[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HBVTDPNPD88ZWXT4T5M8EA":3,"skill-same:01M6HBVTDPNPD88ZWXT4T5M8EA":69},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":48,"updatedAt":49,"install":50,"resources":62},"01M6HBVTDPNPD88ZWXT4T5M8EA","triage",null,"Respond to a production incident, outage, or regression in the wild: establish the timeline, assess blast radius, and reconstruct what happened with cited evidence. Use this when something is failing in production and you need to understand it before fixing it.","SyloRei\u002Fclaude-godmode","SyloRei","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5840195?v=4","01M6HBT6QSK7QM4DTVPNGARNP4","Andrey Prokofev","01M6HBT6WED1MEN8W7JYP412WE",3,"MIT","https:\u002F\u002Fgithub.com\u002FSyloRei\u002Fclaude-godmode\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"production incident","wild","true","you","with","understand","it","respond","assess","incident","evidence","use","regression","radius","timeline","Production","blast radius","2026-11-10 10:12:30",false,"---\nname: triage\ndescription: \"Respond to a production incident, outage, or regression in the wild: establish the timeline, assess blast radius, and reconstruct what happened with cited evidence. Use this when something is failing in production and you need to understand it before fixing it.\"\nuser-invocable: true\n---\n\n# Incident Triage\n\nRespond to a live production incident — an outage, a regression, or unexpected\nbehavior reported from the field. Establish what happened and how bad it is\nBEFORE touching code. This skill triages; it does not write the fix.\n\n---\n\n## Auto Mode\n\nAuto Mode suppresses confirmation prompts and proceed-pauses — not the one\nclarifying question that can matter here: **when it started, when it was last\nknown-good, or who reported it is unknown, don't ask blank — lead with your\nbest-inferred answer to override** (e.g. \"I'll take the incident start as the\nfirst error at 14:02 UTC — correct me if it began earlier\"), since triaging the\nwrong incident wastes the whole effort. This clarifying question follows the\nshared recommendation convention (`godmode:recommend-convention`) defined in\n`rules\u002Fgodmode-recommend.md`. Once the symptom is anchored, proceed: reconstruct\nthe timeline, assess blast radius, and route the fix without pausing. Treat\ncourse-corrections as normal input.\n\n---\n\n## The Job\n\n1. Establish the timeline\n2. Assess blast radius\n3. Reconstruct with cited evidence via `@incident-responder`\n4. Route the confirmed fix\n\nDo NOT skip to the fix. Understand the incident first.\n\n---\n\n## Step 1: TIMELINE\n\n- What is the first observed symptom? (error, alert, user report)\n- When did it start? When was the system last known-good?\n- What changed in that window? (deploys, config, dependency, traffic)\n\n**Output:** \"Symptom [X] first seen at [time]. Last known-good [time]. Changed in window: [Y].\"\n\n---\n\n## Step 2: BLAST RADIUS\n\n- Who and what is affected? (users, endpoints, regions, downstream systems)\n- How severe is it? (full outage, degraded, single feature, cosmetic)\n- Is it still ongoing or self-resolved?\n\n**Output:** \"Affected: [scope]. Severity: [level]. Status: [ongoing\u002Fresolved].\"\n\n---\n\n## Step 3: RECONSTRUCT (spawn `@incident-responder`)\n\nSpawn `@incident-responder` (read-only) to reconstruct the timeline against the\ncode and recommend remediation with cited evidence. It investigates; it does\nnot change code.\n\n- It correlates the symptom and the change window with the codebase\n- It returns a reconstructed timeline and remediation options with `file:line`\n  evidence\n\n**Output:** \"Root cause hypothesis: [cause] at [file:line]. Remediation: [options].\"\n\n---\n\n## Step 4: ROUTE THE FIX\n\nThe triage itself does not write the fix. Once a code fix is confirmed:\n\n- Route a small, well-understood defect to `@debugger` for a minimal targeted\n  fix plus regression test.\n- Route a larger or isolated change to `@writer`.\n\n**Output:** \"Routed [fix] to [@debugger \u002F @writer].\"\n\n---\n\n## Rules\n\n- Triage before fixing. Anchor the symptom and blast radius first.\n- `@incident-responder` is read-only — it reconstructs and recommends, it never\n  edits code.\n- The skill never writes the fix itself; it routes to `@debugger` or `@writer`.\n- Every root-cause claim must carry `file:line` evidence.\n\n---\n\n## Agent Routing\n\n| Step | Agent | Purpose |\n|------|-------|---------|\n| RECONSTRUCT | MUST spawn `@incident-responder` (`subagent_type: claude-godmode:incident-responder`) | Read-only reconstruction of the timeline + remediation with cited evidence |\n| ROUTE | `@debugger` (small defect) or `@writer` (larger change) | Apply the confirmed code fix — the triage skill never writes it inline |\n\n**Rule:** Never reconstruct the incident inline when `@incident-responder` can\ndo it read-only with cited evidence. Never write the fix from this skill.\n\n---\n\n## On-Demand Helper\n\nThis is an on-demand helper, invoked when an incident lands. It is not part of\nthe routine spine and records no workflow state — run it, route the fix, and\nhand off to `@debugger` or `@writer`.\n\n---\n\n## Output\n\n\u003C!-- Output follows the in-skill output convention: godmode:output-convention — see rules\u002Fgodmode-output.md -->\n\nClose the run with one consolidated result block. The per-step `**Output:**` lines above narrate timeline → blast radius → reconstruct → route as you go; this block is the single legible summary the user reads at the end — it leads with the terminal state, summarizes the incident, and names one next move:\n\n- **Status** — incident triaged; the root-cause hypothesis is established and the fix is routed.\n- **Timeline** — first symptom and time, last known-good, and what changed in the window.\n- **Blast radius** — who and what is affected, severity, and whether it is ongoing or resolved.\n- **Remediation** — the routes considered, each with `file:line` evidence.\n- **Next** — the single onward pointer:\n\n> \"Incident triaged. Root-cause hypothesis: [cause] at [file:line]. Affected [scope], severity [level], [ongoing\u002Fresolved]. Routed the fix to `@debugger`. Run `\u002Fdebug` to verify the fix, then `\u002Fbrief N` if it warrants a tracked work unit.\"\n\n---\n\n## Related\n\n- **@incident-responder** — read-only reconstruction and remediation advice\n- **@debugger** — minimal targeted fix plus regression test for a confirmed defect\n- **@writer** — larger or isolated fix\n- **\u002Fdebug** — once the fix is in hand, the debugging protocol verifies it\n\n**Spine:** off-spine helper — triage the incident and route the fix, then resume the spine at `\u002Fbrief N` if the fix warrants a tracked work unit.\n","# Incident Triage\n\nRespond to a live production incident — an outage, a regression, or unexpected\nbehavior reported from the field. Establish what happened and how bad it is\nBEFORE touching code. This skill triages; it does not write the fix.\n\n---\n\n## Auto Mode\n\nAuto Mode suppresses confirmation prompts and proceed-pauses — not the one\nclarifying question that can matter here: **when it started, when it was last\nknown-good, or who reported it is unknown, don't ask blank — lead with your\nbest-inferred answer to override** (e.g. \"I'll take the incident start as the\nfirst error at 14:02 UTC — correct me if it began earlier\"), since triaging the\nwrong incident wastes the whole effort. This clarifying question follows the\nshared recommendation convention (`godmode:recommend-convention`) defined in\n`rules\u002Fgodmode-recommend.md`. Once the symptom is anchored, proceed: reconstruct\nthe timeline, assess blast radius, and route the fix without pausing. Treat\ncourse-corrections as normal input.\n\n---\n\n## The Job\n\n1. Establish the timeline\n2. Assess blast radius\n3. Reconstruct with cited evidence via `@incident-responder`\n4. Route the confirmed fix\n\nDo NOT skip to the fix. Understand the incident first.\n\n---\n\n## Step 1: TIMELINE\n\n- What is the first observed symptom? (error, alert, user report)\n- When did it start? When was the system last known-good?\n- What changed in that window? (deploys, config, dependency, traffic)\n\n**Output:** \"Symptom [X] first seen at [time]. Last known-good [time]. Changed in window: [Y].\"\n\n---\n\n## Step 2: BLAST RADIUS\n\n- Who and what is affected? (users, endpoints, regions, downstream systems)\n- How severe is it? (full outage, degraded, single feature, cosmetic)\n- Is it still ongoing or self-resolved?\n\n**Output:** \"Affected: [scope]. Severity: [level]. Status: [ongoing\u002Fresolved].\"\n\n---\n\n## Step 3: RECONSTRUCT (spawn `@incident-responder`)\n\nSpawn `@incident-responder` (read-only) to reconstruct the timeline against the\ncode and recommend remediation with cited evidence. It investigates; it does\nnot change code.\n\n- It correlates the symptom and the change window with the codebase\n- It returns a reconstructed timeline and remediation options with `file:line`\n  evidence\n\n**Output:** \"Root cause hypothesis: [cause] at [file:line]. Remediation: [options].\"\n\n---\n\n## Step 4: ROUTE THE FIX\n\nThe triage itself does not write the fix. Once a code fix is confirmed:\n\n- Route a small, well-understood defect to `@debugger` for a minimal targeted\n  fix plus regression test.\n- Route a larger or isolated change to `@writer`.\n\n**Output:** \"Routed [fix] to [@debugger \u002F @writer].\"\n\n---\n\n## Rules\n\n- Triage before fixing. Anchor the symptom and blast radius first.\n- `@incident-responder` is read-only — it reconstructs and recommends, it never\n  edits code.\n- The skill never writes the fix itself; it routes to `@debugger` or `@writer`.\n- Every root-cause claim must carry `file:line` evidence.\n\n---\n\n## Agent Routing\n\n| Step | Agent | Purpose |\n|------|-------|---------|\n| RECONSTRUCT | MUST spawn `@incident-responder` (`subagent_type: claude-godmode:incident-responder`) | Read-only reconstruction of the timeline + remediation with cited evidence |\n| ROUTE | `@debugger` (small defect) or `@writer` (larger change) | Apply the confirmed code fix — the triage skill never writes it inline |\n\n**Rule:** Never reconstruct the incident inline when `@incident-responder` can\ndo it read-only with cited evidence. Never write the fix from this skill.\n\n---\n\n## On-Demand Helper\n\nThis is an on-demand helper, invoked when an incident lands. It is not part of\nthe routine spine and records no workflow state — run it, route the fix, and\nhand off to `@debugger` or `@writer`.\n\n---\n\n## Output\n\n\u003C!-- Output follows the in-skill output convention: godmode:output-convention — see rules\u002Fgodmode-output.md -->\n\nClose the run with one consolidated result block. The per-step `**Output:**` lines above narrate timeline → blast radius → reconstruct → route as you go; this block is the single legible summary the user reads at the end — it leads with the terminal state, summarizes the incident, and names one next move:\n\n- **Status** — incident triaged; the root-cause hypothesis is established and the fix is routed.\n- **Timeline** — first symptom and time, last known-good, and what changed in the window.\n- **Blast radius** — who and what is affected, severity, and whether it is ongoing or resolved.\n- **Remediation** — the routes considered, each with `file:line` evidence.\n- **Next** — the single onward pointer:\n\n> \"Incident triaged. Root-cause hypothesis: [cause] at [file:line]. Affected [scope], severity [level], [ongoing\u002Fresolved]. Routed the fix to `@debugger`. Run `\u002Fdebug` to verify the fix, then `\u002Fbrief N` if it warrants a tracked work unit.\"\n\n---\n\n## Related\n\n- **@incident-responder** — read-only reconstruction and remediation advice\n- **@debugger** — minimal targeted fix plus regression test for a confirmed defect\n- **@writer** — larger or isolated fix\n- **\u002Fdebug** — once the fix is in hand, the debugging protocol verifies it\n\n**Spine:** off-spine helper — triage the incident and route the fix, then resume the spine at `\u002Fbrief N` if the fix warrants a tracked work unit.\n",{"name":5,"description":7,"user-invocable":41},true,"main","717a1f3af996804502df0047840b6c74a1d464c5","skills\u002Ftriage",0,"https:\u002F\u002Fgithub.com\u002FSyloRei\u002Fclaude-godmode","https:\u002F\u002Fgithub.com\u002FSyloRei","Nya? Kawai? Desu?","2026-06-08 16:03:07",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":41},[52,55,58],{"tool":53,"command":54},"npx","npx skills add SyloRei\u002Fclaude-godmode --skill triage",{"tool":56,"command":57},"bunx","bunx skills add SyloRei\u002Fclaude-godmode --skill triage",{"tool":59,"command":60},"pnpm","pnpm dlx skills add SyloRei\u002Fclaude-godmode --skill triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSyloRei\u002Fclaude-godmode\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[63],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"scripts\u002FREADME.md","SCRIPT","脚本",1123,"https:\u002F\u002Fgithub.com\u002FSyloRei\u002Fclaude-godmode\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002Fscripts\u002FREADME.md",[70,78,103,132,151,176],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":36},"01M6HBW3WEVBXANCRWF5YK5BYC","{{name=null}=null}","{{description=null}=null}","https:\u002F\u002Fgithub.com\u002FSyloRei\u002Fclaude-godmode\u002Fblob\u002Fmain\u002Ftemplates\u002Fskill\u002FSKILL.md",[],[72,77,21],"name",{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":36},"01M6HBVZ86GN3TGGFSJ4XM9C5Q","verify","Check a built unit goal-backward: classify every brief acceptance criterion COVERED \u002F PARTIAL \u002F MISSING with concrete evidence, so you know what is truly done. Use when: verify N, check whether unit N is done, confirm the goals for roadmap unit N are met.","https:\u002F\u002Fgithub.com\u002FSyloRei\u002Fclaude-godmode\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[80,85,86,87,22,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102],"run","git","godmode","ShellCheck","unit","scripts","classify","done","show","log","goal","roadmap","coverage","read","model","Bash","brief","acceptance",{"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":117,"publishedAt":36},"01M6HBVNQ1ASFTJTYT47F8M559","tdd","Build new behavior test-first using strict Red-Green-Refactor cycles. Use this when you want to drive a new feature or behavior from failing tests before writing the implementation.","https:\u002F\u002Fgithub.com\u002FSyloRei\u002Fclaude-godmode\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[109,114],{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":115,"categoryName":116,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000023","Skill与智能体开发",[105,30,21,22,118,119,120,121,122,123,124,125,126,127,128,129,130,131],"red","feature","tests","green","build","implementation","drive","red-green-refactor","new feature","behavior","first","refactor","test","writing",{"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},"01M6HBVH8GX9JCMS5432JZVTMN","ship","Run every canonical quality gate, push the branch, and open a pull request — release in one command. Use when: ship it, ready to ship, create the PR, push and open a PR.","https:\u002F\u002Fgithub.com\u002FSyloRei\u002Fclaude-godmode\u002Fblob\u002Fmain\u002Fskills\u002Fship\u002FSKILL.md",[],[134,139,90,140,87,86,141,98,142,143,99,100,144,145,146,147,85,148,149,150],"canonical","ship it","ready","command","branch","open","push","pull","release","create","quality gate","pr",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":162,"publishedAt":36},"01M6HBVB6SVSMQPXBMWEWQ4J5M","refine","Mid-mission gap analysis: read the active mission's roadmap and briefs, surface what's missing or underspecified, converge on one gap, and append a NEW numbered work unit plus its full brief — strictly additive. Use when: refine, what are we missing, find gaps in the current mission, add the next unit. Never edits an existing brief or roadmap unit in place — that is \u002Fbrief N's job.","https:\u002F\u002Fgithub.com\u002FSyloRei\u002Fclaude-godmode\u002Fblob\u002Fmain\u002Fskills\u002Frefine\u002FSKILL.md",[157],{"categoryNo":158,"categoryName":159,"taxonomyType":160,"taxonomyTypeDesc":161},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[153,163,164,165,87,96,166,167,168,169,98,170,100,171,101,172,173,174,89,175],"work","active","next","never","append","edit","write","full","analysis","mission","converge","briefs","add",{"skillNo":177,"name":129,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":186,"publishedAt":36},"01M6HBV7SGBH14T5K2336RYZWW","Improve code structure without changing behavior, verifying with tests at every step. Use this when you want to restructure, extract, rename, or simplify existing code that already works.","https:\u002F\u002Fgithub.com\u002FSyloRei\u002Fclaude-godmode\u002Fblob\u002Fmain\u002Fskills\u002Frefactor\u002FSKILL.md",[181,182,183],{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},{"categoryNo":115,"categoryName":116,"taxonomyType":112,"taxonomyTypeDesc":113},{"categoryNo":184,"categoryName":185,"taxonomyType":160,"taxonomyTypeDesc":161},"01JBSEEDCAT000000000000030","开发工程师",[129,127,187,188,189,30,190,191,21,22,23,120,192,193,194],"code","simplify","improve","Existing","at","structure","extract","rename"]