[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718CPE2QT7TQMYAG56R19JW":3,"skill-same:01M718CPE2QT7TQMYAG56R19JW":64},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M718CPE2QT7TQMYAG56R19JW","incident-triage-runbook",null,"The SRE team's runbook for triaging production latency and error-rate incidents. Use this whenever investigating an incident, a latency spike, elevated error rates, or when asked \"what caused X\" about a production service.","anthropics\u002Fcwc-workshops","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M718C167JSRVRHKR28E40JYN",2309,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fship-your-first-managed-agent\u002Fskills\u002Fincident-triage-runbook\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"incident","incident triage","triage","runbook","incident triage runbook","team","when","use","service","spike","Production","rate","incidents","about","for","latency","sre","error","2026-11-10 10:12:30",false,"---\nname: incident-triage-runbook\ndescription: The SRE team's runbook for triaging production latency and error-rate incidents. Use this whenever investigating an incident, a latency spike, elevated error rates, or when asked \"what caused X\" about a production service.\n---\n\n# Incident triage\n\nIf you change the order below, say why in #sre.\n\n## Order of operations\n\n1. Pull deploys for the last 6h. Don't open the log first.\n2. Line the deploy timestamps up against `p99_latency_ms` \u002F `error_rate` for the paged service. State the gap (\"deploy 14:31, p99 moves 14:33\").\n3. If a deploy lines up: pull the diff, read it. Check for the stuff in the next section.\n4. Then grep the log to confirm. Don't grep to fish.\n5. No deploy lines up → the service may be a victim. Check `db_pool_utilization` across checkout\u002Fcart\u002Fauth\u002Finventory, then the upstream deps (`db-primary`, `db-inventory`, `idp.internal`). Find what moved first.\n\nAsk `get_metrics` for a name that doesn't exist and it lists the ones that do.\n\n## Things that have burned us\n\nIn rough order of how often:\n\n- per-row query where there used to be a batch\n- cache decorator removed \"temporarily\"\n- new query, no index\n- blocking call in an async handler\n- retry loop with no backoff\n\n## Write-up\n\nOne line at the bottom of your reply:\n\n> **Root cause:** `\u003Csha>` — one sentence on the mechanism.\n\nIf it wasn't a deploy, put the component or upstream dep where the sha goes (`db-primary`, `stripe-api`, whatever). Still one sentence.\n\nEverything above that line is evidence. Keep it short; the long version goes in the postmortem doc.\n\nIf you were handed an incident id, also save the structured version to `\u002Fworkspace\u002Ffindings\u002F\u003CINCIDENT_ID>.json` so the postmortem can be built from it:\n\n```json\n{\n  \"incident_id\": \"INC-0000\",\n  \"service\": \"checkout\",\n  \"title\": \"one line, what users saw\",\n  \"root_cause\": {\"ref\": \"\u003Csha or component>\", \"summary\": \"one sentence on the mechanism\"},\n  \"timeline\": [{\"time\": \"14:31:18\", \"event\": \"what happened\"}],\n  \"evidence\": [\"one fact per line, with the number or timestamp that proves it\"],\n  \"ruled_out\": [\"what you checked that turned out not to be the cause, and why\"],\n  \"impact\": {\"metric\": \"p99_latency_ms\", \"baseline\": 65, \"peak\": 3640, \"unit\": \"ms\"},\n  \"fix\": \"the immediate remediation\",\n  \"caused_by_incident\": null\n}\n```\n\nSet `caused_by_incident` to another page's id when your service is a victim of it.\n","# Incident triage\n\nIf you change the order below, say why in #sre.\n\n## Order of operations\n\n1. Pull deploys for the last 6h. Don't open the log first.\n2. Line the deploy timestamps up against `p99_latency_ms` \u002F `error_rate` for the paged service. State the gap (\"deploy 14:31, p99 moves 14:33\").\n3. If a deploy lines up: pull the diff, read it. Check for the stuff in the next section.\n4. Then grep the log to confirm. Don't grep to fish.\n5. No deploy lines up → the service may be a victim. Check `db_pool_utilization` across checkout\u002Fcart\u002Fauth\u002Finventory, then the upstream deps (`db-primary`, `db-inventory`, `idp.internal`). Find what moved first.\n\nAsk `get_metrics` for a name that doesn't exist and it lists the ones that do.\n\n## Things that have burned us\n\nIn rough order of how often:\n\n- per-row query where there used to be a batch\n- cache decorator removed \"temporarily\"\n- new query, no index\n- blocking call in an async handler\n- retry loop with no backoff\n\n## Write-up\n\nOne line at the bottom of your reply:\n\n> **Root cause:** `\u003Csha>` — one sentence on the mechanism.\n\nIf it wasn't a deploy, put the component or upstream dep where the sha goes (`db-primary`, `stripe-api`, whatever). Still one sentence.\n\nEverything above that line is evidence. Keep it short; the long version goes in the postmortem doc.\n\nIf you were handed an incident id, also save the structured version to `\u002Fworkspace\u002Ffindings\u002F\u003CINCIDENT_ID>.json` so the postmortem can be built from it:\n\n```json\n{\n  \"incident_id\": \"INC-0000\",\n  \"service\": \"checkout\",\n  \"title\": \"one line, what users saw\",\n  \"root_cause\": {\"ref\": \"\u003Csha or component>\", \"summary\": \"one sentence on the mechanism\"},\n  \"timeline\": [{\"time\": \"14:31:18\", \"event\": \"what happened\"}],\n  \"evidence\": [\"one fact per line, with the number or timestamp that proves it\"],\n  \"ruled_out\": [\"what you checked that turned out not to be the cause, and why\"],\n  \"impact\": {\"metric\": \"p99_latency_ms\", \"baseline\": 65, \"peak\": 3640, \"unit\": \"ms\"},\n  \"fix\": \"the immediate remediation\",\n  \"caused_by_incident\": null\n}\n```\n\nSet `caused_by_incident` to another page's id when your service is a victim of it.\n",{"name":5,"description":7},"main","2c65d16c6de16f8f24117d539a712ea706b5dee7","ship-your-first-managed-agent\u002Fskills\u002Fincident-triage-runbook",713,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-11-05 02:53:17",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add anthropics\u002Fcwc-workshops --skill incident-triage-runbook",{"tool":56,"command":57},"bunx","bunx skills add anthropics\u002Fcwc-workshops --skill incident-triage-runbook",{"tool":59,"command":60},"pnpm","pnpm dlx skills add anthropics\u002Fcwc-workshops --skill incident-triage-runbook","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fship-your-first-managed-agent\u002Fskills\u002Fincident-triage-runbook\u002FSKILL.md",true,[],[65,92,103,131,150,168],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":81,"publishedAt":37},"01M718CS4VJNEW3SRN5S3MG35W","postmortem-report","How the SRE team writes a postmortem PDF. Use this whenever asked for a postmortem, an incident report, a write-up to share, or a PDF of what happened.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fship-your-first-managed-agent\u002Fskills\u002Fpostmortem-report\u002FSKILL.md",[71,76],{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[82,83,84,35,85,86,87,33,19,88,89,90,26,24,91],"report","postmortem","postmortem report","what happened","PDF","how","write","up","incident report","share",{"skillNo":93,"name":94,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":37},"01M718CMK6R22RHEBDN1VW1YB5","eval-audit-and-sweep","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Frightmodel\u002F.claude\u002Fskills\u002Feval-audit-and-sweep\u002FSKILL.md",[],[98,99,100,101,102],"sweep","audit","eval audit and sweep","eval audit","eval",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":112,"publishedAt":37},"01M718CJ7RTEG518SSEJMH3H8H","edgartools-sec-data","How to pull SEC EDGAR data with the edgartools Python package — company lookup, filings, XBRL financial statements, and filing sections like Item 1A risk factors. Use whenever a task involves SEC filings, 10-K\u002F10-Q data, or company financials.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fresearch-desk\u002Fskills\u002Fedgartools\u002FSKILL.md",[109],{"categoryNo":110,"categoryName":111,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000033","数据分析师",[113,114,115,116,117,118,87,119,120,26,121,122,123,124,125,126,127,128,129,130],"data","edgartools sec data","edgartools","lookup","company lookup","financial statements","with","task","package","how to","python","company","filings","filing","pull","financials","sec edgar","risk",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":140,"publishedAt":37},"01M718CF9KPNBKPWFJN27XDN6A","workshop","Workshop coach for the Research Desk (SEC agents) workshop. Use when the user types \u002Fworkshop, asks for a workshop act or module (\"act 2\", \"next act\", \"where am I\"), wants a TODO(workshop-N) implemented or explained, or asks for help following WORKSHOP.md.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fresearch-desk\u002F.claude\u002Fskills\u002Fworkshop\u002FSKILL.md",[137],{"categoryNo":138,"categoryName":139,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000021","资料检索与研究",[133,141,142,33,143,26,25,144,145,146,147,148,149],"module","types","coach","todo","research","next","help","act","user",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":157,"publishedAt":37},"01M718CD3EBG31CBH0KSPVX0YR","weekly-report","Structure and data sources for the weekly inventory report. Load this when the task is \"weekly report\", \"Monday report\", or \"summarize inventory status\".","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fagent-decomposition\u002F.claude\u002Fskills\u002Fweekly-report\u002FSKILL.md",[156],{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},[82,158,159,160,161,162,163,33,164,165,113,166,25,120,167],"Weekly Report","weekly","sources","structure","monday","data sources","inventory","status","load","summarize",{"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":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":37},"01M718CBJPS1CFB1RBBY4HAA5F","supplier-selection","How to rank and pick a supplier for a SKU. Load this whenever a task involves choosing a supplier, comparing quotes, or creating a purchase order.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcwc-workshops\u002Fblob\u002Fmain\u002Fagent-decomposition\u002F.claude\u002Fskills\u002Fsupplier-selection\u002FSKILL.md",[],[175,176,177,178,122,166,179,33,87,120,180],"supplier selection","selection","purchase","pick","purchase order","quotes"]