[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AE1YZ3F3MSARGA29CWCD2Y":3,"skill-same:01M6AE1YZ3F3MSARGA29CWCD2Y":75},{"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":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6AE1YZ3F3MSARGA29CWCD2Y","qdrant-search-speed-optimization",null,"Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was fast but now it's slow'. Also use when search performance degrades after config changes or data growth.","github\u002Fawesome-copilot","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3PBDYPK7NVFJNJ66Y8RS",41028,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fqdrant-performance-optimization\u002Fsearch-speed-optimization\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"search","Optimization","Qdrant","qdrant search speed optimization","Speed Optimization","speed","but","when","filtered","fixes","too long","throughput","now","long","latency","performance","reports","take","data","fast","config","2026-11-10 10:12:30",false,"---\nname: qdrant-search-speed-optimization\ndescription: \"Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was fast but now it's slow'. Also use when search performance degrades after config changes or data growth.\"\n---\n\n# Diagnose a problem\n\nThere the multiple possible reasons for search performance degradation. The most common ones are:\n\n* Memory pressure: if the working set exceeds available RAM\n* Complex requests (e.g. high `hnsw_ef`, complex filters without payload index)\n* Competing background processes (e.g. optimizer still running after bulk upload)\n* Problem with the cluster (e.g. network issues, hardware degradation)\n\n\n## Single Query Too Slow (Latency)\n\nUse when: individual queries take too long regardless of load.\n\n### Diagnostic steps:\n\n- Check if second run of the same request is significantly faster (indicates memory pressure)\n- Try the same query with `with_payload: false` and `with_vectors: false` to see if payload retrieval is the bottleneck\n- If request uses filters, try to remove them one by one to identify if a specific filter condition is the bottleneck\n\n### Common fixes:\n\n- Tune HNSW parameters: [Fine-tuning search](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=fine-tuning-search-parameters)\n- Enable in-memory quantization: [Scalar quantization](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=scalar-quantization)\n- Reduce Vector Dimensionality with Matryoshka Models: [Matryoshka Models](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Finference\u002F?s=reduce-vector-dimensionality-with-matryoshka-models)\n- Use oversampling + rescore for high-dimensional vectors [Search with quantization](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=searching-with-quantization)\n- Enable io_uring for disk-heavy workloads on Linux [io_uring](https:\u002F\u002Fqdrant.tech\u002Farticles\u002Fio_uring\u002F)\n\n\n## Can't Handle Enough QPS (Throughput)\n\nUse when: system can't serve enough queries per second under load.\n\n- Reduce segment count (`default_segment_number` to 2) [Maximizing throughput](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=maximizing-throughput)\n- Use batch search API instead of single queries [Batch search](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=batch-search-api)\n- Enable quantization to reduce CPU cost [Scalar quantization](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=scalar-quantization)\n- Add replicas to distribute read load [Replication](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Fdistributed_deployment\u002F?s=replication)\n\n\n## Filtered Search Is Slow\n\nUse when: filtered search is significantly slower than unfiltered. Most common SA complaint after memory.\n\n- Create payload index on the filtered field [Payload index](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=payload-index)\n- Use `is_tenant=true` for primary filtering condition: [Tenant index](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=tenant-index)\n- Try ACORN algorithm for complex filters: [ACORN](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=acorn-search-algorithm)\n- Avoid using `nested` filtering conditions as a primary filter. It might force qdrant to read raw payload values instead of using index.\n- If payload index was added after HNSW build, trigger re-index to create filterable subgraph links\n\n\n## Optimize search performance with parallel updates\n\n### Diagnostic steps\n\n- Try to run the same query with `indexed_only=true` parameter, if the query is significantly faster, it means that the optimizer is still running and has not yet indexed all segments.\n- If CPU or IO usage is high even with no queries, it also indicates that the optimizer is still running.\n\n### Recommended configuration changes\n\n- reduce `optimizer_cpu_budget` to reserve more CPU for queries\n- Use `prevent_unoptimized=true` to prevent creating segments with a large amount of unindexed data for searches. Instead, once a segment reaches the so called indexing_threshold, all additional points will be added in ‘deferred state’. \n\nLearn more [here](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Flow-latency-search\u002F?s=query-indexed-data-only)\n\n\n## What NOT to Do\n\n- Set `always_ram=false` on quantization (disk thrashing on every search)\n- Put HNSW on disk for latency-sensitive production (only for cold storage)\n- Increase segment count for throughput (opposite: fewer = better)\n- Create payload indexes on every field (wastes memory)\n- Blame Qdrant before checking optimizer status\n","# Diagnose a problem\n\nThere the multiple possible reasons for search performance degradation. The most common ones are:\n\n* Memory pressure: if the working set exceeds available RAM\n* Complex requests (e.g. high `hnsw_ef`, complex filters without payload index)\n* Competing background processes (e.g. optimizer still running after bulk upload)\n* Problem with the cluster (e.g. network issues, hardware degradation)\n\n\n## Single Query Too Slow (Latency)\n\nUse when: individual queries take too long regardless of load.\n\n### Diagnostic steps:\n\n- Check if second run of the same request is significantly faster (indicates memory pressure)\n- Try the same query with `with_payload: false` and `with_vectors: false` to see if payload retrieval is the bottleneck\n- If request uses filters, try to remove them one by one to identify if a specific filter condition is the bottleneck\n\n### Common fixes:\n\n- Tune HNSW parameters: [Fine-tuning search](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=fine-tuning-search-parameters)\n- Enable in-memory quantization: [Scalar quantization](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=scalar-quantization)\n- Reduce Vector Dimensionality with Matryoshka Models: [Matryoshka Models](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Finference\u002F?s=reduce-vector-dimensionality-with-matryoshka-models)\n- Use oversampling + rescore for high-dimensional vectors [Search with quantization](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=searching-with-quantization)\n- Enable io_uring for disk-heavy workloads on Linux [io_uring](https:\u002F\u002Fqdrant.tech\u002Farticles\u002Fio_uring\u002F)\n\n\n## Can't Handle Enough QPS (Throughput)\n\nUse when: system can't serve enough queries per second under load.\n\n- Reduce segment count (`default_segment_number` to 2) [Maximizing throughput](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=maximizing-throughput)\n- Use batch search API instead of single queries [Batch search](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=batch-search-api)\n- Enable quantization to reduce CPU cost [Scalar quantization](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F?s=scalar-quantization)\n- Add replicas to distribute read load [Replication](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Fdistributed_deployment\u002F?s=replication)\n\n\n## Filtered Search Is Slow\n\nUse when: filtered search is significantly slower than unfiltered. Most common SA complaint after memory.\n\n- Create payload index on the filtered field [Payload index](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=payload-index)\n- Use `is_tenant=true` for primary filtering condition: [Tenant index](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=tenant-index)\n- Try ACORN algorithm for complex filters: [ACORN](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Fsearch\u002F?s=acorn-search-algorithm)\n- Avoid using `nested` filtering conditions as a primary filter. It might force qdrant to read raw payload values instead of using index.\n- If payload index was added after HNSW build, trigger re-index to create filterable subgraph links\n\n\n## Optimize search performance with parallel updates\n\n### Diagnostic steps\n\n- Try to run the same query with `indexed_only=true` parameter, if the query is significantly faster, it means that the optimizer is still running and has not yet indexed all segments.\n- If CPU or IO usage is high even with no queries, it also indicates that the optimizer is still running.\n\n### Recommended configuration changes\n\n- reduce `optimizer_cpu_budget` to reserve more CPU for queries\n- Use `prevent_unoptimized=true` to prevent creating segments with a large amount of unindexed data for searches. Instead, once a segment reaches the so called indexing_threshold, all additional points will be added in ‘deferred state’. \n\nLearn more [here](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fsearch\u002Flow-latency-search\u002F?s=query-indexed-data-only)\n\n\n## What NOT to Do\n\n- Set `always_ram=false` on quantization (disk thrashing on every search)\n- Put HNSW on disk for latency-sensitive production (only for cold storage)\n- Increase segment count for throughput (opposite: fewer = better)\n- Create payload indexes on every field (wastes memory)\n- Blame Qdrant before checking optimizer status\n",{"name":5,"description":7},"main","5269f7ea2d6c3a9bfda5ed878b6726cf509121fd","skills\u002Fqdrant-performance-optimization\u002Fsearch-speed-optimization",5335,"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 11:59:04",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add github\u002Fawesome-copilot --skill qdrant-search-speed-optimization",{"tool":61,"command":62},"bunx","bunx skills add github\u002Fawesome-copilot --skill qdrant-search-speed-optimization",{"tool":64,"command":65},"pnpm","pnpm dlx skills add github\u002Fawesome-copilot --skill qdrant-search-speed-optimization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fqdrant-performance-optimization\u002Fsearch-speed-optimization\u002FSKILL.md",true,[69],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"agents\u002Fopenai.yaml","REFERENCE","参考文档",158,"https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwait-what\u002Fagents\u002Fopenai.yaml",[76,110,138,168,201,218],{"skillNo":77,"name":78,"nameZh":6,"description":79,"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":90,"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",[82,87],{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":88,"categoryName":89,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000023","Skill与智能体开发",[91,92,93,94,95,26,96,97,98,99,100,101,102,103,104,105,106,107,108,109],"supabase","rls","supabase rls","supabase rls policies","project","review","change","read","write","security","isolation","tables","as","tests","prove","use","users","functions","with",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":117,"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",[116],{"categoryNo":88,"categoryName":89,"taxonomyType":85,"taxonomyTypeDesc":86},[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"distribution","skill distribution audit","audit","SET","deterministic","installer","for","discovery","comparison","helper","manifest","version","collection","drift","output","investigate","duplicate","template","release","reconcile",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":142,"sourceHtmlUrl":143,"categories":144,"keywords":150,"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",[145],{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[151,152,153,154,155,156,124,95,157,158,159,160,161,162,163,106,164,165,166,167],"custom","code","logicapps custom code net10 migration","migration","projects","standalone","deployment","applications","local","azure","worker","upgrades","package","apps","Legacy","debugging","workflows",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":172,"sourceHtmlUrl":173,"categories":174,"keywords":179,"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",[175,178],{"categoryNo":176,"categoryName":177,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},[180,19,181,182,183,184,185,186,187,188,189,190,191,192,193,26,194,195,196,197,198,124,199,200],"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":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":205,"licenseFileUrl":206,"sourceHtmlUrl":207,"categories":208,"keywords":214,"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",[209,210,213],{"categoryNo":176,"categoryName":177,"taxonomyType":85,"taxonomyTypeDesc":86},{"categoryNo":211,"categoryName":212,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":88,"categoryName":89,"taxonomyType":85,"taxonomyTypeDesc":86},[215,121,188,216,217],"resemble detect","https","identity",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":205,"licenseFileUrl":222,"sourceHtmlUrl":223,"categories":224,"keywords":229,"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",[225,228],{"categoryNo":226,"categoryName":227,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":88,"categoryName":89,"taxonomyType":85,"taxonomyTypeDesc":86},[230,231,232,233,152,96,9,120,234,235,216,236,237,238,239,240,241,242,243,244,245,246,104,247,248,249,250],"playbook","quality playbook","quality","code review","tdd","run","report","spec","bug report","council","engineering","functional","spec audit","bug","verified","multi-model","three","coverage","model","regression","structural"]