[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-subagent-driven-development":3,"mdc-jd6ov3-key":33,"related-repo-openai-subagent-driven-development":1281,"related-org-openai-subagent-driven-development":1403},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"subagent-driven-development","execute implementation plans with subagents","Use when executing implementation plans with independent tasks in the current session",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19],{"name":13,"slug":14,"type":15},"Agents","agents","tag",{"name":17,"slug":18,"type":15},"Engineering","engineering",{"name":20,"slug":21,"type":15},"Multi-Agent","multi-agent",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-04-16T05:11:54.993402",null,465,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fsuperpowers\u002Fskills\u002Fsubagent-driven-development","---\nname: subagent-driven-development\ndescription: Use when executing implementation plans with independent tasks in the current session\n---\n\n# 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:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.\n\n**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration\n\n**Continuous execution:** Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. \"Should I continue?\" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.\n\n## When to Use\n\n```dot\ndigraph when_to_use {\n    \"Have implementation plan?\" [shape=diamond];\n    \"Tasks mostly independent?\" [shape=diamond];\n    \"Stay in this session?\" [shape=diamond];\n    \"subagent-driven-development\" [shape=box];\n    \"executing-plans\" [shape=box];\n    \"Manual execution or brainstorm first\" [shape=box];\n\n    \"Have implementation plan?\" -> \"Tasks mostly independent?\" [label=\"yes\"];\n    \"Have implementation plan?\" -> \"Manual execution or brainstorm first\" [label=\"no\"];\n    \"Tasks mostly independent?\" -> \"Stay in this session?\" [label=\"yes\"];\n    \"Tasks mostly independent?\" -> \"Manual execution or brainstorm first\" [label=\"no - tightly coupled\"];\n    \"Stay in this session?\" -> \"subagent-driven-development\" [label=\"yes\"];\n    \"Stay in this session?\" -> \"executing-plans\" [label=\"no - parallel session\"];\n}\n```\n\n**vs. Executing Plans (parallel session):**\n- Same session (no context switch)\n- Fresh subagent per task (no context pollution)\n- Two-stage review after each task: spec compliance first, then code quality\n- Faster iteration (no human-in-loop between tasks)\n\n## The Process\n\n```dot\ndigraph process {\n    rankdir=TB;\n\n    subgraph cluster_per_task {\n        label=\"Per Task\";\n        \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\" [shape=box];\n        \"Implementer subagent asks questions?\" [shape=diamond];\n        \"Answer questions, provide context\" [shape=box];\n        \"Implementer subagent implements, tests, commits, self-reviews\" [shape=box];\n        \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\" [shape=box];\n        \"Spec reviewer subagent confirms code matches spec?\" [shape=diamond];\n        \"Implementer subagent fixes spec gaps\" [shape=box];\n        \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" [shape=box];\n        \"Code quality reviewer subagent approves?\" [shape=diamond];\n        \"Implementer subagent fixes quality issues\" [shape=box];\n        \"Mark task complete in TodoWrite\" [shape=box];\n    }\n\n    \"Read plan, extract all tasks with full text, note context, create TodoWrite\" [shape=box];\n    \"More tasks remain?\" [shape=diamond];\n    \"Dispatch final code reviewer subagent for entire implementation\" [shape=box];\n    \"Use superpowers:finishing-a-development-branch\" [shape=box style=filled fillcolor=lightgreen];\n\n    \"Read plan, extract all tasks with full text, note context, create TodoWrite\" -> \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\";\n    \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\" -> \"Implementer subagent asks questions?\";\n    \"Implementer subagent asks questions?\" -> \"Answer questions, provide context\" [label=\"yes\"];\n    \"Answer questions, provide context\" -> \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\";\n    \"Implementer subagent asks questions?\" -> \"Implementer subagent implements, tests, commits, self-reviews\" [label=\"no\"];\n    \"Implementer subagent implements, tests, commits, self-reviews\" -> \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\";\n    \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\" -> \"Spec reviewer subagent confirms code matches spec?\";\n    \"Spec reviewer subagent confirms code matches spec?\" -> \"Implementer subagent fixes spec gaps\" [label=\"no\"];\n    \"Implementer subagent fixes spec gaps\" -> \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\" [label=\"re-review\"];\n    \"Spec reviewer subagent confirms code matches spec?\" -> \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" [label=\"yes\"];\n    \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" -> \"Code quality reviewer subagent approves?\";\n    \"Code quality reviewer subagent approves?\" -> \"Implementer subagent fixes quality issues\" [label=\"no\"];\n    \"Implementer subagent fixes quality issues\" -> \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" [label=\"re-review\"];\n    \"Code quality reviewer subagent approves?\" -> \"Mark task complete in TodoWrite\" [label=\"yes\"];\n    \"Mark task complete in TodoWrite\" -> \"More tasks remain?\";\n    \"More tasks remain?\" -> \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\" [label=\"yes\"];\n    \"More tasks remain?\" -> \"Dispatch final code reviewer subagent for entire implementation\" [label=\"no\"];\n    \"Dispatch final code reviewer subagent for entire implementation\" -> \"Use superpowers:finishing-a-development-branch\";\n}\n```\n\n## Model Selection\n\nUse the least powerful model that can handle each role to conserve cost and increase speed.\n\n**Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.\n\n**Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.\n\n**Architecture, design, and review tasks**: use the most capable available model.\n\n**Task complexity signals:**\n- Touches 1-2 files with a complete spec → cheap model\n- Touches multiple files with integration concerns → standard model\n- Requires design judgment or broad codebase understanding → most capable model\n\n## Handling Implementer Status\n\nImplementer subagents report one of four statuses. Handle each appropriately:\n\n**DONE:** Proceed to spec compliance review.\n\n**DONE_WITH_CONCERNS:** The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., \"this file is getting large\"), note them and proceed to review.\n\n**NEEDS_CONTEXT:** The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.\n\n**BLOCKED:** The implementer cannot complete the task. Assess the blocker:\n1. If it's a context problem, provide more context and re-dispatch with the same model\n2. If the task requires more reasoning, re-dispatch with a more capable model\n3. If the task is too large, break it into smaller pieces\n4. If the plan itself is wrong, escalate to the human\n\n**Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.\n\n## Prompt Templates\n\n- `.\u002Fimplementer-prompt.md` - Dispatch implementer subagent\n- `.\u002Fspec-reviewer-prompt.md` - Dispatch spec compliance reviewer subagent\n- `.\u002Fcode-quality-reviewer-prompt.md` - Dispatch code quality reviewer subagent\n\n## Example Workflow\n\n```\nYou: I'm using Subagent-Driven Development to execute this plan.\n\n[Read plan file once: docs\u002Fsuperpowers\u002Fplans\u002Ffeature-plan.md]\n[Extract all 5 tasks with full text and context]\n[Create TodoWrite with all tasks]\n\nTask 1: Hook installation script\n\n[Get Task 1 text and context (already extracted)]\n[Dispatch implementation subagent with full task text + context]\n\nImplementer: \"Before I begin - should the hook be installed at user or system level?\"\n\nYou: \"User level (~\u002F.config\u002Fsuperpowers\u002Fhooks\u002F)\"\n\nImplementer: \"Got it. Implementing now...\"\n[Later] Implementer:\n  - Implemented install-hook command\n  - Added tests, 5\u002F5 passing\n  - Self-review: Found I missed --force flag, added it\n  - Committed\n\n[Dispatch spec compliance reviewer]\nSpec reviewer: ✅ Spec compliant - all requirements met, nothing extra\n\n[Get git SHAs, dispatch code quality reviewer]\nCode reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.\n\n[Mark Task 1 complete]\n\nTask 2: Recovery modes\n\n[Get Task 2 text and context (already extracted)]\n[Dispatch implementation subagent with full task text + context]\n\nImplementer: [No questions, proceeds]\nImplementer:\n  - Added verify\u002Frepair modes\n  - 8\u002F8 tests passing\n  - Self-review: All good\n  - Committed\n\n[Dispatch spec compliance reviewer]\nSpec reviewer: ❌ Issues:\n  - Missing: Progress reporting (spec says \"report every 100 items\")\n  - Extra: Added --json flag (not requested)\n\n[Implementer fixes issues]\nImplementer: Removed --json flag, added progress reporting\n\n[Spec reviewer reviews again]\nSpec reviewer: ✅ Spec compliant now\n\n[Dispatch code quality reviewer]\nCode reviewer: Strengths: Solid. Issues (Important): Magic number (100)\n\n[Implementer fixes]\nImplementer: Extracted PROGRESS_INTERVAL constant\n\n[Code reviewer reviews again]\nCode reviewer: ✅ Approved\n\n[Mark Task 2 complete]\n\n...\n\n[After all tasks]\n[Dispatch final code-reviewer]\nFinal reviewer: All requirements met, ready to merge\n\nDone!\n```\n\n## Advantages\n\n**vs. Manual execution:**\n- Subagents follow TDD naturally\n- Fresh context per task (no confusion)\n- Parallel-safe (subagents don't interfere)\n- Subagent can ask questions (before AND during work)\n\n**vs. Executing Plans:**\n- Same session (no handoff)\n- Continuous progress (no waiting)\n- Review checkpoints automatic\n\n**Efficiency gains:**\n- No file reading overhead (controller provides full text)\n- Controller curates exactly what context is needed\n- Subagent gets complete information upfront\n- Questions surfaced before work begins (not after)\n\n**Quality gates:**\n- Self-review catches issues before handoff\n- Two-stage review: spec compliance, then code quality\n- Review loops ensure fixes actually work\n- Spec compliance prevents over\u002Funder-building\n- Code quality ensures implementation is well-built\n\n**Cost:**\n- More subagent invocations (implementer + 2 reviewers per task)\n- Controller does more prep work (extracting all tasks upfront)\n- Review loops add iterations\n- But catches issues early (cheaper than debugging later)\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- Skip scene-setting context (subagent needs to understand where task fits)\n- Ignore subagent questions (answer before letting them proceed)\n- Accept \"close enough\" on spec compliance (spec reviewer found issues = not done)\n- Skip review loops (reviewer found issues = implementer fixes = review again)\n- Let implementer self-review replace actual review (both are needed)\n- **Start code quality review before spec compliance is ✅** (wrong order)\n- Move to next task while either review has open issues\n\n**If subagent asks questions:**\n- Answer clearly and completely\n- Provide additional context if needed\n- Don't rush them into implementation\n\n**If reviewer finds issues:**\n- Implementer (same subagent) fixes them\n- Reviewer reviews again\n- Repeat until approved\n- Don't skip the re-review\n\n**If subagent fails task:**\n- Dispatch fix subagent with specific instructions\n- Don't try to fix manually (context pollution)\n\n## Integration\n\n**Required workflow skills:**\n- **superpowers:using-git-worktrees** - Ensures isolated workspace (creates one or verifies existing)\n- **superpowers:writing-plans** - Creates the plan this skill executes\n- **superpowers:requesting-code-review** - Code review template for reviewer subagents\n- **superpowers:finishing-a-development-branch** - Complete development after all tasks\n\n**Subagents should use:**\n- **superpowers:test-driven-development** - Subagents follow TDD for each task\n\n**Alternative workflow:**\n- **superpowers:executing-plans** - Use for parallel session instead of same-session execution\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,46,52,63,73,83,90,240,248,273,279,645,651,656,666,676,686,694,712,718,723,733,743,753,763,787,797,803,839,845,855,861,869,892,900,918,926,949,957,985,993,1016,1022,1030,1098,1106,1124,1132,1155,1163,1176,1182,1190,1233,1241,1254,1262,1275],{"type":39,"tag":40,"props":41,"children":42},"element","h1",{"id":4},[43],{"type":44,"value":45},"text","Subagent-Driven Development",{"type":39,"tag":47,"props":48,"children":49},"p",{},[50],{"type":44,"value":51},"Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.",{"type":39,"tag":47,"props":53,"children":54},{},[55,61],{"type":39,"tag":56,"props":57,"children":58},"strong",{},[59],{"type":44,"value":60},"Why subagents:",{"type":44,"value":62}," You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.",{"type":39,"tag":47,"props":64,"children":65},{},[66,71],{"type":39,"tag":56,"props":67,"children":68},{},[69],{"type":44,"value":70},"Core principle:",{"type":44,"value":72}," Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration",{"type":39,"tag":47,"props":74,"children":75},{},[76,81],{"type":39,"tag":56,"props":77,"children":78},{},[79],{"type":44,"value":80},"Continuous execution:",{"type":44,"value":82}," Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. \"Should I continue?\" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.",{"type":39,"tag":84,"props":85,"children":87},"h2",{"id":86},"when-to-use",[88],{"type":44,"value":89},"When to Use",{"type":39,"tag":91,"props":92,"children":97},"pre",{"className":93,"code":94,"language":95,"meta":96,"style":96},"language-dot shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","digraph when_to_use {\n    \"Have implementation plan?\" [shape=diamond];\n    \"Tasks mostly independent?\" [shape=diamond];\n    \"Stay in this session?\" [shape=diamond];\n    \"subagent-driven-development\" [shape=box];\n    \"executing-plans\" [shape=box];\n    \"Manual execution or brainstorm first\" [shape=box];\n\n    \"Have implementation plan?\" -> \"Tasks mostly independent?\" [label=\"yes\"];\n    \"Have implementation plan?\" -> \"Manual execution or brainstorm first\" [label=\"no\"];\n    \"Tasks mostly independent?\" -> \"Stay in this session?\" [label=\"yes\"];\n    \"Tasks mostly independent?\" -> \"Manual execution or brainstorm first\" [label=\"no - tightly coupled\"];\n    \"Stay in this session?\" -> \"subagent-driven-development\" [label=\"yes\"];\n    \"Stay in this session?\" -> \"executing-plans\" [label=\"no - parallel session\"];\n}\n","dot","",[98],{"type":39,"tag":99,"props":100,"children":101},"code",{"__ignoreMap":96},[102,113,122,131,140,149,158,167,177,186,195,204,213,222,231],{"type":39,"tag":103,"props":104,"children":107},"span",{"class":105,"line":106},"line",1,[108],{"type":39,"tag":103,"props":109,"children":110},{},[111],{"type":44,"value":112},"digraph when_to_use {\n",{"type":39,"tag":103,"props":114,"children":116},{"class":105,"line":115},2,[117],{"type":39,"tag":103,"props":118,"children":119},{},[120],{"type":44,"value":121},"    \"Have implementation plan?\" [shape=diamond];\n",{"type":39,"tag":103,"props":123,"children":125},{"class":105,"line":124},3,[126],{"type":39,"tag":103,"props":127,"children":128},{},[129],{"type":44,"value":130},"    \"Tasks mostly independent?\" [shape=diamond];\n",{"type":39,"tag":103,"props":132,"children":134},{"class":105,"line":133},4,[135],{"type":39,"tag":103,"props":136,"children":137},{},[138],{"type":44,"value":139},"    \"Stay in this session?\" [shape=diamond];\n",{"type":39,"tag":103,"props":141,"children":143},{"class":105,"line":142},5,[144],{"type":39,"tag":103,"props":145,"children":146},{},[147],{"type":44,"value":148},"    \"subagent-driven-development\" [shape=box];\n",{"type":39,"tag":103,"props":150,"children":152},{"class":105,"line":151},6,[153],{"type":39,"tag":103,"props":154,"children":155},{},[156],{"type":44,"value":157},"    \"executing-plans\" [shape=box];\n",{"type":39,"tag":103,"props":159,"children":161},{"class":105,"line":160},7,[162],{"type":39,"tag":103,"props":163,"children":164},{},[165],{"type":44,"value":166},"    \"Manual execution or brainstorm first\" [shape=box];\n",{"type":39,"tag":103,"props":168,"children":170},{"class":105,"line":169},8,[171],{"type":39,"tag":103,"props":172,"children":174},{"emptyLinePlaceholder":173},true,[175],{"type":44,"value":176},"\n",{"type":39,"tag":103,"props":178,"children":180},{"class":105,"line":179},9,[181],{"type":39,"tag":103,"props":182,"children":183},{},[184],{"type":44,"value":185},"    \"Have implementation plan?\" -> \"Tasks mostly independent?\" [label=\"yes\"];\n",{"type":39,"tag":103,"props":187,"children":189},{"class":105,"line":188},10,[190],{"type":39,"tag":103,"props":191,"children":192},{},[193],{"type":44,"value":194},"    \"Have implementation plan?\" -> \"Manual execution or brainstorm first\" [label=\"no\"];\n",{"type":39,"tag":103,"props":196,"children":198},{"class":105,"line":197},11,[199],{"type":39,"tag":103,"props":200,"children":201},{},[202],{"type":44,"value":203},"    \"Tasks mostly independent?\" -> \"Stay in this session?\" [label=\"yes\"];\n",{"type":39,"tag":103,"props":205,"children":207},{"class":105,"line":206},12,[208],{"type":39,"tag":103,"props":209,"children":210},{},[211],{"type":44,"value":212},"    \"Tasks mostly independent?\" -> \"Manual execution or brainstorm first\" [label=\"no - tightly coupled\"];\n",{"type":39,"tag":103,"props":214,"children":216},{"class":105,"line":215},13,[217],{"type":39,"tag":103,"props":218,"children":219},{},[220],{"type":44,"value":221},"    \"Stay in this session?\" -> \"subagent-driven-development\" [label=\"yes\"];\n",{"type":39,"tag":103,"props":223,"children":225},{"class":105,"line":224},14,[226],{"type":39,"tag":103,"props":227,"children":228},{},[229],{"type":44,"value":230},"    \"Stay in this session?\" -> \"executing-plans\" [label=\"no - parallel session\"];\n",{"type":39,"tag":103,"props":232,"children":234},{"class":105,"line":233},15,[235],{"type":39,"tag":103,"props":236,"children":237},{},[238],{"type":44,"value":239},"}\n",{"type":39,"tag":47,"props":241,"children":242},{},[243],{"type":39,"tag":56,"props":244,"children":245},{},[246],{"type":44,"value":247},"vs. Executing Plans (parallel session):",{"type":39,"tag":249,"props":250,"children":251},"ul",{},[252,258,263,268],{"type":39,"tag":253,"props":254,"children":255},"li",{},[256],{"type":44,"value":257},"Same session (no context switch)",{"type":39,"tag":253,"props":259,"children":260},{},[261],{"type":44,"value":262},"Fresh subagent per task (no context pollution)",{"type":39,"tag":253,"props":264,"children":265},{},[266],{"type":44,"value":267},"Two-stage review after each task: spec compliance first, then code quality",{"type":39,"tag":253,"props":269,"children":270},{},[271],{"type":44,"value":272},"Faster iteration (no human-in-loop between tasks)",{"type":39,"tag":84,"props":274,"children":276},{"id":275},"the-process",[277],{"type":44,"value":278},"The Process",{"type":39,"tag":91,"props":280,"children":282},{"className":93,"code":281,"language":95,"meta":96,"style":96},"digraph process {\n    rankdir=TB;\n\n    subgraph cluster_per_task {\n        label=\"Per Task\";\n        \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\" [shape=box];\n        \"Implementer subagent asks questions?\" [shape=diamond];\n        \"Answer questions, provide context\" [shape=box];\n        \"Implementer subagent implements, tests, commits, self-reviews\" [shape=box];\n        \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\" [shape=box];\n        \"Spec reviewer subagent confirms code matches spec?\" [shape=diamond];\n        \"Implementer subagent fixes spec gaps\" [shape=box];\n        \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" [shape=box];\n        \"Code quality reviewer subagent approves?\" [shape=diamond];\n        \"Implementer subagent fixes quality issues\" [shape=box];\n        \"Mark task complete in TodoWrite\" [shape=box];\n    }\n\n    \"Read plan, extract all tasks with full text, note context, create TodoWrite\" [shape=box];\n    \"More tasks remain?\" [shape=diamond];\n    \"Dispatch final code reviewer subagent for entire implementation\" [shape=box];\n    \"Use superpowers:finishing-a-development-branch\" [shape=box style=filled fillcolor=lightgreen];\n\n    \"Read plan, extract all tasks with full text, note context, create TodoWrite\" -> \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\";\n    \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\" -> \"Implementer subagent asks questions?\";\n    \"Implementer subagent asks questions?\" -> \"Answer questions, provide context\" [label=\"yes\"];\n    \"Answer questions, provide context\" -> \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\";\n    \"Implementer subagent asks questions?\" -> \"Implementer subagent implements, tests, commits, self-reviews\" [label=\"no\"];\n    \"Implementer subagent implements, tests, commits, self-reviews\" -> \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\";\n    \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\" -> \"Spec reviewer subagent confirms code matches spec?\";\n    \"Spec reviewer subagent confirms code matches spec?\" -> \"Implementer subagent fixes spec gaps\" [label=\"no\"];\n    \"Implementer subagent fixes spec gaps\" -> \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\" [label=\"re-review\"];\n    \"Spec reviewer subagent confirms code matches spec?\" -> \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" [label=\"yes\"];\n    \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" -> \"Code quality reviewer subagent approves?\";\n    \"Code quality reviewer subagent approves?\" -> \"Implementer subagent fixes quality issues\" [label=\"no\"];\n    \"Implementer subagent fixes quality issues\" -> \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" [label=\"re-review\"];\n    \"Code quality reviewer subagent approves?\" -> \"Mark task complete in TodoWrite\" [label=\"yes\"];\n    \"Mark task complete in TodoWrite\" -> \"More tasks remain?\";\n    \"More tasks remain?\" -> \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\" [label=\"yes\"];\n    \"More tasks remain?\" -> \"Dispatch final code reviewer subagent for entire implementation\" [label=\"no\"];\n    \"Dispatch final code reviewer subagent for entire implementation\" -> \"Use superpowers:finishing-a-development-branch\";\n}\n",[283],{"type":39,"tag":99,"props":284,"children":285},{"__ignoreMap":96},[286,294,302,309,317,325,333,341,349,357,365,373,381,389,397,405,414,423,431,440,449,458,467,475,484,493,502,511,520,529,538,547,556,565,574,583,592,601,610,619,628,637],{"type":39,"tag":103,"props":287,"children":288},{"class":105,"line":106},[289],{"type":39,"tag":103,"props":290,"children":291},{},[292],{"type":44,"value":293},"digraph process {\n",{"type":39,"tag":103,"props":295,"children":296},{"class":105,"line":115},[297],{"type":39,"tag":103,"props":298,"children":299},{},[300],{"type":44,"value":301},"    rankdir=TB;\n",{"type":39,"tag":103,"props":303,"children":304},{"class":105,"line":124},[305],{"type":39,"tag":103,"props":306,"children":307},{"emptyLinePlaceholder":173},[308],{"type":44,"value":176},{"type":39,"tag":103,"props":310,"children":311},{"class":105,"line":133},[312],{"type":39,"tag":103,"props":313,"children":314},{},[315],{"type":44,"value":316},"    subgraph cluster_per_task {\n",{"type":39,"tag":103,"props":318,"children":319},{"class":105,"line":142},[320],{"type":39,"tag":103,"props":321,"children":322},{},[323],{"type":44,"value":324},"        label=\"Per Task\";\n",{"type":39,"tag":103,"props":326,"children":327},{"class":105,"line":151},[328],{"type":39,"tag":103,"props":329,"children":330},{},[331],{"type":44,"value":332},"        \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\" [shape=box];\n",{"type":39,"tag":103,"props":334,"children":335},{"class":105,"line":160},[336],{"type":39,"tag":103,"props":337,"children":338},{},[339],{"type":44,"value":340},"        \"Implementer subagent asks questions?\" [shape=diamond];\n",{"type":39,"tag":103,"props":342,"children":343},{"class":105,"line":169},[344],{"type":39,"tag":103,"props":345,"children":346},{},[347],{"type":44,"value":348},"        \"Answer questions, provide context\" [shape=box];\n",{"type":39,"tag":103,"props":350,"children":351},{"class":105,"line":179},[352],{"type":39,"tag":103,"props":353,"children":354},{},[355],{"type":44,"value":356},"        \"Implementer subagent implements, tests, commits, self-reviews\" [shape=box];\n",{"type":39,"tag":103,"props":358,"children":359},{"class":105,"line":188},[360],{"type":39,"tag":103,"props":361,"children":362},{},[363],{"type":44,"value":364},"        \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\" [shape=box];\n",{"type":39,"tag":103,"props":366,"children":367},{"class":105,"line":197},[368],{"type":39,"tag":103,"props":369,"children":370},{},[371],{"type":44,"value":372},"        \"Spec reviewer subagent confirms code matches spec?\" [shape=diamond];\n",{"type":39,"tag":103,"props":374,"children":375},{"class":105,"line":206},[376],{"type":39,"tag":103,"props":377,"children":378},{},[379],{"type":44,"value":380},"        \"Implementer subagent fixes spec gaps\" [shape=box];\n",{"type":39,"tag":103,"props":382,"children":383},{"class":105,"line":215},[384],{"type":39,"tag":103,"props":385,"children":386},{},[387],{"type":44,"value":388},"        \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" [shape=box];\n",{"type":39,"tag":103,"props":390,"children":391},{"class":105,"line":224},[392],{"type":39,"tag":103,"props":393,"children":394},{},[395],{"type":44,"value":396},"        \"Code quality reviewer subagent approves?\" [shape=diamond];\n",{"type":39,"tag":103,"props":398,"children":399},{"class":105,"line":233},[400],{"type":39,"tag":103,"props":401,"children":402},{},[403],{"type":44,"value":404},"        \"Implementer subagent fixes quality issues\" [shape=box];\n",{"type":39,"tag":103,"props":406,"children":408},{"class":105,"line":407},16,[409],{"type":39,"tag":103,"props":410,"children":411},{},[412],{"type":44,"value":413},"        \"Mark task complete in TodoWrite\" [shape=box];\n",{"type":39,"tag":103,"props":415,"children":417},{"class":105,"line":416},17,[418],{"type":39,"tag":103,"props":419,"children":420},{},[421],{"type":44,"value":422},"    }\n",{"type":39,"tag":103,"props":424,"children":426},{"class":105,"line":425},18,[427],{"type":39,"tag":103,"props":428,"children":429},{"emptyLinePlaceholder":173},[430],{"type":44,"value":176},{"type":39,"tag":103,"props":432,"children":434},{"class":105,"line":433},19,[435],{"type":39,"tag":103,"props":436,"children":437},{},[438],{"type":44,"value":439},"    \"Read plan, extract all tasks with full text, note context, create TodoWrite\" [shape=box];\n",{"type":39,"tag":103,"props":441,"children":443},{"class":105,"line":442},20,[444],{"type":39,"tag":103,"props":445,"children":446},{},[447],{"type":44,"value":448},"    \"More tasks remain?\" [shape=diamond];\n",{"type":39,"tag":103,"props":450,"children":452},{"class":105,"line":451},21,[453],{"type":39,"tag":103,"props":454,"children":455},{},[456],{"type":44,"value":457},"    \"Dispatch final code reviewer subagent for entire implementation\" [shape=box];\n",{"type":39,"tag":103,"props":459,"children":461},{"class":105,"line":460},22,[462],{"type":39,"tag":103,"props":463,"children":464},{},[465],{"type":44,"value":466},"    \"Use superpowers:finishing-a-development-branch\" [shape=box style=filled fillcolor=lightgreen];\n",{"type":39,"tag":103,"props":468,"children":470},{"class":105,"line":469},23,[471],{"type":39,"tag":103,"props":472,"children":473},{"emptyLinePlaceholder":173},[474],{"type":44,"value":176},{"type":39,"tag":103,"props":476,"children":478},{"class":105,"line":477},24,[479],{"type":39,"tag":103,"props":480,"children":481},{},[482],{"type":44,"value":483},"    \"Read plan, extract all tasks with full text, note context, create TodoWrite\" -> \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\";\n",{"type":39,"tag":103,"props":485,"children":487},{"class":105,"line":486},25,[488],{"type":39,"tag":103,"props":489,"children":490},{},[491],{"type":44,"value":492},"    \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\" -> \"Implementer subagent asks questions?\";\n",{"type":39,"tag":103,"props":494,"children":496},{"class":105,"line":495},26,[497],{"type":39,"tag":103,"props":498,"children":499},{},[500],{"type":44,"value":501},"    \"Implementer subagent asks questions?\" -> \"Answer questions, provide context\" [label=\"yes\"];\n",{"type":39,"tag":103,"props":503,"children":505},{"class":105,"line":504},27,[506],{"type":39,"tag":103,"props":507,"children":508},{},[509],{"type":44,"value":510},"    \"Answer questions, provide context\" -> \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\";\n",{"type":39,"tag":103,"props":512,"children":514},{"class":105,"line":513},28,[515],{"type":39,"tag":103,"props":516,"children":517},{},[518],{"type":44,"value":519},"    \"Implementer subagent asks questions?\" -> \"Implementer subagent implements, tests, commits, self-reviews\" [label=\"no\"];\n",{"type":39,"tag":103,"props":521,"children":523},{"class":105,"line":522},29,[524],{"type":39,"tag":103,"props":525,"children":526},{},[527],{"type":44,"value":528},"    \"Implementer subagent implements, tests, commits, self-reviews\" -> \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\";\n",{"type":39,"tag":103,"props":530,"children":532},{"class":105,"line":531},30,[533],{"type":39,"tag":103,"props":534,"children":535},{},[536],{"type":44,"value":537},"    \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\" -> \"Spec reviewer subagent confirms code matches spec?\";\n",{"type":39,"tag":103,"props":539,"children":541},{"class":105,"line":540},31,[542],{"type":39,"tag":103,"props":543,"children":544},{},[545],{"type":44,"value":546},"    \"Spec reviewer subagent confirms code matches spec?\" -> \"Implementer subagent fixes spec gaps\" [label=\"no\"];\n",{"type":39,"tag":103,"props":548,"children":550},{"class":105,"line":549},32,[551],{"type":39,"tag":103,"props":552,"children":553},{},[554],{"type":44,"value":555},"    \"Implementer subagent fixes spec gaps\" -> \"Dispatch spec reviewer subagent (.\u002Fspec-reviewer-prompt.md)\" [label=\"re-review\"];\n",{"type":39,"tag":103,"props":557,"children":559},{"class":105,"line":558},33,[560],{"type":39,"tag":103,"props":561,"children":562},{},[563],{"type":44,"value":564},"    \"Spec reviewer subagent confirms code matches spec?\" -> \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" [label=\"yes\"];\n",{"type":39,"tag":103,"props":566,"children":568},{"class":105,"line":567},34,[569],{"type":39,"tag":103,"props":570,"children":571},{},[572],{"type":44,"value":573},"    \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" -> \"Code quality reviewer subagent approves?\";\n",{"type":39,"tag":103,"props":575,"children":577},{"class":105,"line":576},35,[578],{"type":39,"tag":103,"props":579,"children":580},{},[581],{"type":44,"value":582},"    \"Code quality reviewer subagent approves?\" -> \"Implementer subagent fixes quality issues\" [label=\"no\"];\n",{"type":39,"tag":103,"props":584,"children":586},{"class":105,"line":585},36,[587],{"type":39,"tag":103,"props":588,"children":589},{},[590],{"type":44,"value":591},"    \"Implementer subagent fixes quality issues\" -> \"Dispatch code quality reviewer subagent (.\u002Fcode-quality-reviewer-prompt.md)\" [label=\"re-review\"];\n",{"type":39,"tag":103,"props":593,"children":595},{"class":105,"line":594},37,[596],{"type":39,"tag":103,"props":597,"children":598},{},[599],{"type":44,"value":600},"    \"Code quality reviewer subagent approves?\" -> \"Mark task complete in TodoWrite\" [label=\"yes\"];\n",{"type":39,"tag":103,"props":602,"children":604},{"class":105,"line":603},38,[605],{"type":39,"tag":103,"props":606,"children":607},{},[608],{"type":44,"value":609},"    \"Mark task complete in TodoWrite\" -> \"More tasks remain?\";\n",{"type":39,"tag":103,"props":611,"children":613},{"class":105,"line":612},39,[614],{"type":39,"tag":103,"props":615,"children":616},{},[617],{"type":44,"value":618},"    \"More tasks remain?\" -> \"Dispatch implementer subagent (.\u002Fimplementer-prompt.md)\" [label=\"yes\"];\n",{"type":39,"tag":103,"props":620,"children":622},{"class":105,"line":621},40,[623],{"type":39,"tag":103,"props":624,"children":625},{},[626],{"type":44,"value":627},"    \"More tasks remain?\" -> \"Dispatch final code reviewer subagent for entire implementation\" [label=\"no\"];\n",{"type":39,"tag":103,"props":629,"children":631},{"class":105,"line":630},41,[632],{"type":39,"tag":103,"props":633,"children":634},{},[635],{"type":44,"value":636},"    \"Dispatch final code reviewer subagent for entire implementation\" -> \"Use superpowers:finishing-a-development-branch\";\n",{"type":39,"tag":103,"props":638,"children":640},{"class":105,"line":639},42,[641],{"type":39,"tag":103,"props":642,"children":643},{},[644],{"type":44,"value":239},{"type":39,"tag":84,"props":646,"children":648},{"id":647},"model-selection",[649],{"type":44,"value":650},"Model Selection",{"type":39,"tag":47,"props":652,"children":653},{},[654],{"type":44,"value":655},"Use the least powerful model that can handle each role to conserve cost and increase speed.",{"type":39,"tag":47,"props":657,"children":658},{},[659,664],{"type":39,"tag":56,"props":660,"children":661},{},[662],{"type":44,"value":663},"Mechanical implementation tasks",{"type":44,"value":665}," (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.",{"type":39,"tag":47,"props":667,"children":668},{},[669,674],{"type":39,"tag":56,"props":670,"children":671},{},[672],{"type":44,"value":673},"Integration and judgment tasks",{"type":44,"value":675}," (multi-file coordination, pattern matching, debugging): use a standard model.",{"type":39,"tag":47,"props":677,"children":678},{},[679,684],{"type":39,"tag":56,"props":680,"children":681},{},[682],{"type":44,"value":683},"Architecture, design, and review tasks",{"type":44,"value":685},": use the most capable available model.",{"type":39,"tag":47,"props":687,"children":688},{},[689],{"type":39,"tag":56,"props":690,"children":691},{},[692],{"type":44,"value":693},"Task complexity signals:",{"type":39,"tag":249,"props":695,"children":696},{},[697,702,707],{"type":39,"tag":253,"props":698,"children":699},{},[700],{"type":44,"value":701},"Touches 1-2 files with a complete spec → cheap model",{"type":39,"tag":253,"props":703,"children":704},{},[705],{"type":44,"value":706},"Touches multiple files with integration concerns → standard model",{"type":39,"tag":253,"props":708,"children":709},{},[710],{"type":44,"value":711},"Requires design judgment or broad codebase understanding → most capable model",{"type":39,"tag":84,"props":713,"children":715},{"id":714},"handling-implementer-status",[716],{"type":44,"value":717},"Handling Implementer Status",{"type":39,"tag":47,"props":719,"children":720},{},[721],{"type":44,"value":722},"Implementer subagents report one of four statuses. Handle each appropriately:",{"type":39,"tag":47,"props":724,"children":725},{},[726,731],{"type":39,"tag":56,"props":727,"children":728},{},[729],{"type":44,"value":730},"DONE:",{"type":44,"value":732}," Proceed to spec compliance review.",{"type":39,"tag":47,"props":734,"children":735},{},[736,741],{"type":39,"tag":56,"props":737,"children":738},{},[739],{"type":44,"value":740},"DONE_WITH_CONCERNS:",{"type":44,"value":742}," The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., \"this file is getting large\"), note them and proceed to review.",{"type":39,"tag":47,"props":744,"children":745},{},[746,751],{"type":39,"tag":56,"props":747,"children":748},{},[749],{"type":44,"value":750},"NEEDS_CONTEXT:",{"type":44,"value":752}," The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.",{"type":39,"tag":47,"props":754,"children":755},{},[756,761],{"type":39,"tag":56,"props":757,"children":758},{},[759],{"type":44,"value":760},"BLOCKED:",{"type":44,"value":762}," The implementer cannot complete the task. Assess the blocker:",{"type":39,"tag":764,"props":765,"children":766},"ol",{},[767,772,777,782],{"type":39,"tag":253,"props":768,"children":769},{},[770],{"type":44,"value":771},"If it's a context problem, provide more context and re-dispatch with the same model",{"type":39,"tag":253,"props":773,"children":774},{},[775],{"type":44,"value":776},"If the task requires more reasoning, re-dispatch with a more capable model",{"type":39,"tag":253,"props":778,"children":779},{},[780],{"type":44,"value":781},"If the task is too large, break it into smaller pieces",{"type":39,"tag":253,"props":783,"children":784},{},[785],{"type":44,"value":786},"If the plan itself is wrong, escalate to the human",{"type":39,"tag":47,"props":788,"children":789},{},[790,795],{"type":39,"tag":56,"props":791,"children":792},{},[793],{"type":44,"value":794},"Never",{"type":44,"value":796}," ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.",{"type":39,"tag":84,"props":798,"children":800},{"id":799},"prompt-templates",[801],{"type":44,"value":802},"Prompt Templates",{"type":39,"tag":249,"props":804,"children":805},{},[806,817,828],{"type":39,"tag":253,"props":807,"children":808},{},[809,815],{"type":39,"tag":99,"props":810,"children":812},{"className":811},[],[813],{"type":44,"value":814},".\u002Fimplementer-prompt.md",{"type":44,"value":816}," - Dispatch implementer subagent",{"type":39,"tag":253,"props":818,"children":819},{},[820,826],{"type":39,"tag":99,"props":821,"children":823},{"className":822},[],[824],{"type":44,"value":825},".\u002Fspec-reviewer-prompt.md",{"type":44,"value":827}," - Dispatch spec compliance reviewer subagent",{"type":39,"tag":253,"props":829,"children":830},{},[831,837],{"type":39,"tag":99,"props":832,"children":834},{"className":833},[],[835],{"type":44,"value":836},".\u002Fcode-quality-reviewer-prompt.md",{"type":44,"value":838}," - Dispatch code quality reviewer subagent",{"type":39,"tag":84,"props":840,"children":842},{"id":841},"example-workflow",[843],{"type":44,"value":844},"Example Workflow",{"type":39,"tag":91,"props":846,"children":850},{"className":847,"code":849,"language":44},[848],"language-text","You: I'm using Subagent-Driven Development to execute this plan.\n\n[Read plan file once: docs\u002Fsuperpowers\u002Fplans\u002Ffeature-plan.md]\n[Extract all 5 tasks with full text and context]\n[Create TodoWrite with all tasks]\n\nTask 1: Hook installation script\n\n[Get Task 1 text and context (already extracted)]\n[Dispatch implementation subagent with full task text + context]\n\nImplementer: \"Before I begin - should the hook be installed at user or system level?\"\n\nYou: \"User level (~\u002F.config\u002Fsuperpowers\u002Fhooks\u002F)\"\n\nImplementer: \"Got it. Implementing now...\"\n[Later] Implementer:\n  - Implemented install-hook command\n  - Added tests, 5\u002F5 passing\n  - Self-review: Found I missed --force flag, added it\n  - Committed\n\n[Dispatch spec compliance reviewer]\nSpec reviewer: ✅ Spec compliant - all requirements met, nothing extra\n\n[Get git SHAs, dispatch code quality reviewer]\nCode reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.\n\n[Mark Task 1 complete]\n\nTask 2: Recovery modes\n\n[Get Task 2 text and context (already extracted)]\n[Dispatch implementation subagent with full task text + context]\n\nImplementer: [No questions, proceeds]\nImplementer:\n  - Added verify\u002Frepair modes\n  - 8\u002F8 tests passing\n  - Self-review: All good\n  - Committed\n\n[Dispatch spec compliance reviewer]\nSpec reviewer: ❌ Issues:\n  - Missing: Progress reporting (spec says \"report every 100 items\")\n  - Extra: Added --json flag (not requested)\n\n[Implementer fixes issues]\nImplementer: Removed --json flag, added progress reporting\n\n[Spec reviewer reviews again]\nSpec reviewer: ✅ Spec compliant now\n\n[Dispatch code quality reviewer]\nCode reviewer: Strengths: Solid. Issues (Important): Magic number (100)\n\n[Implementer fixes]\nImplementer: Extracted PROGRESS_INTERVAL constant\n\n[Code reviewer reviews again]\nCode reviewer: ✅ Approved\n\n[Mark Task 2 complete]\n\n...\n\n[After all tasks]\n[Dispatch final code-reviewer]\nFinal reviewer: All requirements met, ready to merge\n\nDone!\n",[851],{"type":39,"tag":99,"props":852,"children":853},{"__ignoreMap":96},[854],{"type":44,"value":849},{"type":39,"tag":84,"props":856,"children":858},{"id":857},"advantages",[859],{"type":44,"value":860},"Advantages",{"type":39,"tag":47,"props":862,"children":863},{},[864],{"type":39,"tag":56,"props":865,"children":866},{},[867],{"type":44,"value":868},"vs. Manual execution:",{"type":39,"tag":249,"props":870,"children":871},{},[872,877,882,887],{"type":39,"tag":253,"props":873,"children":874},{},[875],{"type":44,"value":876},"Subagents follow TDD naturally",{"type":39,"tag":253,"props":878,"children":879},{},[880],{"type":44,"value":881},"Fresh context per task (no confusion)",{"type":39,"tag":253,"props":883,"children":884},{},[885],{"type":44,"value":886},"Parallel-safe (subagents don't interfere)",{"type":39,"tag":253,"props":888,"children":889},{},[890],{"type":44,"value":891},"Subagent can ask questions (before AND during work)",{"type":39,"tag":47,"props":893,"children":894},{},[895],{"type":39,"tag":56,"props":896,"children":897},{},[898],{"type":44,"value":899},"vs. Executing Plans:",{"type":39,"tag":249,"props":901,"children":902},{},[903,908,913],{"type":39,"tag":253,"props":904,"children":905},{},[906],{"type":44,"value":907},"Same session (no handoff)",{"type":39,"tag":253,"props":909,"children":910},{},[911],{"type":44,"value":912},"Continuous progress (no waiting)",{"type":39,"tag":253,"props":914,"children":915},{},[916],{"type":44,"value":917},"Review checkpoints automatic",{"type":39,"tag":47,"props":919,"children":920},{},[921],{"type":39,"tag":56,"props":922,"children":923},{},[924],{"type":44,"value":925},"Efficiency gains:",{"type":39,"tag":249,"props":927,"children":928},{},[929,934,939,944],{"type":39,"tag":253,"props":930,"children":931},{},[932],{"type":44,"value":933},"No file reading overhead (controller provides full text)",{"type":39,"tag":253,"props":935,"children":936},{},[937],{"type":44,"value":938},"Controller curates exactly what context is needed",{"type":39,"tag":253,"props":940,"children":941},{},[942],{"type":44,"value":943},"Subagent gets complete information upfront",{"type":39,"tag":253,"props":945,"children":946},{},[947],{"type":44,"value":948},"Questions surfaced before work begins (not after)",{"type":39,"tag":47,"props":950,"children":951},{},[952],{"type":39,"tag":56,"props":953,"children":954},{},[955],{"type":44,"value":956},"Quality gates:",{"type":39,"tag":249,"props":958,"children":959},{},[960,965,970,975,980],{"type":39,"tag":253,"props":961,"children":962},{},[963],{"type":44,"value":964},"Self-review catches issues before handoff",{"type":39,"tag":253,"props":966,"children":967},{},[968],{"type":44,"value":969},"Two-stage review: spec compliance, then code quality",{"type":39,"tag":253,"props":971,"children":972},{},[973],{"type":44,"value":974},"Review loops ensure fixes actually work",{"type":39,"tag":253,"props":976,"children":977},{},[978],{"type":44,"value":979},"Spec compliance prevents over\u002Funder-building",{"type":39,"tag":253,"props":981,"children":982},{},[983],{"type":44,"value":984},"Code quality ensures implementation is well-built",{"type":39,"tag":47,"props":986,"children":987},{},[988],{"type":39,"tag":56,"props":989,"children":990},{},[991],{"type":44,"value":992},"Cost:",{"type":39,"tag":249,"props":994,"children":995},{},[996,1001,1006,1011],{"type":39,"tag":253,"props":997,"children":998},{},[999],{"type":44,"value":1000},"More subagent invocations (implementer + 2 reviewers per task)",{"type":39,"tag":253,"props":1002,"children":1003},{},[1004],{"type":44,"value":1005},"Controller does more prep work (extracting all tasks upfront)",{"type":39,"tag":253,"props":1007,"children":1008},{},[1009],{"type":44,"value":1010},"Review loops add iterations",{"type":39,"tag":253,"props":1012,"children":1013},{},[1014],{"type":44,"value":1015},"But catches issues early (cheaper than debugging later)",{"type":39,"tag":84,"props":1017,"children":1019},{"id":1018},"red-flags",[1020],{"type":44,"value":1021},"Red Flags",{"type":39,"tag":47,"props":1023,"children":1024},{},[1025],{"type":39,"tag":56,"props":1026,"children":1027},{},[1028],{"type":44,"value":1029},"Never:",{"type":39,"tag":249,"props":1031,"children":1032},{},[1033,1038,1043,1048,1053,1058,1063,1068,1073,1078,1083,1093],{"type":39,"tag":253,"props":1034,"children":1035},{},[1036],{"type":44,"value":1037},"Start implementation on main\u002Fmaster branch without explicit user consent",{"type":39,"tag":253,"props":1039,"children":1040},{},[1041],{"type":44,"value":1042},"Skip reviews (spec compliance OR code quality)",{"type":39,"tag":253,"props":1044,"children":1045},{},[1046],{"type":44,"value":1047},"Proceed with unfixed issues",{"type":39,"tag":253,"props":1049,"children":1050},{},[1051],{"type":44,"value":1052},"Dispatch multiple implementation subagents in parallel (conflicts)",{"type":39,"tag":253,"props":1054,"children":1055},{},[1056],{"type":44,"value":1057},"Make subagent read plan file (provide full text instead)",{"type":39,"tag":253,"props":1059,"children":1060},{},[1061],{"type":44,"value":1062},"Skip scene-setting context (subagent needs to understand where task fits)",{"type":39,"tag":253,"props":1064,"children":1065},{},[1066],{"type":44,"value":1067},"Ignore subagent questions (answer before letting them proceed)",{"type":39,"tag":253,"props":1069,"children":1070},{},[1071],{"type":44,"value":1072},"Accept \"close enough\" on spec compliance (spec reviewer found issues = not done)",{"type":39,"tag":253,"props":1074,"children":1075},{},[1076],{"type":44,"value":1077},"Skip review loops (reviewer found issues = implementer fixes = review again)",{"type":39,"tag":253,"props":1079,"children":1080},{},[1081],{"type":44,"value":1082},"Let implementer self-review replace actual review (both are needed)",{"type":39,"tag":253,"props":1084,"children":1085},{},[1086,1091],{"type":39,"tag":56,"props":1087,"children":1088},{},[1089],{"type":44,"value":1090},"Start code quality review before spec compliance is ✅",{"type":44,"value":1092}," (wrong order)",{"type":39,"tag":253,"props":1094,"children":1095},{},[1096],{"type":44,"value":1097},"Move to next task while either review has open issues",{"type":39,"tag":47,"props":1099,"children":1100},{},[1101],{"type":39,"tag":56,"props":1102,"children":1103},{},[1104],{"type":44,"value":1105},"If subagent asks questions:",{"type":39,"tag":249,"props":1107,"children":1108},{},[1109,1114,1119],{"type":39,"tag":253,"props":1110,"children":1111},{},[1112],{"type":44,"value":1113},"Answer clearly and completely",{"type":39,"tag":253,"props":1115,"children":1116},{},[1117],{"type":44,"value":1118},"Provide additional context if needed",{"type":39,"tag":253,"props":1120,"children":1121},{},[1122],{"type":44,"value":1123},"Don't rush them into implementation",{"type":39,"tag":47,"props":1125,"children":1126},{},[1127],{"type":39,"tag":56,"props":1128,"children":1129},{},[1130],{"type":44,"value":1131},"If reviewer finds issues:",{"type":39,"tag":249,"props":1133,"children":1134},{},[1135,1140,1145,1150],{"type":39,"tag":253,"props":1136,"children":1137},{},[1138],{"type":44,"value":1139},"Implementer (same subagent) fixes them",{"type":39,"tag":253,"props":1141,"children":1142},{},[1143],{"type":44,"value":1144},"Reviewer reviews again",{"type":39,"tag":253,"props":1146,"children":1147},{},[1148],{"type":44,"value":1149},"Repeat until approved",{"type":39,"tag":253,"props":1151,"children":1152},{},[1153],{"type":44,"value":1154},"Don't skip the re-review",{"type":39,"tag":47,"props":1156,"children":1157},{},[1158],{"type":39,"tag":56,"props":1159,"children":1160},{},[1161],{"type":44,"value":1162},"If subagent fails task:",{"type":39,"tag":249,"props":1164,"children":1165},{},[1166,1171],{"type":39,"tag":253,"props":1167,"children":1168},{},[1169],{"type":44,"value":1170},"Dispatch fix subagent with specific instructions",{"type":39,"tag":253,"props":1172,"children":1173},{},[1174],{"type":44,"value":1175},"Don't try to fix manually (context pollution)",{"type":39,"tag":84,"props":1177,"children":1179},{"id":1178},"integration",[1180],{"type":44,"value":1181},"Integration",{"type":39,"tag":47,"props":1183,"children":1184},{},[1185],{"type":39,"tag":56,"props":1186,"children":1187},{},[1188],{"type":44,"value":1189},"Required workflow skills:",{"type":39,"tag":249,"props":1191,"children":1192},{},[1193,1203,1213,1223],{"type":39,"tag":253,"props":1194,"children":1195},{},[1196,1201],{"type":39,"tag":56,"props":1197,"children":1198},{},[1199],{"type":44,"value":1200},"superpowers:using-git-worktrees",{"type":44,"value":1202}," - Ensures isolated workspace (creates one or verifies existing)",{"type":39,"tag":253,"props":1204,"children":1205},{},[1206,1211],{"type":39,"tag":56,"props":1207,"children":1208},{},[1209],{"type":44,"value":1210},"superpowers:writing-plans",{"type":44,"value":1212}," - Creates the plan this skill executes",{"type":39,"tag":253,"props":1214,"children":1215},{},[1216,1221],{"type":39,"tag":56,"props":1217,"children":1218},{},[1219],{"type":44,"value":1220},"superpowers:requesting-code-review",{"type":44,"value":1222}," - Code review template for reviewer subagents",{"type":39,"tag":253,"props":1224,"children":1225},{},[1226,1231],{"type":39,"tag":56,"props":1227,"children":1228},{},[1229],{"type":44,"value":1230},"superpowers:finishing-a-development-branch",{"type":44,"value":1232}," - Complete development after all tasks",{"type":39,"tag":47,"props":1234,"children":1235},{},[1236],{"type":39,"tag":56,"props":1237,"children":1238},{},[1239],{"type":44,"value":1240},"Subagents should use:",{"type":39,"tag":249,"props":1242,"children":1243},{},[1244],{"type":39,"tag":253,"props":1245,"children":1246},{},[1247,1252],{"type":39,"tag":56,"props":1248,"children":1249},{},[1250],{"type":44,"value":1251},"superpowers:test-driven-development",{"type":44,"value":1253}," - Subagents follow TDD for each task",{"type":39,"tag":47,"props":1255,"children":1256},{},[1257],{"type":39,"tag":56,"props":1258,"children":1259},{},[1260],{"type":44,"value":1261},"Alternative workflow:",{"type":39,"tag":249,"props":1263,"children":1264},{},[1265],{"type":39,"tag":253,"props":1266,"children":1267},{},[1268,1273],{"type":39,"tag":56,"props":1269,"children":1270},{},[1271],{"type":44,"value":1272},"superpowers:executing-plans",{"type":44,"value":1274}," - Use for parallel session instead of same-session execution",{"type":39,"tag":1276,"props":1277,"children":1278},"style",{},[1279],{"type":44,"value":1280},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1282,"total":1402},[1283,1302,1316,1328,1348,1370,1390],{"slug":1284,"name":1284,"fn":1285,"description":1286,"org":1287,"tags":1288,"stars":22,"repoUrl":23,"updatedAt":1301},"accessibility-and-inclusive-visualization","make data visualizations accessible","Make data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1289,1292,1295,1298],{"name":1290,"slug":1291,"type":15},"Accessibility","accessibility",{"name":1293,"slug":1294,"type":15},"Charts","charts",{"name":1296,"slug":1297,"type":15},"Data Visualization","data-visualization",{"name":1299,"slug":1300,"type":15},"Design","design","2026-06-30T19:00:57.102",{"slug":1303,"name":1303,"fn":1304,"description":1305,"org":1306,"tags":1307,"stars":22,"repoUrl":23,"updatedAt":1315},"agent-browser","automate browser interactions for agents","Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1308,1309,1312],{"name":13,"slug":14,"type":15},{"name":1310,"slug":1311,"type":15},"Browser Automation","browser-automation",{"name":1313,"slug":1314,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":1317,"name":1317,"fn":1318,"description":1319,"org":1320,"tags":1321,"stars":22,"repoUrl":23,"updatedAt":1327},"agent-browser-verify","verify dev server output with automated browser","Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass\u002Ffail before continuing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1322,1323,1326],{"name":1310,"slug":1311,"type":15},{"name":1324,"slug":1325,"type":15},"Local Development","local-development",{"name":1313,"slug":1314,"type":15},"2026-04-06T18:41:17.526867",{"slug":1329,"name":1329,"fn":1330,"description":1331,"org":1332,"tags":1333,"stars":22,"repoUrl":23,"updatedAt":1347},"agents-sdk","build AI agents on Cloudflare Workers","Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1334,1335,1338,1341,1344],{"name":13,"slug":14,"type":15},{"name":1336,"slug":1337,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1339,"slug":1340,"type":15},"SDK","sdk",{"name":1342,"slug":1343,"type":15},"Serverless","serverless",{"name":1345,"slug":1346,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":1349,"name":1349,"fn":1350,"description":1351,"org":1352,"tags":1353,"stars":22,"repoUrl":23,"updatedAt":1369},"ai-elements","build chat UIs with AI Elements","AI Elements component library guidance — pre-built React components for AI interfaces built on shadcn\u002Fui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1354,1357,1360,1363,1366],{"name":1355,"slug":1356,"type":15},"Frontend","frontend",{"name":1358,"slug":1359,"type":15},"React","react",{"name":1361,"slug":1362,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":1364,"slug":1365,"type":15},"UI Components","ui-components",{"name":1367,"slug":1368,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":1371,"name":1371,"fn":1372,"description":1373,"org":1374,"tags":1375,"stars":22,"repoUrl":23,"updatedAt":1389},"ai-gateway","configure Vercel AI Gateway","Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1376,1379,1382,1385,1388],{"name":1377,"slug":1378,"type":15},"AI Infrastructure","ai-infrastructure",{"name":1380,"slug":1381,"type":15},"Cost Optimization","cost-optimization",{"name":1383,"slug":1384,"type":15},"LLM","llm",{"name":1386,"slug":1387,"type":15},"Performance","performance",{"name":1367,"slug":1368,"type":15},"2026-04-06T18:40:44.377464",{"slug":1391,"name":1391,"fn":1392,"description":1393,"org":1394,"tags":1395,"stars":22,"repoUrl":23,"updatedAt":1401},"ai-generation-persistence","implement persistence patterns for AI generations","AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1396,1397,1400],{"name":1380,"slug":1381,"type":15},{"name":1398,"slug":1399,"type":15},"Database","database",{"name":1383,"slug":1384,"type":15},"2026-04-06T18:41:08.513425",600,{"items":1404,"total":1601},[1405,1426,1449,1466,1482,1499,1518,1530,1544,1558,1570,1585],{"slug":1406,"name":1406,"fn":1407,"description":1408,"org":1409,"tags":1410,"stars":1423,"repoUrl":1424,"updatedAt":1425},"prior-auth-packet-builder","build healthcare prior authorization packets","Build a concise prior authorization packet from local case files and payer policy docs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1411,1414,1417,1420],{"name":1412,"slug":1413,"type":15},"Documents","documents",{"name":1415,"slug":1416,"type":15},"Healthcare","healthcare",{"name":1418,"slug":1419,"type":15},"Insurance","insurance",{"name":1421,"slug":1422,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":1427,"name":1427,"fn":1428,"description":1429,"org":1430,"tags":1431,"stars":1446,"repoUrl":1447,"updatedAt":1448},"aspnet-core","build ASP.NET Core web applications","Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1432,1435,1437,1440,1443],{"name":1433,"slug":1434,"type":15},".NET","dotnet",{"name":1436,"slug":1427,"type":15},"ASP.NET Core",{"name":1438,"slug":1439,"type":15},"Blazor","blazor",{"name":1441,"slug":1442,"type":15},"C#","csharp",{"name":1444,"slug":1445,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1450,"name":1450,"fn":1451,"description":1452,"org":1453,"tags":1454,"stars":1446,"repoUrl":1447,"updatedAt":1465},"chatgpt-apps","build ChatGPT Apps SDK applications","Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1455,1458,1461,1464],{"name":1456,"slug":1457,"type":15},"Apps SDK","apps-sdk",{"name":1459,"slug":1460,"type":15},"ChatGPT","chatgpt",{"name":1462,"slug":1463,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1467,"name":1467,"fn":1468,"description":1469,"org":1470,"tags":1471,"stars":1446,"repoUrl":1447,"updatedAt":1481},"cli-creator","build CLIs from API docs","Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1472,1475,1478],{"name":1473,"slug":1474,"type":15},"API Development","api-development",{"name":1476,"slug":1477,"type":15},"CLI","cli",{"name":1479,"slug":1480,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1483,"name":1483,"fn":1484,"description":1485,"org":1486,"tags":1487,"stars":1446,"repoUrl":1447,"updatedAt":1498},"cloudflare-deploy","deploy projects to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1488,1491,1494,1495],{"name":1489,"slug":1490,"type":15},"Cloudflare","cloudflare",{"name":1492,"slug":1493,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1336,"slug":1337,"type":15},{"name":1496,"slug":1497,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1500,"name":1500,"fn":1501,"description":1502,"org":1503,"tags":1504,"stars":1446,"repoUrl":1447,"updatedAt":1517},"define-goal","define and set measurable project goals","Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1505,1508,1511,1514],{"name":1506,"slug":1507,"type":15},"Productivity","productivity",{"name":1509,"slug":1510,"type":15},"Project Management","project-management",{"name":1512,"slug":1513,"type":15},"Strategy","strategy",{"name":1515,"slug":1516,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1519,"name":1519,"fn":1520,"description":1521,"org":1522,"tags":1523,"stars":1446,"repoUrl":1447,"updatedAt":1529},"figma","translate Figma designs into code","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1524,1525,1527,1528],{"name":1299,"slug":1300,"type":15},{"name":1526,"slug":1519,"type":15},"Figma",{"name":1355,"slug":1356,"type":15},{"name":1462,"slug":1463,"type":15},"2026-04-12T05:06:47.939943",{"slug":1531,"name":1531,"fn":1532,"description":1533,"org":1534,"tags":1535,"stars":1446,"repoUrl":1447,"updatedAt":1543},"figma-code-connect-components","connect Figma designs to code components","Connects Figma design components to code components using Code Connect mapping tools. Use when user says \"code connect\", \"connect this component to code\", \"map this component\", \"link component to code\", \"create code connect mapping\", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1536,1537,1540,1541,1542],{"name":1299,"slug":1300,"type":15},{"name":1538,"slug":1539,"type":15},"Design System","design-system",{"name":1526,"slug":1519,"type":15},{"name":1355,"slug":1356,"type":15},{"name":1364,"slug":1365,"type":15},"2026-05-10T05:59:52.971881",{"slug":1545,"name":1545,"fn":1546,"description":1547,"org":1548,"tags":1549,"stars":1446,"repoUrl":1447,"updatedAt":1557},"figma-create-design-system-rules","generate design system rules from Figma","Generates custom design system rules for the user's codebase. Use when user says \"create design system rules\", \"generate rules for my project\", \"set up design rules\", \"customize design system guidelines\", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1550,1551,1552,1555,1556],{"name":1299,"slug":1300,"type":15},{"name":1538,"slug":1539,"type":15},{"name":1553,"slug":1554,"type":15},"Documentation","documentation",{"name":1526,"slug":1519,"type":15},{"name":1355,"slug":1356,"type":15},"2026-05-16T06:07:47.821474",{"slug":1559,"name":1559,"fn":1560,"description":1561,"org":1562,"tags":1563,"stars":1446,"repoUrl":1447,"updatedAt":1569},"figma-implement-design","translate Figma designs into application code","Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions \"implement design\", \"generate code\", \"implement component\", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1564,1565,1566,1567,1568],{"name":1299,"slug":1300,"type":15},{"name":1526,"slug":1519,"type":15},{"name":1355,"slug":1356,"type":15},{"name":1364,"slug":1365,"type":15},{"name":1444,"slug":1445,"type":15},"2026-05-16T06:07:40.583615",{"slug":1571,"name":1571,"fn":1572,"description":1573,"org":1574,"tags":1575,"stars":1446,"repoUrl":1447,"updatedAt":1584},"hatch-pet","create animated pets for Codex","Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1576,1579,1580,1583],{"name":1577,"slug":1578,"type":15},"Animation","animation",{"name":1479,"slug":1480,"type":15},{"name":1581,"slug":1582,"type":15},"Creative","creative",{"name":1299,"slug":1300,"type":15},"2026-05-02T05:31:48.48485",{"slug":1586,"name":1586,"fn":1587,"description":1588,"org":1589,"tags":1590,"stars":1446,"repoUrl":1447,"updatedAt":1600},"imagegen","generate and edit raster images","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1591,1592,1593,1596,1599],{"name":1581,"slug":1582,"type":15},{"name":1299,"slug":1300,"type":15},{"name":1594,"slug":1595,"type":15},"Image Generation","image-generation",{"name":1597,"slug":1598,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]