[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FAC2TW7QQJBAHVBB5DHSVE":3,"skill-same:01M7FAC2TW7QQJBAHVBB5DHSVE":70},{"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},"01M7FAC2TW7QQJBAHVBB5DHSVE","rag-applications",null,"Compose and validate LEANN RAG workflows for documents, code, personal or live data, semantic file search, images, and visual PDFs without exposing private data or triggering heavy setup.","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\u002Frag-applications\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: rag-applications\ndescription: \"Compose and validate LEANN RAG workflows for documents, code,\n  personal or live data, semantic file search, images, and visual PDFs without\n  exposing private data or triggering heavy setup.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# LEANN RAG Applications\n\nUse this sub-skill to turn a source into LEANN passages, preserve useful\nmetadata, build a searchable index, and choose retrieval or chat. Start with a\nsmall bounded sample and keep private, live, and multimodal sources opt-in.\n\n## Route by source\n\n- For PDF\u002FTXT\u002FMarkdown documents, code repositories, or mixed code and prose,\n  use [document and code RAG](references\u002Fdocument-and-code-rag.md).\n- For browser history, Apple Mail, Apple Calendar, iMessage, existing WeChat\n  exports, Slack, or Twitter\u002FX, use\n  [personal and live data](references\u002Fpersonal-and-live-data.md).\n- For CLIP image retrieval or ColQwen2\u002FColPali visual-PDF retrieval, use\n  [multimodal RAG](references\u002Fmultimodal-rag.md).\n- For chunk sizes, Abstract Syntax Tree (AST) fallback, file layout, ignore\n  rules, metadata schemas, filters, or temporal search, use\n  [chunking, metadata, and layout](references\u002Fchunking-metadata-and-layout.md).\n- For parser, permission, export, Model Context Protocol (MCP), PDF, image,\n  dependency, or empty-corpus failures, use\n  [troubleshooting](references\u002Ftroubleshooting.md).\n- To produce a validated public `leann` command without executing it, use the\n  bundled [command planner](scripts\u002Fbuild_rag_command.py).\n\n## Operating sequence\n\n1. Classify the source as local public files, private local data, live MCP data,\n   image data, or vision-PDF data. State platform, permissions, export format,\n   dependency, model-cache, and compute prerequisites before access.\n2. Define a passage contract: non-empty `text` plus a flat `metadata` mapping.\n   Select stable source identifiers and use one field name and type per concept.\n3. Load a bounded sample. Exclude hidden, ignored, generated, oversized, empty,\n   corrupt, or unsupported inputs before chunking.\n4. Chunk prose traditionally; use AST-aware chunking only for supported code.\n   Keep the deterministic traditional fallback enabled.\n5. Validate counts and inspect representative passage text and metadata. Stop if\n   zero passages, required source identity is missing, or chunk metadata no\n   longer matches its text.\n6. Build, then search with a query whose expected source is known. Add metadata\n   or time filters only after verifying those fields exist in stored passages.\n7. Add chat only after retrieval is sound. Provider, credential, and model\n   selection belongs to the provider sub-skill.\n\n## Safety rules\n\n- Never export private platform data, open private databases, start an MCP\n  server, read credentials, install system packages, or download models merely\n  to plan a workflow.\n- Never print secrets or include them in generated commands. Pass credentials\n  through the provider or server's documented environment only when the user\n  separately authorizes execution.\n- Treat Slack and Twitter\u002FX readers, Spotlight collection, image encoders, and\n  visual-PDF models as reference-only here. Preflight them; do not run them.\n- Treat an existing WeChat export as input. Do not invoke an exporter or attempt\n  to modify a running client.\n- Do not force rebuilds or include hidden files by default. Preserve the source\n  corpus and write indexes to a separate destination.\n\n## Boundaries\n\n- Backend choice, graph\u002Fsearch parameters, compact storage, recomputation, and\n  index updates: [backends and storage](..\u002Fbackends-and-storage\u002FSKILL.md).\n- Embedding modes, model caches, API credentials, prompt templates, and LLM\u002Fchat\n  providers: [embeddings and chat](..\u002Fembeddings-and-chat\u002FSKILL.md).\n- MCP protocol details, server installation, transport, and deployment:\n  [MCP and services](..\u002Fmcp-and-services\u002FSKILL.md).\n- General Python builder\u002Fsearcher lifecycle and custom precomputed-vector code:\n  [API and indexing](..\u002Fapi-and-indexing\u002FSKILL.md).\n","# LEANN RAG Applications\n\nUse this sub-skill to turn a source into LEANN passages, preserve useful\nmetadata, build a searchable index, and choose retrieval or chat. Start with a\nsmall bounded sample and keep private, live, and multimodal sources opt-in.\n\n## Route by source\n\n- For PDF\u002FTXT\u002FMarkdown documents, code repositories, or mixed code and prose,\n  use [document and code RAG](references\u002Fdocument-and-code-rag.md).\n- For browser history, Apple Mail, Apple Calendar, iMessage, existing WeChat\n  exports, Slack, or Twitter\u002FX, use\n  [personal and live data](references\u002Fpersonal-and-live-data.md).\n- For CLIP image retrieval or ColQwen2\u002FColPali visual-PDF retrieval, use\n  [multimodal RAG](references\u002Fmultimodal-rag.md).\n- For chunk sizes, Abstract Syntax Tree (AST) fallback, file layout, ignore\n  rules, metadata schemas, filters, or temporal search, use\n  [chunking, metadata, and layout](references\u002Fchunking-metadata-and-layout.md).\n- For parser, permission, export, Model Context Protocol (MCP), PDF, image,\n  dependency, or empty-corpus failures, use\n  [troubleshooting](references\u002Ftroubleshooting.md).\n- To produce a validated public `leann` command without executing it, use the\n  bundled [command planner](scripts\u002Fbuild_rag_command.py).\n\n## Operating sequence\n\n1. Classify the source as local public files, private local data, live MCP data,\n   image data, or vision-PDF data. State platform, permissions, export format,\n   dependency, model-cache, and compute prerequisites before access.\n2. Define a passage contract: non-empty `text` plus a flat `metadata` mapping.\n   Select stable source identifiers and use one field name and type per concept.\n3. Load a bounded sample. Exclude hidden, ignored, generated, oversized, empty,\n   corrupt, or unsupported inputs before chunking.\n4. Chunk prose traditionally; use AST-aware chunking only for supported code.\n   Keep the deterministic traditional fallback enabled.\n5. Validate counts and inspect representative passage text and metadata. Stop if\n   zero passages, required source identity is missing, or chunk metadata no\n   longer matches its text.\n6. Build, then search with a query whose expected source is known. Add metadata\n   or time filters only after verifying those fields exist in stored passages.\n7. Add chat only after retrieval is sound. Provider, credential, and model\n   selection belongs to the provider sub-skill.\n\n## Safety rules\n\n- Never export private platform data, open private databases, start an MCP\n  server, read credentials, install system packages, or download models merely\n  to plan a workflow.\n- Never print secrets or include them in generated commands. Pass credentials\n  through the provider or server's documented environment only when the user\n  separately authorizes execution.\n- Treat Slack and Twitter\u002FX readers, Spotlight collection, image encoders, and\n  visual-PDF models as reference-only here. Preflight them; do not run them.\n- Treat an existing WeChat export as input. Do not invoke an exporter or attempt\n  to modify a running client.\n- Do not force rebuilds or include hidden files by default. Preserve the source\n  corpus and write indexes to a separate destination.\n\n## Boundaries\n\n- Backend choice, graph\u002Fsearch parameters, compact storage, recomputation, and\n  index updates: [backends and storage](..\u002Fbackends-and-storage\u002FSKILL.md).\n- Embedding modes, model caches, API credentials, prompt templates, and LLM\u002Fchat\n  providers: [embeddings and chat](..\u002Fembeddings-and-chat\u002FSKILL.md).\n- MCP protocol details, server installation, transport, and deployment:\n  [MCP and services](..\u002Fmcp-and-services\u002FSKILL.md).\n- General Python builder\u002Fsearcher lifecycle and custom precomputed-vector code:\n  [API and indexing](..\u002Fapi-and-indexing\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\u002Frag-applications",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 rag-applications",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill rag-applications",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill rag-applications","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\u002Frag-applications\u002FSKILL.md",[48,54,58,62,66],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fchunking-metadata-and-layout.md","REFERENCE","参考文档",9382,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Frag-applications\u002Freferences\u002Fchunking-metadata-and-layout.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fdocument-and-code-rag.md",6190,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Frag-applications\u002Freferences\u002Fdocument-and-code-rag.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fmultimodal-rag.md",7196,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Frag-applications\u002Freferences\u002Fmultimodal-rag.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fpersonal-and-live-data.md",9379,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Frag-applications\u002Freferences\u002Fpersonal-and-live-data.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Ftroubleshooting.md",10533,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fleann\u002Fsub-skills\u002Frag-applications\u002Freferences\u002Ftroubleshooting.md",[71,78,83,90,97,104],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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",[],[]]