[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AE2PGV0SWVCKFB3HYH0F5J":3,"skill-same:01M6AE2PGV0SWVCKFB3HYH0F5J":115},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6AE2PGV0SWVCKFB3HYH0F5J","qdrant-search-quality",null,"Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improve search quality?', 'which embedding model?', 'should I use hybrid search?', 'should I use reranking?'. Also use when search quality degrades after quantization, model change, or data growth.","github\u002Fawesome-copilot","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3PBDYPK7NVFJNJ66Y8RS",41046,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fqdrant-search-quality\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"search","Qdrant","qdrant search quality","quality","when","change","reranking","hybrid","expected","which","Hybrid Search","embedding","how to","missing","bad","reports","use","growth","model","improve","data","2026-11-10 10:12:30",false,"---\nname: qdrant-search-quality\ndescription: \"Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improve search quality?', 'which embedding model?', 'should I use hybrid search?', 'should I use reranking?'. Also use when search quality degrades after quantization, model change, or data growth.\"\nallowed-tools:\n  - Read\n  - Grep\n  - Glob\n---\n\n# Qdrant Search Quality\n\nFirst determine whether the problem is the embedding model, Qdrant configuration, or the query strategy. Most quality issues come from the model or data, not from Qdrant itself. If search quality is low, inspect how chunks are being passed to Qdrant before tuning any parameters. Splitting mid-sentence can drop quality 30-40%.\n\n- Start by testing with exact search to isolate the problem [Search API](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=search-api)\n\n\n## Diagnosis and Tuning\n\nIsolate the source of quality issues, tune HNSW parameters, and choose the right embedding model. [Diagnosis and Tuning](diagnosis\u002FSKILL.md)\n\n\n## Search Strategies\n\nHybrid search, reranking, relevance feedback, and exploration APIs for improving result quality. [Search Strategies](search-strategies\u002FSKILL.md)\n","# Qdrant Search Quality\n\nFirst determine whether the problem is the embedding model, Qdrant configuration, or the query strategy. Most quality issues come from the model or data, not from Qdrant itself. If search quality is low, inspect how chunks are being passed to Qdrant before tuning any parameters. Splitting mid-sentence can drop quality 30-40%.\n\n- Start by testing with exact search to isolate the problem [Search API](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=search-api)\n\n\n## Diagnosis and Tuning\n\nIsolate the source of quality issues, tune HNSW parameters, and choose the right embedding model. [Diagnosis and Tuning](diagnosis\u002FSKILL.md)\n\n\n## Search Strategies\n\nHybrid search, reranking, relevance feedback, and exploration APIs for improving result quality. [Search Strategies](search-strategies\u002FSKILL.md)\n",{"name":5,"description":7,"allowed-tools":45},[46,47,48],"Read","Grep","Glob","main","5269f7ea2d6c3a9bfda5ed878b6726cf509121fd","skills\u002Fqdrant-search-quality",5340,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot","https:\u002F\u002Fawesome-copilot.github.com\u002F","https:\u002F\u002Fgithub.com\u002Fgithub","https:\u002F\u002Fgithub.com\u002Fabout","How people build software.","2026-11-11 13:41:32",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add github\u002Fawesome-copilot --skill qdrant-search-quality",{"tool":65,"command":66},"bunx","bunx skills add github\u002Fawesome-copilot --skill qdrant-search-quality",{"tool":68,"command":69},"pnpm","pnpm dlx skills add github\u002Fawesome-copilot --skill qdrant-search-quality","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fqdrant-search-quality\u002FSKILL.md",true,[73,79,83,87,93,97,103,107,111],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"append-handoff.sh","SCRIPT","脚本",11104,"https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbranch-context\u002Fappend-handoff.sh",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"append-pr-decision.sh",6651,"https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbranch-context\u002Fappend-pr-decision.sh",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"check-autoload-safety.sh",2788,"https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbranch-context\u002Fcheck-autoload-safety.sh",{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"handoffs-index.template.md","REFERENCE","参考文档",485,"https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbranch-context\u002Fhandoffs-index.template.md",{"path":94,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":95,"sourceHtmlUrl":96},"issue-brief.template.md",1553,"https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbranch-context\u002Fissue-brief.template.md",{"path":98,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":101,"sourceHtmlUrl":102},"issue-comment-fingerprint","OTHER","其他",1448,"https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbranch-context\u002Fissue-comment-fingerprint",{"path":104,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":105,"sourceHtmlUrl":106},"latest-handoff.sh",5623,"https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbranch-context\u002Flatest-handoff.sh",{"path":108,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":109,"sourceHtmlUrl":110},"pr-decisions.template.md",1481,"https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbranch-context\u002Fpr-decisions.template.md",{"path":112,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":113,"sourceHtmlUrl":114},"status.sh",3887,"https:\u002F\u002Fgithub.com\u002Fpydantic\u002Fpydantic-ai\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbranch-context\u002Fstatus.sh",[116,148,176,206,239,256],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":130,"publishedAt":40},"01M70KXZNX9ES38N2A8M58ZZMZ","supabase-rls-policies","Write, review, and test Supabase Row Level Security (RLS) policies so that one user cannot read or change another user's rows. Use when creating or changing tables, policies, views, or security definer functions in a Supabase project, when reviewing a migration that touches RLS, or when asked to prove user isolation with pgTAP tests that sign in as two users.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fsupabase-rls-policies\u002FSKILL.md",[122,127],{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":128,"categoryName":129,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000023","Skill与智能体开发",[131,132,133,134,135,23,136,24,137,138,139,140,141,142,143,144,35,145,146,147],"supabase","rls","supabase rls","supabase rls policies","project","review","read","write","security","isolation","tables","as","tests","prove","users","functions","with",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":40},"01M70KWA5YWXDV6V8DZ19E3T2Y","skill-distribution-audit","Audit a skill collection before release or investigate installer omissions, archived\u002Ftemplate leakage, duplicate identities, and manifest drift. Reconcile the intended public source set, distribution manifest, and actual discovery output for a specified consumer version. Includes a deterministic set-comparison helper.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fskill-distribution-audit\u002FSKILL.md",[154],{"categoryNo":128,"categoryName":129,"taxonomyType":125,"taxonomyTypeDesc":126},[156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175],"distribution","skill distribution audit","audit","SET","deterministic","installer","for","discovery","comparison","helper","manifest","version","collection","drift","output","investigate","duplicate","template","release","reconcile",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":180,"sourceHtmlUrl":181,"categories":182,"keywords":188,"publishedAt":40},"01M70KCJPFVW7PPQ49CC5R8JGK","logicapps-custom-code-net10-migration","Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10. Use for legacy Logic Apps custom-code workspace upgrades, project\u002Fpackage configuration, custom-worker settings, publication, and integrated VS Code debugging. Not for ordinary .NET applications, standalone Azure Functions, Consumption workflows, or cloud deployment.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Flogicapps-custom-code-net10-migration\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Flogicapps-custom-code-net10-migration\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":186,"taxonomyTypeDesc":187},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[189,190,191,192,193,194,162,135,195,196,197,198,199,200,201,35,202,203,204,205],"custom","code","logicapps custom code net10 migration","migration","projects","standalone","deployment","applications","local","azure","worker","upgrades","package","apps","Legacy","debugging","workflows",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":210,"sourceHtmlUrl":211,"categories":212,"keywords":217,"publishedAt":40},"01M6AEBN37RQMXJ3298PEY7PG1","winmd-api-search","Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI\u002FML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fwinmd-api-search\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fwinmd-api-search\u002FSKILL.md",[213,216],{"categoryNo":214,"categoryName":215,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":184,"categoryName":185,"taxonomyType":186,"taxonomyTypeDesc":187},[218,19,219,220,221,222,223,224,225,226,227,228,229,230,231,23,232,233,234,235,236,162,237,238],"winmd api search","api","windows","desktop","file access","enumeration","ui","ml","file","networking","capabilities","notifications","explore","access","features","full","camera","events","platform","methods","controls",{"skillNo":240,"name":241,"nameZh":6,"description":242,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":243,"licenseFileUrl":244,"sourceHtmlUrl":245,"categories":246,"keywords":252,"publishedAt":40},"01M6AE571R3SC1ZGE202B3NB5S","resemble-detect","Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fresemble-detect\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fresemble-detect\u002FSKILL.md",[247,248,251],{"categoryNo":214,"categoryName":215,"taxonomyType":125,"taxonomyTypeDesc":126},{"categoryNo":249,"categoryName":250,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":128,"categoryName":129,"taxonomyType":125,"taxonomyTypeDesc":126},[253,159,226,254,255],"resemble detect","https","identity",{"skillNo":257,"name":258,"nameZh":6,"description":259,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":243,"licenseFileUrl":260,"sourceHtmlUrl":261,"categories":262,"keywords":267,"publishedAt":40},"01M6AE30BSK2HCY4TQQ22Z8JRD","quality-playbook","Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fquality-playbook\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fquality-playbook\u002FSKILL.md",[263,266],{"categoryNo":264,"categoryName":265,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":128,"categoryName":129,"taxonomyType":125,"taxonomyTypeDesc":126},[268,269,22,270,190,136,9,158,271,272,254,273,274,275,276,277,278,279,280,281,282,283,143,284,37,285,286],"playbook","quality playbook","code review","tdd","run","report","spec","bug report","council","engineering","functional","spec audit","bug","verified","multi-model","three","coverage","regression","structural"]