[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EN41BTK7XFDB4CMDRH8BB4":3,"skill-same:01M6EN41BTK7XFDB4CMDRH8BB4":117},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":6,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6EN41BTK7XFDB4CMDRH8BB4","managing-workflow",null,"Manages the specification-driven development workflow. Use this skill when the user runs \u002Forbit,\nrequests to \"define feature\", \"create plan\", \"implement\", or needs workflow guidance.\nIt detects the current phase from artifacts and executes the appropriate action.","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",67,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"workflow","managing workflow","use","implement","orbit","feature","define","task","specification","guidance","development workflow","development","edit","write","read","grep","plan","Bash","artifacts","create","2026-11-10 10:12:30",false,"---\nname: managing-workflow\ndescription: |\n  Manages the specification-driven development workflow. Use this skill when the user runs \u002Forbit,\n  requests to \"define feature\", \"create plan\", \"implement\", or needs workflow guidance.\n  It detects the current phase from artifacts and executes the appropriate action.\ntools:\n  - Read\n  - Write\n  - Edit\n  - Glob\n  - Grep\n  - Bash\n  - Task\n  - AskUserQuestion\n---\n\n# Orbit Workflow\n\nSingle skill for specification-driven development. **Artifacts are the source of truth.**\n\n## Initialization\n\n\u003Ccontext-loading>\nBefore any workflow action, load full context with a single Bash call:\n\n```bash\nnode plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Fcontext-loader.js\n```\n\nThis returns JSON with:\n- `suggestion`: Recommended next action\n- `current`: Active feature state and artifacts\n- `features.active`: All features with frontmatter state\n- `features.in_progress`: Features needing attention\n- `architecture_files`: Available architecture docs\n\nUse this context for all decisions. Avoid additional Read calls for state detection.\n\u003C\u002Fcontext-loading>\n\n## Phase Detection\n\nPhase is stored in spec.md frontmatter `status` field:\n\n| Status | Artifacts | Next Action |\n|--------|-----------|-------------|\n| `initialize` | None | Create spec.md |\n| `specification` | spec.md (no [CLARIFY]) | Create plan.md |\n| `clarification` | spec.md with [CLARIFY] | Resolve questions |\n| `planning` | spec.md + plan.md | Create tasks.md |\n| `implementation` | tasks.md has `- [ ]` | Execute tasks |\n| `complete` | All tasks `- [x]` | Archive or new feature |\n\n## Frontmatter Schema\n\n### spec.md Frontmatter\n\n```yaml\n---\nid: 001-feature-name\ntitle: Human Readable Title\nstatus: specification  # initialize|specification|clarification|planning|implementation|complete\npriority: P1           # P1|P2|P3\ncreated: 2025-11-27\nupdated: 2025-11-27\nprogress:\n  tasks_total: 0\n  tasks_done: 0\nowner: team-name\ntags:\n  - api\n  - auth\n---\n```\n\n### Updating Frontmatter\n\nOn every phase transition, use the skill's built-in scripts:\n\n```bash\n# Update status and timestamp\nnode plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Fupdate-status.js \\\n  \".spec\u002Ffeatures\u002F{feature}\u002Fspec.md\" \"planning\"\n\n# Log activity with ISO timestamp\nnode plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Flog-activity.js \\\n  \".spec\u002Ffeatures\u002F{feature}\u002Fmetrics.md\" \"Plan created\"\n```\n\nOr with Edit tool - update the status line in frontmatter.\n\n## Phase Gates (MANDATORY)\n\n**You MUST validate before ANY phase transition. This is NOT optional.**\n\n```bash\n# REQUIRED before every phase change\nRESULT=$(node plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Fvalidate-phase.js \\\n  \".spec\u002Ffeatures\u002F{feature}\" \"{target-phase}\")\n\n# Check result - DO NOT PROCEED if invalid\nif [[ $(echo \"$RESULT\" | jq -r '.valid') != \"true\" ]]; then\n  echo \"BLOCKED: $(echo \"$RESULT\" | jq -r '.suggestion')\"\n  # Create the missing artifact before continuing\nfi\n```\n\n### Phase Prerequisites\n\n| Target Phase | Required Artifacts | If Missing |\n|--------------|-------------------|------------|\n| specification | None | - |\n| clarification | spec.md | Create spec first |\n| planning | spec.md (no [CLARIFY]) | Resolve clarifications |\n| implementation | spec.md, plan.md, tasks.md | Create missing artifacts |\n| complete | All tasks `[x]` | Complete remaining tasks |\n\n### Enforcement Rules\n\n1. **NEVER skip directly to implementation** - plan.md and tasks.md MUST exist\n2. **NEVER mark complete with unchecked tasks** - all `[ ]` must be `[x]`\n3. **If validation fails**: Create the missing artifact, don't proceed\n4. **For simple features**: Use quick-plan template (see plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Ftemplates\u002Fquick-plan.md)\n\n### Quick Planning Option\n\nFor simple features (bug fixes, \u003C 3 files), use streamlined templates:\n- `plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Ftemplates\u002Fquick-plan.md` - Combined plan with inline tasks\n- `plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Ftemplates\u002Fquick-tasks.md` - Minimal task list\n\nThis ensures artifacts exist while reducing overhead for small changes.\n\n## Workflow Actions\n\n### Initialize New Feature\n\n1. Ask user for feature name and description\n2. Generate feature ID: `{NNN}-{kebab-name}`\n3. Create directory and files in parallel:\n\n```bash\nmkdir -p .spec\u002Ffeatures\u002F{id}\n```\n\nCreate these files simultaneously:\n- `spec.md` with frontmatter\n- `metrics.md` with tracking template\n\n4. Set session: `set_feature \"{id}\"`\n\n### spec.md Template\n\n```markdown\n---\nid: {id}\ntitle: {title}\nstatus: specification\npriority: P2\ncreated: {date}\nupdated: {date}\nprogress:\n  tasks_total: 0\n  tasks_done: 0\n---\n\n# Feature: {title}\n\n## Overview\n\n{description}\n\n## User Stories\n\n### US1: {story title}\n\nAs a {role}, I want {goal} so that {benefit}.\n\n**Acceptance Criteria:**\n- [ ] AC1.1: {criterion}\n- [ ] AC1.2: {criterion}\n\n## Technical Constraints\n\n- {constraint}\n\n## Out of Scope\n\n- {exclusion}\n```\n\n### metrics.md Template\n\n```markdown\n# Metrics: {title}\n\n## Progress\n\n| Phase | Status | Updated |\n|-------|--------|---------|\n| Specification | pending | |\n| Clarification | pending | |\n| Planning | pending | |\n| Implementation | 0\u002F0 | |\n\n## Activity\n\n| Timestamp | Event |\n|-----------|-------|\n```\n\nNote: All timestamps use ISO 8601 format: `2025-11-27T10:30:00Z`\n\n### Define Specification\n\n1. Load context to check for related archived features\n2. If related found, ask: \"Found similar feature '{name}'. Reference it?\"\n3. Ask user for feature requirements (use AskUserQuestion for scope\u002Fpriority)\n4. Generate user stories with acceptance criteria\n5. Mark unclear items with `[CLARIFY]`\n6. **Ask user to review `spec.md`**\n7. If approved:\n   - Update frontmatter: `status: specification` (or `clarification` if tags exist)\n   - Update metrics.md\n\n### Clarify\n\n1. Find all `[CLARIFY]` tags in spec.md\n2. Batch into groups of max 4 questions\n3. Use AskUserQuestion to resolve each batch\n4. Update spec.md with answers, remove `[CLARIFY]` tags\n5. **Ask user to review changes**\n6. When all resolved and approved, update frontmatter: `status: specification`\n\n### Create Plan\n\n1. Validate spec completeness (no [CLARIFY] tags)\n2. Read spec.md\n3. Generate technical plan with:\n   - Architecture decisions\n   - Components and their purposes\n   - Data models\n   - API design (if applicable)\n   - Integration points\n4. Write plan.md\n5. **Ask user to review `plan.md`**\n6. If approved:\n   - Update frontmatter: `status: planning`\n   - Update metrics.md\n\n### plan.md Template\n\n```markdown\n# Technical Plan: {title}\n\n## Architecture\n\n{architecture decisions and rationale}\n\n## Components\n\n| Component | Purpose | Dependencies |\n|-----------|---------|--------------|\n| {name} | {purpose} | {deps} |\n\n## Data Models\n\n{model definitions}\n\n## API Design\n\n{endpoints if applicable}\n\n## Implementation Phases\n\n1. **Phase 1**: {description}\n2. **Phase 2**: {description}\n\n## Risks\n\n| Risk | Impact | Mitigation |\n|------|--------|------------|\n| {risk} | {impact} | {mitigation} |\n```\n\n### Create Tasks\n\n1. Read spec.md + plan.md\n2. Break into tasks with parallel groups and dependencies:\n\n```markdown\n## Parallel Group A\n- [ ] T001: {task} [P1]\n- [ ] T002: {task} [P1]\n\n## Parallel Group B [depends:A]\n- [ ] T003: {task} [P1] [depends:T001,T002]\n```\n\n3. Tag critical changes: `[critical:schema]`, `[critical:api]`, `[critical:types]`\n4. Write tasks.md\n5. **Ask user to review `tasks.md`**\n6. If approved:\n   - Update frontmatter: `status: implementation`\n   - Update progress in frontmatter: `tasks_total: {count}`\n   - Update metrics.md\n\n### tasks.md Template\n\n```markdown\n# Tasks: {title}\n\n## Parallel Group A\n\n- [ ] T001: {description} [P1]\n- [ ] T002: {description} [P1]\n\n## Parallel Group B [depends:A]\n\n- [ ] T003: {description} [P1] [depends:T001,T002]\n- [ ] T004: {description} [P2] [depends:T001]\n\n## Sequential\n\n- [ ] T005: {description} [P1] [critical:api] [depends:T003,T004]\n\n---\n\n## Legend\n\n- `[P1\u002FP2\u002FP3]` - Priority level\n- `[depends:X,Y]` - Task dependencies\n- `[critical:type]` - Requires extra review (schema, api, types, auth)\n- `[estimate:S\u002FM\u002FL]` - Size estimate\n```\n\n### Implement\n\n**GATE CHECK REQUIRED** - Before implementing, MUST validate:\n\n```bash\n# MANDATORY: Run this before any implementation\nRESULT=$(node plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Fvalidate-phase.js \\\n  \".spec\u002Ffeatures\u002F{feature}\" \"implementation\")\n\n# If not valid, STOP and create missing artifacts\nif [[ $(echo \"$RESULT\" | jq -r '.valid') != \"true\" ]]; then\n  MISSING=$(echo \"$RESULT\" | jq -r '.missing')\n  echo \"Cannot implement: missing $MISSING\"\n  # Go back and create: plan.md or tasks.md\nfi\n```\n\n**Only after validation passes**, delegate to `task-implementer` agent:\n\n```\nTask: task-implementer agent\n\nFeature: {feature-path}\nTasks file: .spec\u002Ffeatures\u002F{feature}\u002Ftasks.md\n\nExecute tasks in parallel groups where possible.\nUpdate task checkboxes as completed.\nReport any blockers.\n```\n\nAfter implementation:\n- Update frontmatter progress: `tasks_done: {count}`\n- If all complete, update: `status: complete`\n\n### Validate\n\nDelegate to `artifact-validator` agent:\n\n```\nTask: artifact-validator agent\n\nFeature: {feature-path}\n\nValidate:\n1. Spec completeness (all AC have tasks)\n2. Plan coverage (all US have implementation)\n3. Task consistency (dependencies valid)\n```\n\n### Archive Feature\n\nWhen feature is complete:\n\n1. Ask user: \"Archive this feature?\"\n2. If yes:\n   a. Check for repeatable patterns in completed work\n   b. If patterns detected (2+ similar files\u002Ftasks), offer tooling suggestions\n3. Run archive_feature\n\n```bash\nnode plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Farchive-feature.js \"{feature-id}\"\n```\n\n3. If new skills\u002Fagents were created during the feature:\n   - Inform user: \"New tooling was created. Restart Claude to use it.\"\n   - Suggest: `claude --continue` to resume after restart\n4. Suggest next action from context loader\n\n### Tooling Check on Archive\n\nBefore archiving, analyze the completed feature for automation opportunities:\n\n```\nPattern Detection (only for repeatable tasks):\n- Created 3+ similar files? → Suggest generator skill\n- Wrote 3+ test files? → Suggest testing-code skill\n- Added 3+ API endpoints? → Suggest api-testing agent\n- Similar task structure repeated? → Suggest workflow skill\n```\n\n**Skip tooling suggestions if:**\n- Feature was one-off (migration, unique integration)\n- Pattern count \u003C 2\n- Similar tooling already exists\n\nIf tooling is created:\n```markdown\n## New Tooling Created\n\n| Type | Name | Location |\n|------|------|----------|\n| Skill | {name} | .claude\u002Fskills\u002F{name}\u002F |\n| Agent | {name} | .claude\u002Fagents\u002F{name}.md |\n\n**Restart Required**: Run `claude --continue` to use new tooling.\n```\n\n## User Questions\n\nUse AskUserQuestion strategically:\n\n### On Initialize\n```yaml\nquestions:\n  - header: \"Project Type\"\n    question: \"What type of project is this?\"\n    options:\n      - label: \"Greenfield\"\n        description: \"New project from scratch\"\n      - label: \"Brownfield\"\n        description: \"Existing codebase\"\n```\n\n### On Feature Selection (multiple features)\n```yaml\nquestions:\n  - header: \"Feature\"\n    question: \"Which feature to work on?\"\n    options:\n      - label: \"{feature-1}\"\n        description: \"{status} - {progress}\"\n      - label: \"{feature-2}\"\n        description: \"{status}\"\n      - label: \"New Feature\"\n        description: \"Start fresh\"\n```\n\n### On Implementation Start\n```yaml\nquestions:\n  - header: \"Execution\"\n    question: \"How to execute tasks?\"\n    options:\n      - label: \"Guided\"\n        description: \"Confirm each task\"\n      - label: \"Autonomous\"\n        description: \"Execute all, report at end\"\n```\n\n## Error Handling\n\n- Missing artifact → Start from that phase\n- Validation fails → Show gaps, offer to fix\n- Task blocked → Log blocker, skip to next, report at end\n- Frontmatter missing → Add it on next update\n\n## Parallel Execution Guidelines\n\nExecute in parallel when independent:\n- File creation (spec.md + metrics.md)\n- Multiple validations\n- Independent task groups\n\nExecute sequentially when dependent:\n- Spec → Plan → Tasks\n- Dependent task groups\n","# Orbit Workflow\n\nSingle skill for specification-driven development. **Artifacts are the source of truth.**\n\n## Initialization\n\n\u003Ccontext-loading>\nBefore any workflow action, load full context with a single Bash call:\n\n```bash\nnode plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Fcontext-loader.js\n```\n\nThis returns JSON with:\n- `suggestion`: Recommended next action\n- `current`: Active feature state and artifacts\n- `features.active`: All features with frontmatter state\n- `features.in_progress`: Features needing attention\n- `architecture_files`: Available architecture docs\n\nUse this context for all decisions. Avoid additional Read calls for state detection.\n\u003C\u002Fcontext-loading>\n\n## Phase Detection\n\nPhase is stored in spec.md frontmatter `status` field:\n\n| Status | Artifacts | Next Action |\n|--------|-----------|-------------|\n| `initialize` | None | Create spec.md |\n| `specification` | spec.md (no [CLARIFY]) | Create plan.md |\n| `clarification` | spec.md with [CLARIFY] | Resolve questions |\n| `planning` | spec.md + plan.md | Create tasks.md |\n| `implementation` | tasks.md has `- [ ]` | Execute tasks |\n| `complete` | All tasks `- [x]` | Archive or new feature |\n\n## Frontmatter Schema\n\n### spec.md Frontmatter\n\n```yaml\n---\nid: 001-feature-name\ntitle: Human Readable Title\nstatus: specification  # initialize|specification|clarification|planning|implementation|complete\npriority: P1           # P1|P2|P3\ncreated: 2025-11-27\nupdated: 2025-11-27\nprogress:\n  tasks_total: 0\n  tasks_done: 0\nowner: team-name\ntags:\n  - api\n  - auth\n---\n```\n\n### Updating Frontmatter\n\nOn every phase transition, use the skill's built-in scripts:\n\n```bash\n# Update status and timestamp\nnode plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Fupdate-status.js \\\n  \".spec\u002Ffeatures\u002F{feature}\u002Fspec.md\" \"planning\"\n\n# Log activity with ISO timestamp\nnode plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Flog-activity.js \\\n  \".spec\u002Ffeatures\u002F{feature}\u002Fmetrics.md\" \"Plan created\"\n```\n\nOr with Edit tool - update the status line in frontmatter.\n\n## Phase Gates (MANDATORY)\n\n**You MUST validate before ANY phase transition. This is NOT optional.**\n\n```bash\n# REQUIRED before every phase change\nRESULT=$(node plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Fvalidate-phase.js \\\n  \".spec\u002Ffeatures\u002F{feature}\" \"{target-phase}\")\n\n# Check result - DO NOT PROCEED if invalid\nif [[ $(echo \"$RESULT\" | jq -r '.valid') != \"true\" ]]; then\n  echo \"BLOCKED: $(echo \"$RESULT\" | jq -r '.suggestion')\"\n  # Create the missing artifact before continuing\nfi\n```\n\n### Phase Prerequisites\n\n| Target Phase | Required Artifacts | If Missing |\n|--------------|-------------------|------------|\n| specification | None | - |\n| clarification | spec.md | Create spec first |\n| planning | spec.md (no [CLARIFY]) | Resolve clarifications |\n| implementation | spec.md, plan.md, tasks.md | Create missing artifacts |\n| complete | All tasks `[x]` | Complete remaining tasks |\n\n### Enforcement Rules\n\n1. **NEVER skip directly to implementation** - plan.md and tasks.md MUST exist\n2. **NEVER mark complete with unchecked tasks** - all `[ ]` must be `[x]`\n3. **If validation fails**: Create the missing artifact, don't proceed\n4. **For simple features**: Use quick-plan template (see plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Ftemplates\u002Fquick-plan.md)\n\n### Quick Planning Option\n\nFor simple features (bug fixes, \u003C 3 files), use streamlined templates:\n- `plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Ftemplates\u002Fquick-plan.md` - Combined plan with inline tasks\n- `plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Ftemplates\u002Fquick-tasks.md` - Minimal task list\n\nThis ensures artifacts exist while reducing overhead for small changes.\n\n## Workflow Actions\n\n### Initialize New Feature\n\n1. Ask user for feature name and description\n2. Generate feature ID: `{NNN}-{kebab-name}`\n3. Create directory and files in parallel:\n\n```bash\nmkdir -p .spec\u002Ffeatures\u002F{id}\n```\n\nCreate these files simultaneously:\n- `spec.md` with frontmatter\n- `metrics.md` with tracking template\n\n4. Set session: `set_feature \"{id}\"`\n\n### spec.md Template\n\n```markdown\n---\nid: {id}\ntitle: {title}\nstatus: specification\npriority: P2\ncreated: {date}\nupdated: {date}\nprogress:\n  tasks_total: 0\n  tasks_done: 0\n---\n\n# Feature: {title}\n\n## Overview\n\n{description}\n\n## User Stories\n\n### US1: {story title}\n\nAs a {role}, I want {goal} so that {benefit}.\n\n**Acceptance Criteria:**\n- [ ] AC1.1: {criterion}\n- [ ] AC1.2: {criterion}\n\n## Technical Constraints\n\n- {constraint}\n\n## Out of Scope\n\n- {exclusion}\n```\n\n### metrics.md Template\n\n```markdown\n# Metrics: {title}\n\n## Progress\n\n| Phase | Status | Updated |\n|-------|--------|---------|\n| Specification | pending | |\n| Clarification | pending | |\n| Planning | pending | |\n| Implementation | 0\u002F0 | |\n\n## Activity\n\n| Timestamp | Event |\n|-----------|-------|\n```\n\nNote: All timestamps use ISO 8601 format: `2025-11-27T10:30:00Z`\n\n### Define Specification\n\n1. Load context to check for related archived features\n2. If related found, ask: \"Found similar feature '{name}'. Reference it?\"\n3. Ask user for feature requirements (use AskUserQuestion for scope\u002Fpriority)\n4. Generate user stories with acceptance criteria\n5. Mark unclear items with `[CLARIFY]`\n6. **Ask user to review `spec.md`**\n7. If approved:\n   - Update frontmatter: `status: specification` (or `clarification` if tags exist)\n   - Update metrics.md\n\n### Clarify\n\n1. Find all `[CLARIFY]` tags in spec.md\n2. Batch into groups of max 4 questions\n3. Use AskUserQuestion to resolve each batch\n4. Update spec.md with answers, remove `[CLARIFY]` tags\n5. **Ask user to review changes**\n6. When all resolved and approved, update frontmatter: `status: specification`\n\n### Create Plan\n\n1. Validate spec completeness (no [CLARIFY] tags)\n2. Read spec.md\n3. Generate technical plan with:\n   - Architecture decisions\n   - Components and their purposes\n   - Data models\n   - API design (if applicable)\n   - Integration points\n4. Write plan.md\n5. **Ask user to review `plan.md`**\n6. If approved:\n   - Update frontmatter: `status: planning`\n   - Update metrics.md\n\n### plan.md Template\n\n```markdown\n# Technical Plan: {title}\n\n## Architecture\n\n{architecture decisions and rationale}\n\n## Components\n\n| Component | Purpose | Dependencies |\n|-----------|---------|--------------|\n| {name} | {purpose} | {deps} |\n\n## Data Models\n\n{model definitions}\n\n## API Design\n\n{endpoints if applicable}\n\n## Implementation Phases\n\n1. **Phase 1**: {description}\n2. **Phase 2**: {description}\n\n## Risks\n\n| Risk | Impact | Mitigation |\n|------|--------|------------|\n| {risk} | {impact} | {mitigation} |\n```\n\n### Create Tasks\n\n1. Read spec.md + plan.md\n2. Break into tasks with parallel groups and dependencies:\n\n```markdown\n## Parallel Group A\n- [ ] T001: {task} [P1]\n- [ ] T002: {task} [P1]\n\n## Parallel Group B [depends:A]\n- [ ] T003: {task} [P1] [depends:T001,T002]\n```\n\n3. Tag critical changes: `[critical:schema]`, `[critical:api]`, `[critical:types]`\n4. Write tasks.md\n5. **Ask user to review `tasks.md`**\n6. If approved:\n   - Update frontmatter: `status: implementation`\n   - Update progress in frontmatter: `tasks_total: {count}`\n   - Update metrics.md\n\n### tasks.md Template\n\n```markdown\n# Tasks: {title}\n\n## Parallel Group A\n\n- [ ] T001: {description} [P1]\n- [ ] T002: {description} [P1]\n\n## Parallel Group B [depends:A]\n\n- [ ] T003: {description} [P1] [depends:T001,T002]\n- [ ] T004: {description} [P2] [depends:T001]\n\n## Sequential\n\n- [ ] T005: {description} [P1] [critical:api] [depends:T003,T004]\n\n---\n\n## Legend\n\n- `[P1\u002FP2\u002FP3]` - Priority level\n- `[depends:X,Y]` - Task dependencies\n- `[critical:type]` - Requires extra review (schema, api, types, auth)\n- `[estimate:S\u002FM\u002FL]` - Size estimate\n```\n\n### Implement\n\n**GATE CHECK REQUIRED** - Before implementing, MUST validate:\n\n```bash\n# MANDATORY: Run this before any implementation\nRESULT=$(node plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Fvalidate-phase.js \\\n  \".spec\u002Ffeatures\u002F{feature}\" \"implementation\")\n\n# If not valid, STOP and create missing artifacts\nif [[ $(echo \"$RESULT\" | jq -r '.valid') != \"true\" ]]; then\n  MISSING=$(echo \"$RESULT\" | jq -r '.missing')\n  echo \"Cannot implement: missing $MISSING\"\n  # Go back and create: plan.md or tasks.md\nfi\n```\n\n**Only after validation passes**, delegate to `task-implementer` agent:\n\n```\nTask: task-implementer agent\n\nFeature: {feature-path}\nTasks file: .spec\u002Ffeatures\u002F{feature}\u002Ftasks.md\n\nExecute tasks in parallel groups where possible.\nUpdate task checkboxes as completed.\nReport any blockers.\n```\n\nAfter implementation:\n- Update frontmatter progress: `tasks_done: {count}`\n- If all complete, update: `status: complete`\n\n### Validate\n\nDelegate to `artifact-validator` agent:\n\n```\nTask: artifact-validator agent\n\nFeature: {feature-path}\n\nValidate:\n1. Spec completeness (all AC have tasks)\n2. Plan coverage (all US have implementation)\n3. Task consistency (dependencies valid)\n```\n\n### Archive Feature\n\nWhen feature is complete:\n\n1. Ask user: \"Archive this feature?\"\n2. If yes:\n   a. Check for repeatable patterns in completed work\n   b. If patterns detected (2+ similar files\u002Ftasks), offer tooling suggestions\n3. Run archive_feature\n\n```bash\nnode plugins\u002Fspec\u002Fskills\u002Fmanaging-workflow\u002Fscripts\u002Farchive-feature.js \"{feature-id}\"\n```\n\n3. If new skills\u002Fagents were created during the feature:\n   - Inform user: \"New tooling was created. Restart Claude to use it.\"\n   - Suggest: `claude --continue` to resume after restart\n4. Suggest next action from context loader\n\n### Tooling Check on Archive\n\nBefore archiving, analyze the completed feature for automation opportunities:\n\n```\nPattern Detection (only for repeatable tasks):\n- Created 3+ similar files? → Suggest generator skill\n- Wrote 3+ test files? → Suggest testing-code skill\n- Added 3+ API endpoints? → Suggest api-testing agent\n- Similar task structure repeated? → Suggest workflow skill\n```\n\n**Skip tooling suggestions if:**\n- Feature was one-off (migration, unique integration)\n- Pattern count \u003C 2\n- Similar tooling already exists\n\nIf tooling is created:\n```markdown\n## New Tooling Created\n\n| Type | Name | Location |\n|------|------|----------|\n| Skill | {name} | .claude\u002Fskills\u002F{name}\u002F |\n| Agent | {name} | .claude\u002Fagents\u002F{name}.md |\n\n**Restart Required**: Run `claude --continue` to use new tooling.\n```\n\n## User Questions\n\nUse AskUserQuestion strategically:\n\n### On Initialize\n```yaml\nquestions:\n  - header: \"Project Type\"\n    question: \"What type of project is this?\"\n    options:\n      - label: \"Greenfield\"\n        description: \"New project from scratch\"\n      - label: \"Brownfield\"\n        description: \"Existing codebase\"\n```\n\n### On Feature Selection (multiple features)\n```yaml\nquestions:\n  - header: \"Feature\"\n    question: \"Which feature to work on?\"\n    options:\n      - label: \"{feature-1}\"\n        description: \"{status} - {progress}\"\n      - label: \"{feature-2}\"\n        description: \"{status}\"\n      - label: \"New Feature\"\n        description: \"Start fresh\"\n```\n\n### On Implementation Start\n```yaml\nquestions:\n  - header: \"Execution\"\n    question: \"How to execute tasks?\"\n    options:\n      - label: \"Guided\"\n        description: \"Confirm each task\"\n      - label: \"Autonomous\"\n        description: \"Execute all, report at end\"\n```\n\n## Error Handling\n\n- Missing artifact → Start from that phase\n- Validation fails → Show gaps, offer to fix\n- Task blocked → Log blocker, skip to next, report at end\n- Frontmatter missing → Add it on next update\n\n## Parallel Execution Guidelines\n\nExecute in parallel when independent:\n- File creation (spec.md + metrics.md)\n- Multiple validations\n- Independent task groups\n\nExecute sequentially when dependent:\n- Spec → Plan → Tasks\n- Dependent task groups\n",{"name":5,"tools":49,"description":57},[50,51,52,53,54,41,55,56],"Read","Write","Edit","Glob","Grep","Task","AskUserQuestion","Manages the specification-driven development workflow. Use this skill when the user runs \u002Forbit,\nrequests to \"define feature\", \"create plan\", \"implement\", or needs workflow guidance.\nIt detects the current phase from artifacts and executes the appropriate action.\n","main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill managing-workflow",{"tool":73,"command":74},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill managing-workflow",{"tool":76,"command":77},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill managing-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow\u002FSKILL.md",true,[81,87,91,95,99,103,109,113],{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Farchive-feature.js","SCRIPT","脚本",2673,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow\u002Fscripts\u002Farchive-feature.js",{"path":88,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Fcontext-loader.js",1430,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow\u002Fscripts\u002Fcontext-loader.js",{"path":92,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Flog-activity.js",2770,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow\u002Fscripts\u002Flog-activity.js",{"path":96,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":97,"sourceHtmlUrl":98},"scripts\u002Fupdate-status.js",772,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow\u002Fscripts\u002Fupdate-status.js",{"path":100,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Fvalidate-phase.js",2327,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow\u002Fscripts\u002Fvalidate-phase.js",{"path":104,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":107,"sourceHtmlUrl":108},"skill-report.json","REFERENCE","参考文档",10863,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow\u002Fskill-report.json",{"path":110,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":111,"sourceHtmlUrl":112},"templates\u002Fquick-plan.md",1357,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow\u002Ftemplates\u002Fquick-plan.md",{"path":114,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":115,"sourceHtmlUrl":116},"templates\u002Fquick-tasks.md",684,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fbrendanshields\u002Fmanaging-workflow\u002Ftemplates\u002Fquick-tasks.md",[118,128,138,147,153,160],{"skillNo":119,"name":120,"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":121,"categories":122,"keywords":124,"publishedAt":44},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[123],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[125,126,127],"model","model hierarchy","model hierarchy skill",{"skillNo":129,"name":130,"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":131,"categories":132,"keywords":134,"publishedAt":44},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[133],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[135,136,137],"MCP","zoom","zoom mcp",{"skillNo":139,"name":140,"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":141,"categories":142,"keywords":143,"publishedAt":44},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[144,145,146,136],"sdk","zoom apps sdk","apps",{"skillNo":148,"name":149,"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":150,"categories":151,"keywords":152,"publishedAt":44},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[149],{"skillNo":154,"name":155,"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":156,"categories":157,"keywords":159,"publishedAt":44},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[158],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[155],{"skillNo":161,"name":162,"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":163,"categories":164,"keywords":165,"publishedAt":44},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[162]]