[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6N9B46GVKZHP0AP5XEF1RTX":3,"skill-same:01M6N9B46GVKZHP0AP5XEF1RTX":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6N9B46GVKZHP0AP5XEF1RTX","bubbles-scope-workflow-runtime",null,"Operate Bubbles scope artifacts correctly during planning, implementation, testing, and validation. Use when creating a new scope, deciding between single-file and per-scope-directory layout, writing a Test Plan, choosing DoD shape, picking the next scope to work, or honoring scope isolation during multi-scope work.","pkirsanov\u002Fsmackerel","pkirsanov","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F138962?v=4","01M6N8NAPD2KXMVC17X6GJ0WZ5","01M6N8NATQ9SAZ00H9D61R0TPV",1,"MIT","https:\u002F\u002Fgithub.com\u002Fpkirsanov\u002Fsmackerel\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbubbles-scope-workflow-runtime\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"bubbles scope workflow runtime","workflow","scope","runtime","workflow runtime","use","operate","multi","dod","next","single-file","testing","work","plan","test plan","file","artifacts","planning","test","writing","2026-11-10 10:12:30",false,"---\nname: bubbles-scope-workflow-runtime\ndescription: Operate Bubbles scope artifacts correctly during planning, implementation, testing, and validation. Use when creating a new scope, deciding between single-file and per-scope-directory layout, writing a Test Plan, choosing DoD shape, picking the next scope to work, or honoring scope isolation during multi-scope work.\n---\n\n# Bubbles Scope Workflow Runtime\n\n## Goal\nUse the scope layout, DoD shape, dependency declarations, and isolation rules the framework expects, so every scope's evidence and status changes survive `state-transition-guard.sh` and `artifact-lint.sh`.\n\n## When to use\n- Creating or revising `specs\u002F\u003CNNN>\u002Fscopes.md`\n- Splitting a feature into per-scope directories\n- Picking the next scope to execute (DAG-based work selection)\n- Writing the Test Plan table for a scope\n- Choosing between single-file and tiered DoD format\n\n## v4.1.0 scope-kind taxonomy\n\nScopes may declare an optional `Scope-Kind:` header to opt out of E2E enforcement when the scope legitimately does not produce live-runtime evidence:\n\n```markdown\n## Scope 3 — Cosign signature verification\nStatus: Done (completed_owned)\nScope-Kind: deploy-pointer\nLockdown-FRs: [FR-020]\n```\n\nValid kinds (default `runtime-behavior`): `runtime-behavior`, `contract-only`, `deploy-pointer`, `ci-config`, `docs-only`, `bootstrap`. Only `runtime-behavior` enforces the 3-row E2E DoD\u002FTest-Plan requirement (G008A). See [`docs\u002Fv4.1.0-delivered-pending-activation.md`](..\u002F..\u002Fdocs\u002Fv4.1.0-delivered-pending-activation.md) for the full taxonomy + lockdown tag patterns + evidence-by-reference anchor convention.\n\n## Layout decision\n| Scope count | Layout |\n|-------------|--------|\n| ≤ 5 scopes | Single `specs\u002F\u003CNNN>\u002Fscopes.md` with all scopes inline |\n| 6+ scopes | `specs\u002F\u003CNNN>\u002Fscopes\u002F_index.md` + per-scope directory `specs\u002F\u003CNNN>\u002Fscopes\u002FNN-name\u002Fscope.md` (one `report.md` per scope optional) |\n\n## Required scope sections (every scope)\n1. **Status** — `Not Started` \u002F `In Progress` \u002F `Done` \u002F `Blocked`\n2. **Depends On** — list of scope IDs this scope blocks on (DAG, no cycles)\n3. **Gherkin scenarios** — Given\u002FWhen\u002FThen per acceptance criterion\n4. **Implementation plan** — short ordered list of steps; vertical slice preferred over horizontal layer batches\n5. **Test Plan table** — one row per test that will execute, with file path, category (from Canonical Test Taxonomy), description, command, live-system Yes\u002FNo\n6. **Definition of Done — Tiered Format** — Core Items (one bullet per scope-specific outcome) + Build Quality Gate (one grouped bullet covering lint\u002Fformat\u002Fwarnings\u002Fartifact-lint\u002Fdocs)\n\n## Test Plan ↔ DoD parity (NON-NEGOTIABLE)\nTest Plan row count MUST equal DoD test-related item count. The framework's lint rejects scopes where they diverge.\n\n## Stress tests when latency SLAs present (G026)\nIf the scope's Gherkin or design defines a latency target (`\u003C X ms`, `p95 \u003C Y`, throughput target), the Test Plan MUST include a `stress` row and the DoD MUST include a corresponding stress evidence item.\n\n## Scope isolation (per-scope-directory mode)\n- Each scope only edits its own `scopes\u002FNN-name\u002F` files plus its owned source\u002Ftest files.\n- A scope MUST NOT silently amend another scope's DoD, scenarios, or status. Surface the gap via the orchestrator.\n\n## DAG-based pickup\nWhen picking the next scope:\n1. List scopes whose `Status: Not Started` AND every `Depends On` is `Done`.\n2. From that ready set, prefer the smallest, most foundational scope.\n3. Never start work on a scope while a higher-priority pre-existing bug remains in the same feature folder (warn-then-proceed only with explicit acknowledgment).\n\n## Pre-existing bug awareness\nBefore starting new scope work in `specs\u002F\u003Cfeature>\u002F`, scan `specs\u002F\u003Cfeature>\u002Fbugs\u002F*\u002Fstate.json` for `status: in_progress|not_started|blocked`. Surface findings to the orchestrator.\n\n## DoD anti-patterns\n- ❌ \"All tests passing\" as a single catch-all DoD item — split per category\n- ❌ \"Audit clean\" as a catch-all on top of Build Quality Gate — duplicate\n- ❌ Pre-checking DoD items `[x]` at scope creation — every `[x]` must come from real execution\n- ❌ DoD items without inline evidence reference\n\n## Authoritative modules\n- `agents\u002Fbubbles_shared\u002Fscope-workflow.md` — workflow phases + status ceiling\n- `agents\u002Fbubbles_shared\u002Fscope-templates.md` — scope.md canonical template\n- `agents\u002Fbubbles_shared\u002Fartifact-lifecycle.md` — feature\u002Fbug artifact lifecycle\n- `agents\u002Fbubbles_shared\u002Fplanning-core.md` — Test Plan shape + test-plan.json handoff\n- `agents\u002Fbubbles_shared\u002Fstate-gates.md` — status integrity\n- `bubbles\u002Fscripts\u002Fartifact-lint.sh` — template\u002Fsection presence enforcement\n","# Bubbles Scope Workflow Runtime\n\n## Goal\nUse the scope layout, DoD shape, dependency declarations, and isolation rules the framework expects, so every scope's evidence and status changes survive `state-transition-guard.sh` and `artifact-lint.sh`.\n\n## When to use\n- Creating or revising `specs\u002F\u003CNNN>\u002Fscopes.md`\n- Splitting a feature into per-scope directories\n- Picking the next scope to execute (DAG-based work selection)\n- Writing the Test Plan table for a scope\n- Choosing between single-file and tiered DoD format\n\n## v4.1.0 scope-kind taxonomy\n\nScopes may declare an optional `Scope-Kind:` header to opt out of E2E enforcement when the scope legitimately does not produce live-runtime evidence:\n\n```markdown\n## Scope 3 — Cosign signature verification\nStatus: Done (completed_owned)\nScope-Kind: deploy-pointer\nLockdown-FRs: [FR-020]\n```\n\nValid kinds (default `runtime-behavior`): `runtime-behavior`, `contract-only`, `deploy-pointer`, `ci-config`, `docs-only`, `bootstrap`. Only `runtime-behavior` enforces the 3-row E2E DoD\u002FTest-Plan requirement (G008A). See [`docs\u002Fv4.1.0-delivered-pending-activation.md`](..\u002F..\u002Fdocs\u002Fv4.1.0-delivered-pending-activation.md) for the full taxonomy + lockdown tag patterns + evidence-by-reference anchor convention.\n\n## Layout decision\n| Scope count | Layout |\n|-------------|--------|\n| ≤ 5 scopes | Single `specs\u002F\u003CNNN>\u002Fscopes.md` with all scopes inline |\n| 6+ scopes | `specs\u002F\u003CNNN>\u002Fscopes\u002F_index.md` + per-scope directory `specs\u002F\u003CNNN>\u002Fscopes\u002FNN-name\u002Fscope.md` (one `report.md` per scope optional) |\n\n## Required scope sections (every scope)\n1. **Status** — `Not Started` \u002F `In Progress` \u002F `Done` \u002F `Blocked`\n2. **Depends On** — list of scope IDs this scope blocks on (DAG, no cycles)\n3. **Gherkin scenarios** — Given\u002FWhen\u002FThen per acceptance criterion\n4. **Implementation plan** — short ordered list of steps; vertical slice preferred over horizontal layer batches\n5. **Test Plan table** — one row per test that will execute, with file path, category (from Canonical Test Taxonomy), description, command, live-system Yes\u002FNo\n6. **Definition of Done — Tiered Format** — Core Items (one bullet per scope-specific outcome) + Build Quality Gate (one grouped bullet covering lint\u002Fformat\u002Fwarnings\u002Fartifact-lint\u002Fdocs)\n\n## Test Plan ↔ DoD parity (NON-NEGOTIABLE)\nTest Plan row count MUST equal DoD test-related item count. The framework's lint rejects scopes where they diverge.\n\n## Stress tests when latency SLAs present (G026)\nIf the scope's Gherkin or design defines a latency target (`\u003C X ms`, `p95 \u003C Y`, throughput target), the Test Plan MUST include a `stress` row and the DoD MUST include a corresponding stress evidence item.\n\n## Scope isolation (per-scope-directory mode)\n- Each scope only edits its own `scopes\u002FNN-name\u002F` files plus its owned source\u002Ftest files.\n- A scope MUST NOT silently amend another scope's DoD, scenarios, or status. Surface the gap via the orchestrator.\n\n## DAG-based pickup\nWhen picking the next scope:\n1. List scopes whose `Status: Not Started` AND every `Depends On` is `Done`.\n2. From that ready set, prefer the smallest, most foundational scope.\n3. Never start work on a scope while a higher-priority pre-existing bug remains in the same feature folder (warn-then-proceed only with explicit acknowledgment).\n\n## Pre-existing bug awareness\nBefore starting new scope work in `specs\u002F\u003Cfeature>\u002F`, scan `specs\u002F\u003Cfeature>\u002Fbugs\u002F*\u002Fstate.json` for `status: in_progress|not_started|blocked`. Surface findings to the orchestrator.\n\n## DoD anti-patterns\n- ❌ \"All tests passing\" as a single catch-all DoD item — split per category\n- ❌ \"Audit clean\" as a catch-all on top of Build Quality Gate — duplicate\n- ❌ Pre-checking DoD items `[x]` at scope creation — every `[x]` must come from real execution\n- ❌ DoD items without inline evidence reference\n\n## Authoritative modules\n- `agents\u002Fbubbles_shared\u002Fscope-workflow.md` — workflow phases + status ceiling\n- `agents\u002Fbubbles_shared\u002Fscope-templates.md` — scope.md canonical template\n- `agents\u002Fbubbles_shared\u002Fartifact-lifecycle.md` — feature\u002Fbug artifact lifecycle\n- `agents\u002Fbubbles_shared\u002Fplanning-core.md` — Test Plan shape + test-plan.json handoff\n- `agents\u002Fbubbles_shared\u002Fstate-gates.md` — status integrity\n- `bubbles\u002Fscripts\u002Fartifact-lint.sh` — template\u002Fsection presence enforcement\n",{"name":5,"description":7},"main","ed893cc338281a0bb9bb9ecf3415716cb242bb3f",".claude\u002Fskills\u002Fbubbles-scope-workflow-runtime",0,"https:\u002F\u002Fgithub.com\u002Fpkirsanov\u002Fsmackerel","https:\u002F\u002Fgithub.com\u002Fpkirsanov","2026-11-07 02:54:37",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add pkirsanov\u002Fsmackerel --skill bubbles-scope-workflow-runtime",{"tool":64,"command":65},"bunx","bunx skills add pkirsanov\u002Fsmackerel --skill bubbles-scope-workflow-runtime",{"tool":67,"command":68},"pnpm","pnpm dlx skills add pkirsanov\u002Fsmackerel --skill bubbles-scope-workflow-runtime","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpkirsanov\u002Fsmackerel\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbubbles-scope-workflow-runtime\u002FSKILL.md",true,[],[73,99,127,152,172,199],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":80,"publishedAt":46},"01M6N9V5TBHQT20V5SCCJ1VRBC","smackerel-trace-capture","Wire Smackerel's concrete validate-plane stack into the framework trace-driven defect-discovery method. Use when running live-category tests (integration\u002Fe2e\u002Fe2e-ui\u002Fstress) against the ephemeral test stack; capturing SLO or trace evidence; hunting latency\u002Ferror\u002Fperf bugs from spans; querying the test-stack Jaeger or Prometheus; or touching `.specify\u002Fruntime\u002Fobservability`. Concrete smackerel endpoints + the exact `capture-slo.sh` command; do NOT duplicate `bubbles-observability-adapter` — this only adds the wiring.","https:\u002F\u002Fgithub.com\u002Fpkirsanov\u002Fsmackerel\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsmackerel-trace-capture\u002FSKILL.md",[79],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[81,82,83,84,85,86,87,88,89,31,90,91,92,93,94,29,95,96,97,98],"trace","capture","smackerel trace capture","perf","observability","prometheus","specify","e2e","discovery","slo","only","evidence","do","latency","tests","adapter","error","bugs",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":108,"publishedAt":46},"01M6N9TZDEV26RZ7W34HEFPQE9","smackerel-no-defaults","Enforce Smackerel's NO-DEFAULTS \u002F fail-loud SST policy. Use when editing config, Docker Compose, deploy adapters, docs, instructions, skills, env handling, host bind addresses, or any runtime value that could be hidden by fallback syntax.","https:\u002F\u002Fgithub.com\u002Fpkirsanov\u002Fsmackerel\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsmackerel-no-defaults\u002FSKILL.md",[105],{"categoryNo":106,"categoryName":107,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[109,110,111,112,113,114,115,116,117,31,118,119,29,120,121,122,123,124,125,126],"smackerel no defaults","docker","policy","config","deploy","docker compose","syntax","editing","instructions","compose","enforce","bind","env","host","Adapters","sst","addresses","value",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":134,"publishedAt":46},"01M6N9TJRS5PF83JH2W4614D4W","bubbles-workflow-mode-resolution","Resolve a Bubbles workflow mode against `bubbles\u002Fworkflows.yaml`, including template inheritance, status ceilings, gate wiring, and decision policy. Use when picking a mode for a request, when a guard reports a mode-related failure, or when extending workflows.yaml with a new mode or template. Covers natural-language intent routing and the workflow registry consistency rules.","https:\u002F\u002Fgithub.com\u002Fpkirsanov\u002Fsmackerel\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fbubbles-workflow-mode-resolution\u002FSKILL.md",[133],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[27,135,136,137,111,138,139,140,141,142,143,31,144,145,146,147,148,149,150,151],"resolution","mode","bubbles workflow mode resolution","workflows","routing","guard","template","decision","Rules","reports","intent","inheritance","with","consistency","natural-language","for","wiring",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":159,"publishedAt":46},"01M6N9TC98D6DJR0D64SSN0SN3","bubbles-workflow-execution-loops","Run per-round synchronous workflow execution loops correctly. Use when orchestrating a multi-round workflow, dispatching specialist subagents, handling round-based remediation, or interpreting a workflow mode's execution policy. Covers authorized direct execution, dispatch-and-wait, batch-then-summarize prohibition, and mapped-mode execution.","https:\u002F\u002Fgithub.com\u002Fpkirsanov\u002Fsmackerel\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fbubbles-workflow-execution-loops\u002FSKILL.md",[158],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[27,160,161,162,163,111,164,165,166,167,168,31,169,170,33,171,136],"execution","loops","bubbles workflow execution loops","summarize","run","batch","remediation","direct","subagents","dispatch","wait","multi-round",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":182,"publishedAt":46},"01M6N9SYXQNJDQ1T1YT81JH2BG","bubbles-vscode-agent-constraints","Design agents that fit the VS Code Copilot Chat runtime instead of fighting it. Use when authoring or editing any `*.agent.md`; when adding `tools:`, `agents:`, `handoffs:`, `model:`, `user-invocable:`, or `disable-model-invocation:` frontmatter; when designing an orchestrator that dispatches specialists; when a design implies agent-calls-agent-calls-agent chaining; when a subagent dispatch silently no-ops or an agent cannot be selected in the dropdown; or when writing a governance rule about delegation that the runtime cannot actually enforce. Prevents multi-level-subagent designs, prose-only dispatch laws, and frontmatter\u002Fbody contradictions.","https:\u002F\u002Fgithub.com\u002Fpkirsanov\u002Fsmackerel\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fbubbles-vscode-agent-constraints\u002FSKILL.md",[178,181],{"categoryNo":179,"categoryName":180,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[183,184,185,186,45,187,188,189,190,191,192,193,116,194,91,29,195,196,197,198],"vscode","constraints","bubbles vscode agent constraints","design","copilot","code","delegation","Tools","subagent","model","chaining","orchestrator","authoring","fit","subagent dispatch","frontmatter",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":205,"publishedAt":46},"01M6N9SD78SK12PRT9KBRZ6TB3","bubbles-upkeep-cadence","How to schedule, dispatch, and record recurring operational upkeep tasks (backup, restore-drill, BCDR-drill, patch-cycle, secret-rotation, flag-cleanup, compliance-sweep). Use when authoring or modifying `config\u002Fupkeep-calendar.yaml`, when investigating a missed task, when reading the upkeep ledger, or when adding a new task type.","https:\u002F\u002Fgithub.com\u002Fpkirsanov\u002Fsmackerel\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fbubbles-upkeep-cadence\u002FSKILL.md",[],[206,207,208,209,210,211,212,213,31,214,215,216,217,218,219,220,221,222,223,224],"cadence","bubbles upkeep cadence","tasks","cleanup","backup","sweep","schedule","recurring","patch","restore","task","cycle","record","missed","type","drill","how to","new task","rotation"]