embedding configuration consistently. A precomputed\n   build avoids document embedding, but semantic search still needs a query\n   embedding; pure BM25 and grep do not.\n5. Configure recomputation on `LeannSearcher`; the per-call search override is\n   deprecated. Disable warmup and daemon use for offline BM25-only checks.\n6. Always call `cleanup()` or use `with LeannSearcher(...) as searcher:`.\n7. Treat filters as post-retrieval filters. Missing or unsupported fields do\n   not raise by default; they remove the affected result.\n8. Choose update behavior from stored backend\u002Findex metadata. IVF supports\n   remove-then-add; HNSW only supports low-level append on non-compact indexes.\n\n## Boundaries\n\n- For CLI build\u002Fsearch, daemon commands, filesystem watching, or idempotent\n  document builds, use [CLI operations](..\u002Fcli-operations\u002FSKILL.md).\n- For HNSW, IVF, DiskANN algorithms, storage modes, and backend tuning, use\n  [backends and storage](..\u002Fbackends-and-storage\u002FSKILL.md).\n- For embedding modes, model\u002Fprovider credentials, prompt templates, and chat\n  providers, use [embeddings and chat](..\u002Fembeddings-and-chat\u002FSKILL.md).\n- For document, email, browser, chat-history, or code ingestion applications,\n  use [RAG applications](..\u002Frag-applications\u002FSKILL.md).\n","# LEANN API and Indexing\n\nUse this sub-skill for the Python lifecycle around `LeannBuilder`,\n`LeannSearcher`, passage metadata, precomputed vectors, low-level updates,\nmetadata filters, BM25\u002Fvector fusion, grep retrieval, and resource cleanup.\n\n## Route by task\n\n- Verify constructors, method signatures, defaults, result fields, and artifact\n  names in [API reference](references\u002Fapi-reference.md).\n- Implement a new build, precomputed-vector build, update, staged replacement,\n  or cleanup flow with [indexing and search workflows](references\u002Findexing-and-search-workflows.md).\n- Configure post-search metadata filters, pure BM25, hybrid retrieval, or grep\n  with [metadata, hybrid, and grep](references\u002Fmetadata-hybrid-and-grep.md).\n- Diagnose bad base paths, missing artifacts, dimension or ID mismatches,\n  update duplication, BM25\u002Fgrep failures, and daemon cleanup with\n  [troubleshooting](references\u002Ftroubleshooting.md).\n- Prove a local installation and HNSW backend without a model download by\n  running the bundled [precomputed-index smoke](scripts\u002Fprecomputed_index_smoke.py).\n\n## Operating rules\n\n1. Treat `index_path` as a **base path**, not as the `.meta.json`, `.index`, or\n   passage file. Keep every sibling artifact together.\n2. Use a new staging directory for builds and critical updates. Validate it,\n   then publish the whole directory; never overwrite unrelated files or delete\n   a parent directory in response to an error message.\n3. Give every passage a unique string ID. For precomputed arrays, make the\n   passage IDs and supplied vector IDs identical and order-aligned.\n4. Set build and query embedding configuration consistently. A precomputed\n   build avoids document embedding, but semantic search still needs a query\n   embedding; pure BM25 and grep do not.\n5. Configure recomputation on `LeannSearcher`; the per-call search override is\n   deprecated. Disable warmup and daemon use for offline BM25-only checks.\n6. Always call `cleanup()` or use `with LeannSearcher(...) as searcher:`.\n7. Treat filters as post-retrieval filters. Missing or unsupported fields do\n   not raise by default; they remove the affected result.\n8. Choose update behavior from stored backend\u002Findex metadata. IVF supports\n   remove-then-add; HNSW only supports low-level append on non-compact indexes.\n\n## Boundaries\n\n- For CLI build\u002Fsearch, daemon commands, filesystem watching, or idempotent\n  document builds, use [CLI operations](..\u002Fcli-operations\u002FSKILL.md).\n- For HNSW, IVF, DiskANN algorithms, storage modes, and backend tuning, use\n  [backends and storage](..\u002Fbackends-and-storage\u002FSKILL.md).\n- For embedding modes, model\u002Fprovider credentials, prompt templates, and chat\n  providers, use [embeddings and chat](..\u002Fembeddings-and-chat\u002FSKILL.md).\n- For document, email, browser, chat-history, or code ingestion applications,\n  use [RAG applications](..\u002Frag-applications\u002FSKILL.md).\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fleann\u002Fsub-skills\u002Fapi-and-indexing",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill api-and-indexing",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill api-and-indexing",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill api-and-indexing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Fapi-and-indexing\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fapi-reference.md","REFERENCE","参考文档",9085,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Fapi-and-indexing\u002Freferences\u002Fapi-reference.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Findexing-and-search-workflows.md",8502,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Fapi-and-indexing\u002Freferences\u002Findexing-and-search-workflows.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fmetadata-hybrid-and-grep.md",6787,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Fapi-and-indexing\u002Freferences\u002Fmetadata-hybrid-and-grep.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ftroubleshooting.md",10259,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Fapi-and-indexing\u002Freferences\u002Ftroubleshooting.md",[67,74,79,86,93,100],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":75,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]