[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6G8WB53S01C18P93MVR4NGA":3,"skill-same:01M6G8WB53S01C18P93MVR4NGA":76},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6G8WB53S01C18P93MVR4NGA","manage-slos",null,"Assist with Harness Service Reliability Management (SRM) tasks that the MCP server currently supports: pulling recent deployments for incident correlation, generating on-call handover reports from deployment\u002Fexecution history, and drafting operational runbooks. Use when asked about SLOs, error budgets, burn-rate alerts, on-call handover, runbooks, or incident triage. Do NOT use for DORA metrics (use dora-metrics instead) or chaos experiments (use chaos-experiment instead). Trigger phrases: SLO, SLI, error budget, burn rate, on-call handover, runbook, service reliability, incident response, on-call shift.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F6e\u002F6e4ccb9ce909accee0bc2408b3e531541ee4ac613c3fec315cc2787e265ee3e3\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"manage slos","manage","burn-rate","runbooks","error","resources","alerts","incident","done","reports","MCP","sli","slo","reliability","crud","server","tasks","workflows","mcp server","incident response","2026-11-10 10:12:30",false,"---\r\nname: manage-slos\r\ndescription: >-\r\n  Assist with Harness Service Reliability Management (SRM) tasks that the MCP server currently\r\n  supports: pulling recent deployments for incident correlation, generating on-call handover\r\n  reports from deployment\u002Fexecution history, and drafting operational runbooks. Use when asked\r\n  about SLOs, error budgets, burn-rate alerts, on-call handover, runbooks, or incident triage.\r\n  Do NOT use for DORA metrics (use dora-metrics instead) or chaos experiments (use\r\n  chaos-experiment instead). Trigger phrases: SLO, SLI, error budget, burn rate, on-call handover,\r\n  runbook, service reliability, incident response, on-call shift.\r\nmetadata:\r\n  author: Harness\r\n  version: 2.0.0\r\n  mcp-server: harness-mcp-v2\r\nlicense: Apache-2.0\r\ncompatibility: |\r\n  Requires Harness MCP v2 server (harness-mcp-v2).\r\n  NOTE: SRM CRUD resources (`slo`, `slo_alert`, `monitored_service`) are NOT currently exposed\r\n  by the MCP server. Creating\u002Fmanaging SLOs and monitored services must be done in the Harness\r\n  UI. This skill focuses on the incident-correlation and reporting workflows that the MCP server\r\n  does support today (via `execution`, `service`, `environment`).\r\n---\r\n\r\n# Manage SLOs \u002F SRM\r\n\r\n> **Limitation:** The MCP server does not currently expose `slo`, `slo_alert`, or\r\n> `monitored_service` resource types. SLO definitions, burn-rate alerts, and monitored-service\r\n> configuration must be created and edited via the Harness UI under\r\n> **Service Reliability Management**. This skill covers the parts of the SRM workflow that\r\n> *are* supported via MCP: deployment correlation, on-call handover reports, and operational\r\n> runbooks.\r\n\r\n## What this skill can do via MCP\r\n\r\n| Workflow | Supported today |\r\n|---|---|\r\n| Define an SLO or SLI | ❌ Use the Harness UI |\r\n| Configure error-budget \u002F burn-rate alerts | ❌ Use the Harness UI |\r\n| Configure a monitored service | ❌ Use the Harness UI |\r\n| Correlate deployments with an incident | ✅ via `execution` |\r\n| Summarize recent releases for on-call handover | ✅ via `execution`, `service`, `environment` |\r\n| Draft an operational runbook | ✅ (LLM-authored; pulls context from MCP) |\r\n\r\n## Instructions\r\n\r\n### Step 1: Establish Scope\r\n\r\n```\r\nCall MCP tool: harness_list\r\nParameters:\r\n  resource_type: \"project\"\r\n  org_id: \"\u003Corganization>\"\r\n```\r\n\r\n### Step 2: Incident Triage — Correlate Deployments\r\n\r\nWhen the user reports an active incident:\r\n\r\n1. Identify the affected service and environment.\r\n2. Pull recent executions that deployed the service.\r\n\r\n```\r\nCall MCP tool: harness_list\r\nParameters:\r\n  resource_type: \"execution\"\r\n  org_id: \"\u003Corganization>\"\r\n  project_id: \"\u003Cproject>\"\r\n  # filter by service or environment as needed\r\n```\r\n\r\n3. Correlate incident start time with deployment timestamps.\r\n4. Pull the failing execution's details:\r\n\r\n```\r\nCall MCP tool: harness_get\r\nParameters:\r\n  resource_type: \"execution\"\r\n  resource_id: \"\u003Cexecution_id>\"\r\n  org_id: \"\u003Corganization>\"\r\n  project_id: \"\u003Cproject>\"\r\n```\r\n\r\n5. Guide the user through structured RCA: blast radius, suspected root cause, mitigation steps, rollback candidate.\r\n\r\n### Step 3: On-Call Handover Report\r\n\r\nGather from the user: outgoing\u002Fincoming engineers, shift window, owned services.\r\n\r\nPull recent executions and services:\r\n\r\n```\r\nCall MCP tool: harness_list\r\nParameters:\r\n  resource_type: \"execution\"\r\n  org_id: \"\u003Corganization>\"\r\n  project_id: \"\u003Cproject>\"\r\n```\r\n\r\n```\r\nCall MCP tool: harness_list\r\nParameters:\r\n  resource_type: \"service\"\r\n  org_id: \"\u003Corganization>\"\r\n  project_id: \"\u003Cproject>\"\r\n```\r\n\r\nGenerate a structured handover covering: active\u002Frecent incidents the user describes,\r\ndeployments during the shift, services with elevated failure counts, and items\r\nrequiring attention.\r\n\r\n> For SLO burn-rate and error-budget status, direct the user to the SRM UI —\r\n> the MCP server does not expose these metrics.\r\n\r\n### Step 4: Operational Runbook (LLM-Authored)\r\n\r\nGather from the user: service name, team, tech stack, dependencies, SLO targets, common\r\nfailure modes.\r\n\r\nStructure the runbook with:\r\n- Service overview (purpose, owners, tech stack)\r\n- Health checks (pointers to SRM monitored-service dashboard in the Harness UI)\r\n- Common alerts with response procedures\r\n- Escalation paths\r\n- Rollback procedures (reference relevant pipelines via `harness_list resource_type: pipeline`)\r\n- Dependency contacts\r\n\r\n## Defining SLOs (UI-Only Today)\r\n\r\nWhen the user asks to define an SLO, burn-rate alert, or monitored service, respond:\r\n\r\n1. Gather requirements (service tier, health sources, SLO targets, rolling window, SLI type).\r\n2. Explain that SLO CRUD is not exposed via MCP today and link the user to the Harness SRM UI.\r\n3. Offer to draft the SLO spec (name, target %, SLI type, burn-rate thresholds) as text the\r\n   user can paste into the UI.\r\n4. Suggested burn-rate alert windows: 14.4×\u002F1h (page), 6×\u002F6h (ticket), 1×\u002F3d (log).\r\n\r\n## Examples\r\n\r\n- \"Our payment service is down, help me triage\" — Pull recent `execution`s for the service, correlate with incident start, suggest rollback candidate.\r\n- \"Generate an on-call handover report\" — Pull executions and services during the shift, summarize with active issues.\r\n- \"Create a runbook for the auth-service\" — Draft runbook using MCP to list pipelines\u002Fservices\u002Fenvironments for accurate references.\r\n- \"Define SLOs for our payment-gateway service\" — Draft the SLO spec as text; point to the Harness SRM UI for creation.\r\n- \"Configure burn-rate alerts\" — Draft the alert config; point to the SRM UI.\r\n\r\n## Performance Notes\r\n\r\n- When correlating incidents with deployments, pull a wide enough execution window (±30 min) to catch slow-burn failures.\r\n- For handover reports, include both successful and failed executions — a streak of successes is useful context.\r\n\r\n## Troubleshooting\r\n\r\n### \"SLO not found\" or \"Monitored service not found\"\r\n- These resources are not exposed by the MCP server today. Manage them in the Harness UI under Service Reliability Management.\r\n\r\n### Incident correlation missing executions\r\n- Confirm `org_id` and `project_id` scope the service\r\n- Broaden the execution filter time window\r\n- Check that the service's pipelines actually ran (no deploy = no execution)\r\n","# Manage SLOs \u002F SRM\r\n\r\n> **Limitation:** The MCP server does not currently expose `slo`, `slo_alert`, or\r\n> `monitored_service` resource types. SLO definitions, burn-rate alerts, and monitored-service\r\n> configuration must be created and edited via the Harness UI under\r\n> **Service Reliability Management**. This skill covers the parts of the SRM workflow that\r\n> *are* supported via MCP: deployment correlation, on-call handover reports, and operational\r\n> runbooks.\r\n\r\n## What this skill can do via MCP\r\n\r\n| Workflow | Supported today |\r\n|---|---|\r\n| Define an SLO or SLI | ❌ Use the Harness UI |\r\n| Configure error-budget \u002F burn-rate alerts | ❌ Use the Harness UI |\r\n| Configure a monitored service | ❌ Use the Harness UI |\r\n| Correlate deployments with an incident | ✅ via `execution` |\r\n| Summarize recent releases for on-call handover | ✅ via `execution`, `service`, `environment` |\r\n| Draft an operational runbook | ✅ (LLM-authored; pulls context from MCP) |\r\n\r\n## Instructions\r\n\r\n### Step 1: Establish Scope\r\n\r\n```\r\nCall MCP tool: harness_list\r\nParameters:\r\n  resource_type: \"project\"\r\n  org_id: \"\u003Corganization>\"\r\n```\r\n\r\n### Step 2: Incident Triage — Correlate Deployments\r\n\r\nWhen the user reports an active incident:\r\n\r\n1. Identify the affected service and environment.\r\n2. Pull recent executions that deployed the service.\r\n\r\n```\r\nCall MCP tool: harness_list\r\nParameters:\r\n  resource_type: \"execution\"\r\n  org_id: \"\u003Corganization>\"\r\n  project_id: \"\u003Cproject>\"\r\n  # filter by service or environment as needed\r\n```\r\n\r\n3. Correlate incident start time with deployment timestamps.\r\n4. Pull the failing execution's details:\r\n\r\n```\r\nCall MCP tool: harness_get\r\nParameters:\r\n  resource_type: \"execution\"\r\n  resource_id: \"\u003Cexecution_id>\"\r\n  org_id: \"\u003Corganization>\"\r\n  project_id: \"\u003Cproject>\"\r\n```\r\n\r\n5. Guide the user through structured RCA: blast radius, suspected root cause, mitigation steps, rollback candidate.\r\n\r\n### Step 3: On-Call Handover Report\r\n\r\nGather from the user: outgoing\u002Fincoming engineers, shift window, owned services.\r\n\r\nPull recent executions and services:\r\n\r\n```\r\nCall MCP tool: harness_list\r\nParameters:\r\n  resource_type: \"execution\"\r\n  org_id: \"\u003Corganization>\"\r\n  project_id: \"\u003Cproject>\"\r\n```\r\n\r\n```\r\nCall MCP tool: harness_list\r\nParameters:\r\n  resource_type: \"service\"\r\n  org_id: \"\u003Corganization>\"\r\n  project_id: \"\u003Cproject>\"\r\n```\r\n\r\nGenerate a structured handover covering: active\u002Frecent incidents the user describes,\r\ndeployments during the shift, services with elevated failure counts, and items\r\nrequiring attention.\r\n\r\n> For SLO burn-rate and error-budget status, direct the user to the SRM UI —\r\n> the MCP server does not expose these metrics.\r\n\r\n### Step 4: Operational Runbook (LLM-Authored)\r\n\r\nGather from the user: service name, team, tech stack, dependencies, SLO targets, common\r\nfailure modes.\r\n\r\nStructure the runbook with:\r\n- Service overview (purpose, owners, tech stack)\r\n- Health checks (pointers to SRM monitored-service dashboard in the Harness UI)\r\n- Common alerts with response procedures\r\n- Escalation paths\r\n- Rollback procedures (reference relevant pipelines via `harness_list resource_type: pipeline`)\r\n- Dependency contacts\r\n\r\n## Defining SLOs (UI-Only Today)\r\n\r\nWhen the user asks to define an SLO, burn-rate alert, or monitored service, respond:\r\n\r\n1. Gather requirements (service tier, health sources, SLO targets, rolling window, SLI type).\r\n2. Explain that SLO CRUD is not exposed via MCP today and link the user to the Harness SRM UI.\r\n3. Offer to draft the SLO spec (name, target %, SLI type, burn-rate thresholds) as text the\r\n   user can paste into the UI.\r\n4. Suggested burn-rate alert windows: 14.4×\u002F1h (page), 6×\u002F6h (ticket), 1×\u002F3d (log).\r\n\r\n## Examples\r\n\r\n- \"Our payment service is down, help me triage\" — Pull recent `execution`s for the service, correlate with incident start, suggest rollback candidate.\r\n- \"Generate an on-call handover report\" — Pull executions and services during the shift, summarize with active issues.\r\n- \"Create a runbook for the auth-service\" — Draft runbook using MCP to list pipelines\u002Fservices\u002Fenvironments for accurate references.\r\n- \"Define SLOs for our payment-gateway service\" — Draft the SLO spec as text; point to the Harness SRM UI for creation.\r\n- \"Configure burn-rate alerts\" — Draft the alert config; point to the SRM UI.\r\n\r\n## Performance Notes\r\n\r\n- When correlating incidents with deployments, pull a wide enough execution window (±30 min) to catch slow-burn failures.\r\n- For handover reports, include both successful and failed executions — a streak of successes is useful context.\r\n\r\n## Troubleshooting\r\n\r\n### \"SLO not found\" or \"Monitored service not found\"\r\n- These resources are not exposed by the MCP server today. Manage them in the Harness UI under Service Reliability Management.\r\n\r\n### Incident correlation missing executions\r\n- Confirm `org_id` and `project_id` scope the service\r\n- Broaden the execution filter time window\r\n- Check that the service's pipelines actually ran (no deploy = no execution)\r\n",{"name":5,"license":15,"metadata":49,"description":7,"compatibility":53},{"author":50,"version":51,"mcp-server":52},"Harness","2.0.0","harness-mcp-v2","Requires Harness MCP v2 server (harness-mcp-v2).\nNOTE: SRM CRUD resources (`slo`, `slo_alert`, `monitored_service`) are NOT currently exposed\nby the MCP server. Creating\u002Fmanaging SLOs and monitored services must be done in the Harness\nUI. This skill focuses on the incident-correlation and reporting workflows that the MCP server\ndoes support today (via `execution`, `service`, `environment`).","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F6e\u002F6e4ccb9ce909accee0bc2408b3e531541ee4ac613c3fec315cc2787e265ee3e3",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add zapabob\u002FSkills --skill manage-slos",{"tool":68,"command":69},"bunx","bunx skills add zapabob\u002FSkills --skill manage-slos",{"tool":71,"command":72},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill manage-slos","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F6e\u002F6e4ccb9ce909accee0bc2408b3e531541ee4ac613c3fec315cc2787e265ee3e3\u002FSKILL.md",true,[],[77,112,146,173,200,217],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":93,"publishedAt":44},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[84,87,88],{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[79,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,54,109,110,111],"openclaw","macos","cli","github","linux","windows","official","search","https","social-media","api","Media","hermes","hermes agent","twitter","social","via","post",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":129,"publishedAt":44},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[118,121,124,125,126],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},{"categoryNo":127,"categoryName":128,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000036","内容创作者",[130,131,132,133,95,134,98,135,99,136,40,137,138,139,140,141,142,143,144,145],"writing","writing plans","plans","design","review","workflow","documentation","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":155,"publishedAt":44},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[152],{"categoryNo":153,"categoryName":154,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[148,95,98,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":182,"publishedAt":44},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[179],{"categoryNo":180,"categoryName":181,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[183,95,184,185,99,186,187,188,189,190,191,163,192,193,194,195,196,197,198,199],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":207,"publishedAt":44},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[206],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[202,95,208,97,98,209,210,211,212,213,214,106,107,215,216],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":225,"publishedAt":44},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[223,224],{"categoryNo":85,"categoryName":86,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[226,227,228,98,229,156,230,231,232,159,233,104,234,235,236,237,238,239,240,241],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]