[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718HCDRB6WK6MB5Q6V047N7":3,"skill-same:01M718HCDRB6WK6MB5Q6V047N7":62},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M718HCDRB6WK6MB5Q6V047N7","handoff",null,"Write the weekly on-call handoff: everything the incoming on-call needs, triage-ready, posted to the channel at shift boundary. Use when the weekly routine fires, or when someone asks for a handoff \u002F shift summary \u002F \"catch the next on-call up\".","anthropics\u002Foncall-kit","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M718HAM88APBE3NK565F2XWJ",273,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Foncall-kit\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"catch","channel","triage","routine","summary","write","at","next","boundary","when","use","call","up","for","ready","weekly","2026-11-10 10:12:30",false,"---\nname: handoff\ndescription: >\n  Write the weekly on-call handoff: everything the incoming on-call needs,\n  triage-ready, posted to the channel at shift boundary. Use when the weekly\n  routine fires, or when someone asks for a handoff \u002F shift summary \u002F \"catch\n  the next on-call up\".\n---\n\n\u003C!-- Copyright 2026 Anthropic PBC -->\n\u003C!-- SPDX-License-Identifier: Apache-2.0 -->\n\n# Handoff\n\nStanding rules in `CLAUDE.md` apply — especially rules 10 and 11: fresh\nreader, lead with what to do. The incoming on-call missed everything; this\ndocument is their entire week's context, and it must arrive as **work they\ncan start**, not \"here's what happened\".\n\n## Sources — sweep all of them\n\nFan out across every capability in `STACK.md` for the shift window\n(default: the week since the last handoff):\n\n- `pager` — every page and incident: state, severity, resolution\n- `alert-channels` — what fired, what people said, what never got a thread\n- `code` — merges\u002FPRs touching on-call-relevant paths; reverts; deploys\n- `metrics` — week-over-week trend of the health signals in `ONCALL.md`\n- `lessons.md` — every entry appended this shift\n- each incident record's history over the shift window\n\nCross-reference: an alert with no thread, a lessons entry with no incident,\na metric trending wrong with no alert — these orphans are usually the \"watch\nthis week\" items.\n\n## Format\n\nPost to the channel as a message with the exec summary, full doc attached or\nlinked:\n\n> 📋 **On-call handoff — week of {{date}}**\n>\n> **Exec summary:** N incidents (n resolved, n monitoring). N pages.\n> Anything systemic in one clause.\n> **On-call health:** the required weekly metric — incidents and pages\n> vs. last week, split by business-hours \u002F off-hours, false pages, the\n> **rubber-stamp fraction** (diagnoses acted on with no recorded\n> verification step — the early warning that humans stopped\n> cross-examining; see eval\u002Freplay.md), and whether the trend is up or\n> down. This section is how the whole setup is\n> measured over time (see eval\u002Freplay.md), so never omit it and never\n> soften it.\n> **Intake health:** median and worst time from symptom onset to incident\n> declared this week (onset from the alert\u002Fthread timeline; declaration\n> from the incident record). If incidents routinely run 40 minutes before\n> anyone declares one, that's the process finding of the week — you can't\n> fix an intake path you don't measure.\n> **Watch this week:** the 1–3 things most likely to page you, each with\n> why and a link to its pattern (`lessons.md` tag or reference file).\n> **Start here:** the single highest-priority open item, with its current\n> state and next action.\n> **Full doc:** [link] · New to this channel? Read `ONBOARD.md` — how to\n> read a diagnosis, challenge one, or silence a routine.\n\nThe full doc, per incident: **what happened** (one fresh-reader sentence,\nlinks) · **what it means** (pattern or one-off? systemic risk?) · **what you\nshould do** (nothing \u002F monitor \u002F action, with the action named).\n\nThen: open items ranked by \"will this page you?\", not by age. Preventable\nrepeats called out as playbook gaps with proposed reference-file amendments\n(rule 9 — fix the playbook, not just the incident).\n\n## Drift check (required section)\n\nThe ground moves between incidents; this is where the kit notices. Each\nweek, flag:\n\n- any `STACK.md` binding that failed or 403'd during the week's work\n- any reference file whose first-checks cite a tool or query that no\n  longer responds\n- anything in the `deploys` feed or announcement channels suggesting the\n  infrastructure changed under the playbooks — a migration completed, a\n  tool replaced, a service renamed\n- the routine registry vs. reality: does the \"Standing work\" canvas match\n  the channel's actual routines? Fix the registry; flag any routine that\n  exists but was never registered\n- open incidents with no update in >{{72h}} — the zombie list, each with\n  its three-leg staleness evidence per ONCALL.md's lifecycle section,\n  framed as \"close it or update it\", never closed by Claude (rule 2)\n\nEach flag arrives as a proposal, never an edit (rule 9): \"re-run Discover\nfor this binding,\" a reference-file amendment PR, or \"re-run the replay\nagainst post-change incidents\" (see eval\u002Freplay.md's re-validation\ntriggers). A quiet week with no drift gets one line: \"no drift detected.\"\n\n## Discipline\n\n- \"Here's what happened\" without \"start here\" is a diary, not a handoff —\n  the priorities are the point.\n- Never soften a preventable repeat. Write it plainly: \"2 auto-reverts,\n  both preventable.\"\n- If the week was quiet, say so in two lines and stop. Padding a quiet week\n  erodes trust in loud ones.\n","\u003C!-- Copyright 2026 Anthropic PBC -->\n\u003C!-- SPDX-License-Identifier: Apache-2.0 -->\n\n# Handoff\n\nStanding rules in `CLAUDE.md` apply — especially rules 10 and 11: fresh\nreader, lead with what to do. The incoming on-call missed everything; this\ndocument is their entire week's context, and it must arrive as **work they\ncan start**, not \"here's what happened\".\n\n## Sources — sweep all of them\n\nFan out across every capability in `STACK.md` for the shift window\n(default: the week since the last handoff):\n\n- `pager` — every page and incident: state, severity, resolution\n- `alert-channels` — what fired, what people said, what never got a thread\n- `code` — merges\u002FPRs touching on-call-relevant paths; reverts; deploys\n- `metrics` — week-over-week trend of the health signals in `ONCALL.md`\n- `lessons.md` — every entry appended this shift\n- each incident record's history over the shift window\n\nCross-reference: an alert with no thread, a lessons entry with no incident,\na metric trending wrong with no alert — these orphans are usually the \"watch\nthis week\" items.\n\n## Format\n\nPost to the channel as a message with the exec summary, full doc attached or\nlinked:\n\n> 📋 **On-call handoff — week of {{date}}**\n>\n> **Exec summary:** N incidents (n resolved, n monitoring). N pages.\n> Anything systemic in one clause.\n> **On-call health:** the required weekly metric — incidents and pages\n> vs. last week, split by business-hours \u002F off-hours, false pages, the\n> **rubber-stamp fraction** (diagnoses acted on with no recorded\n> verification step — the early warning that humans stopped\n> cross-examining; see eval\u002Freplay.md), and whether the trend is up or\n> down. This section is how the whole setup is\n> measured over time (see eval\u002Freplay.md), so never omit it and never\n> soften it.\n> **Intake health:** median and worst time from symptom onset to incident\n> declared this week (onset from the alert\u002Fthread timeline; declaration\n> from the incident record). If incidents routinely run 40 minutes before\n> anyone declares one, that's the process finding of the week — you can't\n> fix an intake path you don't measure.\n> **Watch this week:** the 1–3 things most likely to page you, each with\n> why and a link to its pattern (`lessons.md` tag or reference file).\n> **Start here:** the single highest-priority open item, with its current\n> state and next action.\n> **Full doc:** [link] · New to this channel? Read `ONBOARD.md` — how to\n> read a diagnosis, challenge one, or silence a routine.\n\nThe full doc, per incident: **what happened** (one fresh-reader sentence,\nlinks) · **what it means** (pattern or one-off? systemic risk?) · **what you\nshould do** (nothing \u002F monitor \u002F action, with the action named).\n\nThen: open items ranked by \"will this page you?\", not by age. Preventable\nrepeats called out as playbook gaps with proposed reference-file amendments\n(rule 9 — fix the playbook, not just the incident).\n\n## Drift check (required section)\n\nThe ground moves between incidents; this is where the kit notices. Each\nweek, flag:\n\n- any `STACK.md` binding that failed or 403'd during the week's work\n- any reference file whose first-checks cite a tool or query that no\n  longer responds\n- anything in the `deploys` feed or announcement channels suggesting the\n  infrastructure changed under the playbooks — a migration completed, a\n  tool replaced, a service renamed\n- the routine registry vs. reality: does the \"Standing work\" canvas match\n  the channel's actual routines? Fix the registry; flag any routine that\n  exists but was never registered\n- open incidents with no update in >{{72h}} — the zombie list, each with\n  its three-leg staleness evidence per ONCALL.md's lifecycle section,\n  framed as \"close it or update it\", never closed by Claude (rule 2)\n\nEach flag arrives as a proposal, never an edit (rule 9): \"re-run Discover\nfor this binding,\" a reference-file amendment PR, or \"re-run the replay\nagainst post-change incidents\" (see eval\u002Freplay.md's re-validation\ntriggers). A quiet week with no drift gets one line: \"no drift detected.\"\n\n## Discipline\n\n- \"Here's what happened\" without \"start here\" is a diary, not a handoff —\n  the priorities are the point.\n- Never soften a preventable repeat. Write it plainly: \"2 auto-reverts,\n  both preventable.\"\n- If the week was quiet, say so in two lines and stop. Padding a quiet week\n  erodes trust in loud ones.\n",{"name":5,"description":7},"main","c03282cd5381a5a2e12e32bfb3c8957d52ce01f1","skills\u002Fhandoff",26,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Foncall-kit","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-08-07 03:11:35",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add anthropics\u002Foncall-kit --skill handoff",{"tool":54,"command":55},"bunx","bunx skills add anthropics\u002Foncall-kit --skill handoff",{"tool":57,"command":58},"pnpm","pnpm dlx skills add anthropics\u002Foncall-kit --skill handoff","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Foncall-kit\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002FSKILL.md",true,[],[63,86,108],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":35},"01M718HM2Z99H6P2ZAV25ZZ1T0","weather","The optional standing status report (\"the weather\"): compile open incidents, build health, merge-queue stats, and deploy lag into one always-current report page, and post to the channel only when a defined event fires. Use when the weather routine fires, or when someone asks to run\u002Fupdate the weather report.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Foncall-kit\u002Fblob\u002Fmain\u002Fskills\u002Fweather\u002FSKILL.md",[],[65,28,70,71,72,73,74,75,76,77,22,78,79,80,81,82,29,83,84,85],"only","open","status report","post","run","merge","update","status","page","event","compile","incidents","build health","weather report","stats","health",{"skillNo":87,"name":21,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":35},"01M718HHWHC8Y2F9FN08Z7ZJ26","Investigate an alert or incident in this channel: classify the symptom, load the matching triage reference, check lessons.md for known causes, and post a grounded first-pass diagnosis with evidence links and a proposed (never executed) fix. Use when an alert fires, a routine detects a new anomaly, or someone reports something broken (\"tests aren't running\", \"deploys look stuck\", \"is CI down?\").","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Foncall-kit\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[],[21,92,93,28,94,95,29,96,97,98,99,100,101,102,103,104,105,32,106,107],"tests","check","alert","load","lessons","new","ci","running","links","broken","evidence","never","anomaly","down","incident","fix",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":35},"01M718HE63YJFD1DJ2K53C66TW","oncall-setup","Bootstrap a Claude-assisted on-call for this channel\u002Frepo: discover the available connectors, mine incident history into draft triage playbooks, interview the human for policy, validate against held-out incidents, and install the scheduled routines. Use when the user wants to \"set up on-call\", \"bootstrap the on-call kit\", \"onboard this channel\", or has just installed the oncall-kit plugin. Five gated phases — never run more than one phase per turn, and never activate anything before Phase 4 sign-off.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Foncall-kit\u002Fblob\u002Fmain\u002Fskills\u002Foncall-setup\u002FSKILL.md",[],[115,116,117,118,119,120,121,103,122,123,32,124,125,106,126,81,31,30,127,128],"oncall","setup","oncall setup","routines","SET","interview","mine","history","discover","just","repo","policy","more","kit"]