[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BYPC1GMBAD7VR9293J7HMV":3,"skill-same:01M6BYPC1GMBAD7VR9293J7HMV":74},{"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":28,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6BYPC1GMBAD7VR9293J7HMV","writing-for-agents",null,"Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","Vortex375\u002Fseraph","Vortex375","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5016523?v=4","01M6BYMHA5FQE4EMD6BSZ13M46","Benjamin Schmitz","01M6BYMHEYGQ7DM3Q8A7KBNZ48",2,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[29,30,31,32,33,34,35],"writing","writing for agents","for","documents","editing","use","when","2026-11-10 10:12:30",false,"---\nname: qdrant-minimize-latency\ndescription: \"Guides Qdrant query latency optimization. Use when someone asks 'search is slow', 'how to reduce latency', 'p99 is too high', 'tail latency', 'single query too slow', 'how to make search faster', or 'latency spikes'.\"\n---\n\n# Scaling for Query Latency\n\nLatency of a single query is determined by the slowest component in the query execution path. It is sometimes correlated with throughput, but not always — throughput and latency are opposite tuning directions.\n\nLow latency optimization is aimed at utilising maximum resource saturation for a single query, while throughput optimization is aimed at minimizing per-query resource usage to allow more parallel queries.\n\n## Performance Tuning for Lower Latency\n\n- Increase segment count to match CPU cores (`default_segment_number: 16`) [Minimizing latency](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=minimizing-latency)\n- Keep quantized vectors and HNSW in RAM (`always_ram=true`)\n- Reduce `hnsw_ef` at query time (trade recall for speed) [Search params](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=fine-tuning-search-parameters)\n- Use local NVMe, avoid network-attached storage\n\n## Memory Pressure and Latency\n\nRAM is the most critical resource for latency. If working set exceeds available RAM, OS cache eviction causes severe, sustained latency degradation.\n\n- Vertical scale RAM first. Critical if working set >80%.\n- Use quantization: scalar (4x reduction) or binary (16x reduction) [Quantization](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F)\n- Move payload indexes to disk if filtering is infrequent [On-disk payload index](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=on-disk-payload-index)\n- Set `optimizer_cpu_budget` to limit background optimization CPUs\n- Schedule indexing: set high `indexing_threshold` during peak hours\n\n\n## Vertical Scaling for Latency\n\nMore RAM and faster CPU directly reduce latency. See [Vertical Scaling](..\u002Fscaling-data-volume\u002Fvertical-scaling\u002FSKILL.md) for node sizing guidelines.\n\n\n## What NOT to Do\n\n- Do not expect to optimize latency and throughput simultaneously on the same node\n- Do not use few large segments for latency-sensitive workloads (each segment takes longer to search)\n- Do not run at >90% RAM (cache eviction causes severe latency degradation that can last days)\n- Do not ignore optimizer status during performance debugging\n- Do not scale down RAM without load testing (cache eviction causes days-long latency incidents)\n","# Scaling for Query Latency\n\nLatency of a single query is determined by the slowest component in the query execution path. It is sometimes correlated with throughput, but not always — throughput and latency are opposite tuning directions.\n\nLow latency optimization is aimed at utilising maximum resource saturation for a single query, while throughput optimization is aimed at minimizing per-query resource usage to allow more parallel queries.\n\n## Performance Tuning for Lower Latency\n\n- Increase segment count to match CPU cores (`default_segment_number: 16`) [Minimizing latency](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=minimizing-latency)\n- Keep quantized vectors and HNSW in RAM (`always_ram=true`)\n- Reduce `hnsw_ef` at query time (trade recall for speed) [Search params](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Foperations\u002Foptimize\u002F?s=fine-tuning-search-parameters)\n- Use local NVMe, avoid network-attached storage\n\n## Memory Pressure and Latency\n\nRAM is the most critical resource for latency. If working set exceeds available RAM, OS cache eviction causes severe, sustained latency degradation.\n\n- Vertical scale RAM first. Critical if working set >80%.\n- Use quantization: scalar (4x reduction) or binary (16x reduction) [Quantization](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Fquantization\u002F)\n- Move payload indexes to disk if filtering is infrequent [On-disk payload index](https:\u002F\u002Fsearch.qdrant.tech\u002Fmd\u002Fdocumentation\u002Fmanage-data\u002Findexing\u002F?s=on-disk-payload-index)\n- Set `optimizer_cpu_budget` to limit background optimization CPUs\n- Schedule indexing: set high `indexing_threshold` during peak hours\n\n\n## Vertical Scaling for Latency\n\nMore RAM and faster CPU directly reduce latency. See [Vertical Scaling](..\u002Fscaling-data-volume\u002Fvertical-scaling\u002FSKILL.md) for node sizing guidelines.\n\n\n## What NOT to Do\n\n- Do not expect to optimize latency and throughput simultaneously on the same node\n- Do not use few large segments for latency-sensitive workloads (each segment takes longer to search)\n- Do not run at >90% RAM (cache eviction causes severe latency degradation that can last days)\n- Do not ignore optimizer status during performance debugging\n- Do not scale down RAM without load testing (cache eviction causes days-long latency incidents)\n",{"name":41,"description":42},"qdrant-minimize-latency","Guides Qdrant query latency optimization. Use when someone asks 'search is slow', 'how to reduce latency', 'p99 is too high', 'tail latency', 'single query too slow', 'how to make search faster', or 'latency spikes'.","main","5269f7ea2d6c3a9bfda5ed878b6726cf509121fd",".agents\u002Fskills\u002Fwriting-for-agents",0,"https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph","https:\u002F\u002Fgithub.com\u002FVortex375","2026-11-08 18:46:14",{"source":8,"skillName":41,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add Vortex375\u002Fseraph --skill qdrant-minimize-latency",{"tool":56,"command":57},"bunx","bunx skills add Vortex375\u002Fseraph --skill qdrant-minimize-latency",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Vortex375\u002Fseraph --skill qdrant-minimize-latency","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",true,[64,70],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"agents\u002Fopenai.yaml","REFERENCE","参考文档",102,"https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002Fagents\u002Fopenai.yaml",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"SKILL-MECHANICS.md",2629,"https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL-MECHANICS.md",[75,82,107,132,148,167],{"skillNo":76,"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":77,"categories":78,"keywords":81,"publishedAt":36},"01M6BYS1QVW7F887EXS5RR34TA","https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002Fapp\u002Fseraph_app\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[79,80],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[29,31,30,35,34,33,32],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":36},"01M6BYRZNREK0C7V6Y43AKDJWW","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002Fapp\u002Fseraph_app\u002F.agents\u002Fskills\u002Fwizard\u002FSKILL.md",[],[84,89,90,91,92,93,94,95,35,96,97,31,98,99,100,101,102,103,34,104,105,106],"provisioning","ci","generate","infrastructure","dashboard","can","running","invoke","party","credentials","human","provisioning infrastructure","migration","up","only","interactive","Bash","secrets",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":36},"01M6BYRY92S448X31PTG25TCJC","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002Fapp\u002Fseraph_app\u002F.agents\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[109,114,115,116,94,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131],"at","map","agent session","time","true","shared","more","tickets","as","clear","issue","session","one at a time","work","decision","plan","chunk","tracker",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":36},"01M6BYRWXMYWB6PD7E9PAD44M4","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002Fapp\u002Fseraph_app\u002F.agents\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[139,140,141,118,142,143,144,145,146,147],"wait what","wait","re","last","it","pitch","message","stop","land",{"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":154,"publishedAt":36},"01M6BYRTS6JNDYB7BZVAWK7JJ9","triage","Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.","https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002Fapp\u002Fseraph_app\u002F.agents\u002Fskills\u002Ftriage\u002FSKILL.md",[],[150,155,156,157,158,159,160,161,162,163,164,165,118,166],"machine","roles","grill","ready","write","verify","issues","state","move","prs","state machine","briefs",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":36},"01M6BYRRRCDHNXH2YBDTYJPG36","to-tickets","Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).","https:\u002F\u002Fgithub.com\u002FVortex375\u002Fseraph\u002Fblob\u002Fmain\u002Fapp\u002Fseraph_app\u002F.agents\u002Fskills\u002Fto-tickets\u002FSKILL.md",[],[174,121,175,176,177,118,178,179,122,180,131,181,129,182,183],"to tickets","spec","links","break","native","ticket","conversation","text","SET","file"]