[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77K0YCSBCMSS6VMDRJVS1Z4":3,"skill-same:01M77K0YCSBCMSS6VMDRJVS1Z4":57},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":14,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M77K0YCSBCMSS6VMDRJVS1Z4","mobiai-mobile-executing-plans-with-subagents",null,"ALWAYS invoke this when executing a mobile implementation plan in the current session with subagent support available. Drives fresh-subagent-per-task execution with mandatory two-stage review; do not hand-execute plan tasks in-session when this workflow applies.","AdriaanAt\u002FEcosystem-Manager","AdriaanAt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F170892248?v=4","01M77JXW5RB9W9WXQ7RS8ERQ6T","Adriaan","01M77JXW6V5MNR0P0F7D401Y7D",0,"MIT","https:\u002F\u002Fgithub.com\u002FAdriaanAt\u002FEcosystem-Manager\u002Fblob\u002Fmain\u002Fskills\u002Fcore\u002Fskills\u002Fmobiai-mobile-executing-plans-with-subagents\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mobiai-mobile-executing-plans-with-subagents\ndescription: \"ALWAYS invoke this when executing a mobile implementation plan in the current session with subagent support available. Drives fresh-subagent-per-task execution with mandatory two-stage review; do not hand-execute plan tasks in-session when this workflow applies.\"\nlicense: MIT\ncompatibility: [claude-code, cursor, copilot, codex, gemini]\nplatforms: [android, ios, kmp, flutter, react-native]\n---\n\n# Mobile Subagent-Driven Development\n\nExecute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.\n\n**Why subagents:** Fresh context per task prevents pollution. Precise instructions ensure focus. This preserves your own context for coordination.\n\n**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration\n\n## When to Use\n\n- Have implementation plan from `mobiai-mobile-planning`\n- Tasks mostly independent\n- Want to stay in this session\n\n**vs. mobiai-mobile-executing-plans:** Same session, fresh subagent per task, two-stage review, faster iteration.\n\n## The Process\n\n```\n[Read plan, extract all tasks with full text, create TodoWrite]\n\nFor each task:\n  → Dispatch implementer subagent\n  → Answer questions if any\n  → Implementer implements, tests, commits, self-reviews\n  → Dispatch spec reviewer subagent\n  → If gaps: implementer fixes, spec reviewer re-reviews\n  → Dispatch code quality reviewer subagent\n  → If issues: implementer fixes, quality reviewer re-reviews\n  → Mark task complete in TodoWrite\n\nAfter all tasks:\n  → Dispatch final code reviewer for entire implementation\n  → Use mobiai-mobile-finishing-branch\n```\n\n## Model Selection\n\n**Mechanical tasks** (isolated functions, clear specs, 1-2 files): fast, cheap model.\n\n**Integration tasks** (multi-file coordination, debugging): standard model.\n\n**Architecture and review tasks**: most capable model.\n\n## Handling Implementer Status\n\n**DONE:** Proceed to spec compliance review.\n\n**DONE_WITH_CONCERNS:** Read concerns. If about correctness, address before review. If observations, note and proceed.\n\n**NEEDS_CONTEXT:** Provide missing context and re-dispatch.\n\n**BLOCKED:** Assess: context problem → provide more. Task too large → break into pieces. Plan wrong → escalate to human.\n\n**Never** ignore an escalation or force retry without changes.\n\n## Prompt Templates\n\n**Implementer prompt:**\n```\nYour task: [exact task text from plan]\n\nContext:\n- Platform: [Android\u002FiOS\u002FFlutter\u002Fetc.]\n- Architecture: [patterns used in project]\n- Relevant files: [list]\n\nInstructions:\n1. Implement exactly what the task describes\n2. Write tests first (TDD: test → fail → implement → pass)\n3. Run tests and verify they pass\n4. Commit your changes\n5. Self-review: completeness, quality, testing\n6. Report: Status | What implemented | Test results | Files changed | Issues\n\nBuild command: [platform-specific]\nTest command: [platform-specific]\n```\n\n**Spec reviewer prompt:**\n```\nReview this implementation for spec compliance.\n\nTask spec: [original task text]\nFiles changed: [list from implementer]\n\nCheck:\n- Does implementation match spec exactly?\n- Anything missing from requirements?\n- Any extra work not in spec? (scope creep)\n- Tests covering specified behavior?\n\nReport: Spec compliant or Issues found (with specifics)\n```\n\n**Code quality reviewer prompt:**\n```\nReview this implementation for code quality.\n\nFiles changed: [list]\nPlatform: [Android\u002FiOS\u002FFlutter\u002Fetc.]\n\nCheck:\n- Mobile-specific: lifecycle handling, thread safety, memory management\n- Architecture: follows existing patterns\n- Tests: meaningful assertions, not just coverage\n- Naming: clear, consistent with project conventions\n\nReport: Strengths, Issues (Critical\u002FImportant\u002FMinor), Assessment\n```\n\n## Red Flags\n\n**Never:**\n- Start implementation on main\u002Fmaster branch without explicit user consent\n- Skip reviews (spec compliance OR code quality)\n- Proceed with unfixed issues\n- Dispatch multiple implementation subagents in parallel (conflicts)\n- Make subagent read plan file (provide full text instead)\n- Accept \"close enough\" on spec compliance\n- **Start code quality review before spec compliance passes**\n\n**If reviewer finds issues:**\n- Implementer fixes them\n- Reviewer reviews again\n- Repeat until approved\n\n## Integration\n\n**Required workflow skills:**\n- **`mobiai-mobile-worktrees`** - Set up isolated workspace before starting\n- **`mobiai-mobile-planning`** - Creates the plan this skill executes\n- **`mobiai-mobile-finishing-branch`** - Complete development after all tasks\n\n**Subagents should use:**\n- **`mobiai-mobile-tdd`** - Subagents follow TDD for each task\n","# Mobile Subagent-Driven Development\n\nExecute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.\n\n**Why subagents:** Fresh context per task prevents pollution. Precise instructions ensure focus. This preserves your own context for coordination.\n\n**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration\n\n## When to Use\n\n- Have implementation plan from `mobiai-mobile-planning`\n- Tasks mostly independent\n- Want to stay in this session\n\n**vs. mobiai-mobile-executing-plans:** Same session, fresh subagent per task, two-stage review, faster iteration.\n\n## The Process\n\n```\n[Read plan, extract all tasks with full text, create TodoWrite]\n\nFor each task:\n  → Dispatch implementer subagent\n  → Answer questions if any\n  → Implementer implements, tests, commits, self-reviews\n  → Dispatch spec reviewer subagent\n  → If gaps: implementer fixes, spec reviewer re-reviews\n  → Dispatch code quality reviewer subagent\n  → If issues: implementer fixes, quality reviewer re-reviews\n  → Mark task complete in TodoWrite\n\nAfter all tasks:\n  → Dispatch final code reviewer for entire implementation\n  → Use mobiai-mobile-finishing-branch\n```\n\n## Model Selection\n\n**Mechanical tasks** (isolated functions, clear specs, 1-2 files): fast, cheap model.\n\n**Integration tasks** (multi-file coordination, debugging): standard model.\n\n**Architecture and review tasks**: most capable model.\n\n## Handling Implementer Status\n\n**DONE:** Proceed to spec compliance review.\n\n**DONE_WITH_CONCERNS:** Read concerns. If about correctness, address before review. If observations, note and proceed.\n\n**NEEDS_CONTEXT:** Provide missing context and re-dispatch.\n\n**BLOCKED:** Assess: context problem → provide more. Task too large → break into pieces. Plan wrong → escalate to human.\n\n**Never** ignore an escalation or force retry without changes.\n\n## Prompt Templates\n\n**Implementer prompt:**\n```\nYour task: [exact task text from plan]\n\nContext:\n- Platform: [Android\u002FiOS\u002FFlutter\u002Fetc.]\n- Architecture: [patterns used in project]\n- Relevant files: [list]\n\nInstructions:\n1. Implement exactly what the task describes\n2. Write tests first (TDD: test → fail → implement → pass)\n3. Run tests and verify they pass\n4. Commit your changes\n5. Self-review: completeness, quality, testing\n6. Report: Status | What implemented | Test results | Files changed | Issues\n\nBuild command: [platform-specific]\nTest command: [platform-specific]\n```\n\n**Spec reviewer prompt:**\n```\nReview this implementation for spec compliance.\n\nTask spec: [original task text]\nFiles changed: [list from implementer]\n\nCheck:\n- Does implementation match spec exactly?\n- Anything missing from requirements?\n- Any extra work not in spec? (scope creep)\n- Tests covering specified behavior?\n\nReport: Spec compliant or Issues found (with specifics)\n```\n\n**Code quality reviewer prompt:**\n```\nReview this implementation for code quality.\n\nFiles changed: [list]\nPlatform: [Android\u002FiOS\u002FFlutter\u002Fetc.]\n\nCheck:\n- Mobile-specific: lifecycle handling, thread safety, memory management\n- Architecture: follows existing patterns\n- Tests: meaningful assertions, not just coverage\n- Naming: clear, consistent with project conventions\n\nReport: Strengths, Issues (Critical\u002FImportant\u002FMinor), Assessment\n```\n\n## Red Flags\n\n**Never:**\n- Start implementation on main\u002Fmaster branch without explicit user consent\n- Skip reviews (spec compliance OR code quality)\n- Proceed with unfixed issues\n- Dispatch multiple implementation subagents in parallel (conflicts)\n- Make subagent read plan file (provide full text instead)\n- Accept \"close enough\" on spec compliance\n- **Start code quality review before spec compliance passes**\n\n**If reviewer finds issues:**\n- Implementer fixes them\n- Reviewer reviews again\n- Repeat until approved\n\n## Integration\n\n**Required workflow skills:**\n- **`mobiai-mobile-worktrees`** - Set up isolated workspace before starting\n- **`mobiai-mobile-planning`** - Creates the plan this skill executes\n- **`mobiai-mobile-finishing-branch`** - Complete development after all tasks\n\n**Subagents should use:**\n- **`mobiai-mobile-tdd`** - Subagents follow TDD for each task\n",{"name":5,"license":15,"platforms":24,"description":7,"compatibility":30},[25,26,27,28,29],"android","ios","kmp","flutter","react-native",[31,32,33,34,35],"claude-code","cursor","copilot","codex","gemini","main","22db61fe1bb777d1dbf1c3bce1003b60399be288","skills\u002Fcore\u002Fskills\u002Fmobiai-mobile-executing-plans-with-subagents","https:\u002F\u002Fgithub.com\u002FAdriaanAt\u002FEcosystem-Manager","https:\u002F\u002Fgithub.com\u002FAdriaanAt","Fun Funny and Insane.","2026-07-10 13:36:44",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add AdriaanAt\u002FEcosystem-Manager --skill mobiai-mobile-executing-plans-with-subagents",{"tool":49,"command":50},"bunx","bunx skills add AdriaanAt\u002FEcosystem-Manager --skill mobiai-mobile-executing-plans-with-subagents",{"tool":52,"command":53},"pnpm","pnpm dlx skills add AdriaanAt\u002FEcosystem-Manager --skill mobiai-mobile-executing-plans-with-subagents","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAdriaanAt\u002FEcosystem-Manager\u002Fblob\u002Fmain\u002Fskills\u002Fcore\u002Fskills\u002Fmobiai-mobile-executing-plans-with-subagents\u002FSKILL.md",true,[],[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M77K38CDKWPD7Q6G1DQ0CXBX","mobiai-react-native","Use when working on a React Native project — building, testing, debugging, understanding navigation and state management.","https:\u002F\u002Fgithub.com\u002FAdriaanAt\u002FEcosystem-Manager\u002Fblob\u002Fmain\u002Fskills\u002Freact-native\u002Fskills\u002Fmobiai-react-native\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M77K35JEE16T3ED4GRTVBRFY","mobiai-kmp","Use when working on a Kotlin Multiplatform project — shared code, expect\u002Factual declarations, platform-specific implementations, building and testing.","https:\u002F\u002Fgithub.com\u002FAdriaanAt\u002FEcosystem-Manager\u002Fblob\u002Fmain\u002Fskills\u002Fkmp\u002Fskills\u002Fmobiai-kmp\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M77K31WB8FTX6MH5J9X7HDD8","mobiai-ios-testing","Use when writing or running tests in an iOS project — unit tests, UI tests, snapshot tests, choosing the right framework.","https:\u002F\u002Fgithub.com\u002FAdriaanAt\u002FEcosystem-Manager\u002Fblob\u002Fmain\u002Fskills\u002Fios\u002Fskills\u002Fmobiai-ios-testing\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M77K2XYFPQ48R3Z31F3W6RRK","mobiai-ios-device","Use when interacting with an iOS Simulator — run simctl commands, capture screenshots, read device logs, manage simulators.","https:\u002F\u002Fgithub.com\u002FAdriaanAt\u002FEcosystem-Manager\u002Fblob\u002Fmain\u002Fskills\u002Fios\u002Fskills\u002Fmobiai-ios-device\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M77K2VGTE59KQDMBVRAQ22CN","mobiai-ios-build","Use when building an iOS project, configuring schemes, troubleshooting build failures, or managing dependencies with CocoaPods or SPM.","https:\u002F\u002Fgithub.com\u002FAdriaanAt\u002FEcosystem-Manager\u002Fblob\u002Fmain\u002Fskills\u002Fios\u002Fskills\u002Fmobiai-ios-build\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M77K2RMDB69MRJZA5V9EBJGQ","mobiai-ios-architecture","Use when creating features, refactoring, or navigating an iOS codebase — understand project structure, find where to make changes, follow existing patterns.","https:\u002F\u002Fgithub.com\u002FAdriaanAt\u002FEcosystem-Manager\u002Fblob\u002Fmain\u002Fskills\u002Fios\u002Fskills\u002Fmobiai-ios-architecture\u002FSKILL.md",[],[]]