[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ATWNWD24AQ3QYZ5RQSAR2D":3,"skill-same:01M7ATWNWD24AQ3QYZ5RQSAR2D":55},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7ATWNWD24AQ3QYZ5RQSAR2D","specrew-iteration-resume",null,"Resume an interrupted iteration by analyzing state.md plus plan.md's task table and suggesting the next safe execution step or escalation.","alonf\u002FKeyContextAI","alonf","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F554150?v=4","01M7ATEPSCNKG13BVTKA74VG59","Alon Fliess","01M7ATEPSZ4YMBM9W25SKM3GES",0,"MIT","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspecrew-iteration-resume\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"specrew-iteration-resume\"\ndescription: \"Resume an interrupted iteration by analyzing state.md plus plan.md's task table and suggesting the next safe execution step or escalation.\"\ndomain: \"lifecycle-recovery\"\nconfidence: \"high\"\nsource: \"Specrew governance pillar — iteration resume \u002F recovery helper\"\n---\n\n# specrew-iteration-resume\n\n**Type**: Recovery Skill  \n**Schema**: v1  \n**Status**: Active recovery method\n\n## Purpose\n\nResumes interrupted iterations by analyzing `state.md` plus the authoritative task table in `plan.md`, then suggests the next execution step or active repair escalation.\n\n## When to Use\n\n- **When an iteration is interrupted** (agent crash, user stops work, blocker encountered)\n- **When resuming work after a break**\n- **When transferring iteration ownership** (handoff between agents\u002Fhumans)\n\n## Inputs\n\n| Input | Type | Required | Description |\n|-------|------|----------|-------------|\n| iteration_directory | path | Yes | Path to `specs\u002F\u003Cfeature>\u002Fiterations\u002FNNN\u002F` containing `state.md` and `plan.md` |\n| resume_mode | enum: continue, replan, abort | Yes | How to resume the iteration |\n\n## Process\n\n1. Parse `state.md` to extract:\n    - Last completed task\n    - In-progress tasks (started but not done)\n    - Remaining tasks (not yet started)\n    - Active repair escalation state, if one is recorded\n2. Parse `plan.md` to read the authoritative task table and current task statuses.\n3. Reconcile stale or partial `state.md` metadata against the task table:\n   - Repair missing `Tasks Remaining`, `In Progress`, and `Updated` metadata when possible\n   - Treat `planned` tasks as remaining work and `in-progress` \u002F `needs-rework` tasks as active work\n   - Surface blockers when `state.md` references unknown tasks or plan-blocked tasks\n4. Determine resumption strategy based on `resume_mode`:\n    - **continue**: Resume the current repair escalation first; after activating or resolving escalation, sync `.squad\u002Fconfig.json` with `sync-squad-model-overrides.ps1`, otherwise resume the current in-progress task or suggest the next incomplete task\n    - **replan**: Suggest re-planning remaining tasks\n    - **abort**: Mark iteration as abandoned, list salvageable tasks\n5. Generate resume report\n6. Write the report back into `state.md` when the iteration is resumable or intentionally being re-planned\u002Faborted\n\n## Outputs\n\n| Output | Type | Description |\n|--------|------|-------------|\n| status | enum: ready, blocked, needs-replan | Resumption readiness |\n| last_completed_task | string? | ID of last successfully completed task |\n| in_progress_tasks[] | array | Tasks that were started but not finished |\n| remaining_tasks[] | array | Tasks not yet started |\n| next_suggested_task | string? | Task ID to execute next (null if blocked) |\n| next_recovery_action | string? | Escalation step to resume before normal task work |\n| repair_escalation | object | Persisted escalation state from `state.md` |\n| blockers[] | array | Issues preventing resumption |\n| blockers[].type | enum: dependency, role, resource | Type of blocker |\n| blockers[].description | string | What is blocking progress |\n| salvageable_tasks[] | array? | Tasks that can be moved to next iteration (if abort mode) |\n\n## Side Effects\n\n- Updates `state.md` with repaired execution metadata, resume timestamp, escalation summary, suggested next task, and resume report\n- No file writes if status is \"blocked\"\n\n## Error Handling\n\n- If `state.md` is not found under `iteration_directory`: infer state from `plan.md` (all tasks assumed \"planned\")\n- If `plan.md` is not found under `iteration_directory`: return error (cannot resume without plan)\n- If `state.md` references unknown tasks or blocked work: report blockers and preserve the existing file\n\n## Example Usage\n\n```powershell\npwsh -File .\\.specify\\extensions\\specrew-speckit\\scripts\\resume-iteration.ps1 `\n  -IterationDirectory .\\specs\\001-feature\\iterations\\000 `\n  -ResumeMode continue\n```\n\nExpected Output (READY):\n  status: \"ready\"\n  last_completed_task: \"T-003\"\n  in_progress_tasks: []\n  remaining_tasks: [\"T-004\", \"T-005\", \"T-006\"]\n  next_suggested_task: \"T-004\"\n  blockers: []\n  salvageable_tasks: null\n\nExpected Output (BLOCKED):\n  status: \"blocked\"\n  last_completed_task: \"T-003\"\n  in_progress_tasks: [\"T-004\"]\n  remaining_tasks: [\"T-005\", \"T-006\"]\n  next_suggested_task: null\n  blockers:\n    - type: \"dependency\"\n      description: \"T-004 is blocked waiting for external API access\"\n    - type: \"role\"\n      description: \"Reviewer role is unassigned; cannot proceed to review phase\"\n  salvageable_tasks: null\n\nExpected Output (ABORT):\n  status: \"needs-replan\"\n  last_completed_task: \"T-002\"\n  in_progress_tasks: []\n  remaining_tasks: [\"T-003\", \"T-004\", \"T-005\"]\n  next_suggested_task: null\n  blockers:\n    - type: \"resource\"\n      description: \"Critical blocker: upstream dependency no longer available\"\n  salvageable_tasks: [\"T-005\", \"T-006\"]\n\n```\n\n---\n\n**Implementation Status**: Implemented for FR-019 \u002F Iteration 2.\n","# specrew-iteration-resume\n\n**Type**: Recovery Skill  \n**Schema**: v1  \n**Status**: Active recovery method\n\n## Purpose\n\nResumes interrupted iterations by analyzing `state.md` plus the authoritative task table in `plan.md`, then suggests the next execution step or active repair escalation.\n\n## When to Use\n\n- **When an iteration is interrupted** (agent crash, user stops work, blocker encountered)\n- **When resuming work after a break**\n- **When transferring iteration ownership** (handoff between agents\u002Fhumans)\n\n## Inputs\n\n| Input | Type | Required | Description |\n|-------|------|----------|-------------|\n| iteration_directory | path | Yes | Path to `specs\u002F\u003Cfeature>\u002Fiterations\u002FNNN\u002F` containing `state.md` and `plan.md` |\n| resume_mode | enum: continue, replan, abort | Yes | How to resume the iteration |\n\n## Process\n\n1. Parse `state.md` to extract:\n    - Last completed task\n    - In-progress tasks (started but not done)\n    - Remaining tasks (not yet started)\n    - Active repair escalation state, if one is recorded\n2. Parse `plan.md` to read the authoritative task table and current task statuses.\n3. Reconcile stale or partial `state.md` metadata against the task table:\n   - Repair missing `Tasks Remaining`, `In Progress`, and `Updated` metadata when possible\n   - Treat `planned` tasks as remaining work and `in-progress` \u002F `needs-rework` tasks as active work\n   - Surface blockers when `state.md` references unknown tasks or plan-blocked tasks\n4. Determine resumption strategy based on `resume_mode`:\n    - **continue**: Resume the current repair escalation first; after activating or resolving escalation, sync `.squad\u002Fconfig.json` with `sync-squad-model-overrides.ps1`, otherwise resume the current in-progress task or suggest the next incomplete task\n    - **replan**: Suggest re-planning remaining tasks\n    - **abort**: Mark iteration as abandoned, list salvageable tasks\n5. Generate resume report\n6. Write the report back into `state.md` when the iteration is resumable or intentionally being re-planned\u002Faborted\n\n## Outputs\n\n| Output | Type | Description |\n|--------|------|-------------|\n| status | enum: ready, blocked, needs-replan | Resumption readiness |\n| last_completed_task | string? | ID of last successfully completed task |\n| in_progress_tasks[] | array | Tasks that were started but not finished |\n| remaining_tasks[] | array | Tasks not yet started |\n| next_suggested_task | string? | Task ID to execute next (null if blocked) |\n| next_recovery_action | string? | Escalation step to resume before normal task work |\n| repair_escalation | object | Persisted escalation state from `state.md` |\n| blockers[] | array | Issues preventing resumption |\n| blockers[].type | enum: dependency, role, resource | Type of blocker |\n| blockers[].description | string | What is blocking progress |\n| salvageable_tasks[] | array? | Tasks that can be moved to next iteration (if abort mode) |\n\n## Side Effects\n\n- Updates `state.md` with repaired execution metadata, resume timestamp, escalation summary, suggested next task, and resume report\n- No file writes if status is \"blocked\"\n\n## Error Handling\n\n- If `state.md` is not found under `iteration_directory`: infer state from `plan.md` (all tasks assumed \"planned\")\n- If `plan.md` is not found under `iteration_directory`: return error (cannot resume without plan)\n- If `state.md` references unknown tasks or blocked work: report blockers and preserve the existing file\n\n## Example Usage\n\n```powershell\npwsh -File .\\.specify\\extensions\\specrew-speckit\\scripts\\resume-iteration.ps1 `\n  -IterationDirectory .\\specs\\001-feature\\iterations\\000 `\n  -ResumeMode continue\n```\n\nExpected Output (READY):\n  status: \"ready\"\n  last_completed_task: \"T-003\"\n  in_progress_tasks: []\n  remaining_tasks: [\"T-004\", \"T-005\", \"T-006\"]\n  next_suggested_task: \"T-004\"\n  blockers: []\n  salvageable_tasks: null\n\nExpected Output (BLOCKED):\n  status: \"blocked\"\n  last_completed_task: \"T-003\"\n  in_progress_tasks: [\"T-004\"]\n  remaining_tasks: [\"T-005\", \"T-006\"]\n  next_suggested_task: null\n  blockers:\n    - type: \"dependency\"\n      description: \"T-004 is blocked waiting for external API access\"\n    - type: \"role\"\n      description: \"Reviewer role is unassigned; cannot proceed to review phase\"\n  salvageable_tasks: null\n\nExpected Output (ABORT):\n  status: \"needs-replan\"\n  last_completed_task: \"T-002\"\n  in_progress_tasks: []\n  remaining_tasks: [\"T-003\", \"T-004\", \"T-005\"]\n  next_suggested_task: null\n  blockers:\n    - type: \"resource\"\n      description: \"Critical blocker: upstream dependency no longer available\"\n  salvageable_tasks: [\"T-005\", \"T-006\"]\n\n```\n\n---\n\n**Implementation Status**: Implemented for FR-019 \u002F Iteration 2.\n",{"name":5,"domain":24,"source":25,"confidence":26,"description":7},"lifecycle-recovery","Specrew governance pillar — iteration resume \u002F recovery helper","high","main","176da577bfd98859f793bdd1312690c6c3940c67",".claude\u002Fskills\u002Fspecrew-iteration-resume","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI","https:\u002F\u002Fgithub.com\u002Falonf","http:\u002F\u002Falonfliess.me","CTO & Founder of Zionet.\r\nMicrosoft Regional Director and Foundry MVP.\r\n","2026-08-28 05:21:35",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add alonf\u002FKeyContextAI --skill specrew-iteration-resume",{"tool":41,"command":42},"bunx","bunx skills add alonf\u002FKeyContextAI --skill specrew-iteration-resume",{"tool":44,"command":45},"pnpm","pnpm dlx skills add alonf\u002FKeyContextAI --skill specrew-iteration-resume","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspecrew-iteration-resume\u002FSKILL.md",true,[49],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},".specrew-managed","OTHER","其他",81,"https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspecrew-iteration-resume\u002F.specrew-managed",[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7AVHRWWXA0BQ5PXNA8FG30W","windows-compatibility","Cross-platform path handling and command patterns","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fwindows-compatibility\u002FSKILL.md",[],[],{"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":19},"01M7AVHABPRYXYM3GWJY1RW92A","versioning-policy","Semver versioning rules for Squad SDK and CLI — prevents prerelease version incidents","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fversioning-policy\u002FSKILL.md",[],[],{"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":19},"01M7AVH4KNP3TCVQDRVS70VP19","tiered-memory","Three-tier agent memory model (hot\u002Fcold\u002Fwiki) for context reduction per spawn","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftiered-memory\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7AVH18JDSA55Z7KK2GH6X49","test-discipline","Update tests when changing APIs — no exceptions","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftest-discipline\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7AVGVGWYD7NBNXAV4PAZJ92","squad","Squad's command catalog and interactive menu. Invoke via \u002Fsquad (slash command) or natural language (\"squad commands\", \"what can squad do\", \"show me squad options\"). Presents categorized operations (Install & Upgrade, Team Management, Issues & PRs, Plugins & Skills, Model & Cost, Sessions & State) as an interactive picker. Routes to the right squad CLI command or the Squad coordinator agent.","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fsquad\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"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":19},"01M7AVGPSFT1WHW3PK35DHS5XK","squad-version-check","Internals of how @bradygaster\u002Fsquad-cli stamps its version, how `squad upgrade` works (what it preserves vs overwrites), and how to probe the npm registry for the latest version from a coordinator prompt.","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fsquad-version-check\u002FSKILL.md",[],[]]