[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-dispatching-parallel-agents":3,"mdc--gnsd5j-key":33,"related-org-openai-dispatching-parallel-agents":1153,"related-repo-openai-dispatching-parallel-agents":1358},{"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},"dispatching-parallel-agents","dispatch parallel agents for independent tasks","Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies",{"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},"Productivity","productivity","tag",{"name":17,"slug":18,"type":15},"Agents","agents",{"name":20,"slug":21,"type":15},"Multi-Agent","multi-agent",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-04-16T05:11:57.688245",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\u002Fdispatching-parallel-agents","---\nname: dispatching-parallel-agents\ndescription: Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies\n---\n\n# Dispatching Parallel Agents\n\n## Overview\n\nYou 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\nWhen you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.\n\n**Core principle:** Dispatch one agent per independent problem domain. Let them work concurrently.\n\n## When to Use\n\n```dot\ndigraph when_to_use {\n    \"Multiple failures?\" [shape=diamond];\n    \"Are they independent?\" [shape=diamond];\n    \"Single agent investigates all\" [shape=box];\n    \"One agent per problem domain\" [shape=box];\n    \"Can they work in parallel?\" [shape=diamond];\n    \"Sequential agents\" [shape=box];\n    \"Parallel dispatch\" [shape=box];\n\n    \"Multiple failures?\" -> \"Are they independent?\" [label=\"yes\"];\n    \"Are they independent?\" -> \"Single agent investigates all\" [label=\"no - related\"];\n    \"Are they independent?\" -> \"Can they work in parallel?\" [label=\"yes\"];\n    \"Can they work in parallel?\" -> \"Parallel dispatch\" [label=\"yes\"];\n    \"Can they work in parallel?\" -> \"Sequential agents\" [label=\"no - shared state\"];\n}\n```\n\n**Use when:**\n- 3+ test files failing with different root causes\n- Multiple subsystems broken independently\n- Each problem can be understood without context from others\n- No shared state between investigations\n\n**Don't use when:**\n- Failures are related (fix one might fix others)\n- Need to understand full system state\n- Agents would interfere with each other\n\n## The Pattern\n\n### 1. Identify Independent Domains\n\nGroup failures by what's broken:\n- File A tests: Tool approval flow\n- File B tests: Batch completion behavior\n- File C tests: Abort functionality\n\nEach domain is independent - fixing tool approval doesn't affect abort tests.\n\n### 2. Create Focused Agent Tasks\n\nEach agent gets:\n- **Specific scope:** One test file or subsystem\n- **Clear goal:** Make these tests pass\n- **Constraints:** Don't change other code\n- **Expected output:** Summary of what you found and fixed\n\n### 3. Dispatch in Parallel\n\n```typescript\n\u002F\u002F In Claude Code \u002F AI environment\nTask(\"Fix agent-tool-abort.test.ts failures\")\nTask(\"Fix batch-completion-behavior.test.ts failures\")\nTask(\"Fix tool-approval-race-conditions.test.ts failures\")\n\u002F\u002F All three run concurrently\n```\n\n### 4. Review and Integrate\n\nWhen agents return:\n- Read each summary\n- Verify fixes don't conflict\n- Run full test suite\n- Integrate all changes\n\n## Agent Prompt Structure\n\nGood agent prompts are:\n1. **Focused** - One clear problem domain\n2. **Self-contained** - All context needed to understand the problem\n3. **Specific about output** - What should the agent return?\n\n```markdown\nFix the 3 failing tests in src\u002Fagents\u002Fagent-tool-abort.test.ts:\n\n1. \"should abort tool with partial output capture\" - expects 'interrupted at' in message\n2. \"should handle mixed completed and aborted tools\" - fast tool aborted instead of completed\n3. \"should properly track pendingToolCount\" - expects 3 results but gets 0\n\nThese are timing\u002Frace condition issues. Your task:\n\n1. Read the test file and understand what each test verifies\n2. Identify root cause - timing issues or actual bugs?\n3. Fix by:\n   - Replacing arbitrary timeouts with event-based waiting\n   - Fixing bugs in abort implementation if found\n   - Adjusting test expectations if testing changed behavior\n\nDo NOT just increase timeouts - find the real issue.\n\nReturn: Summary of what you found and what you fixed.\n```\n\n## Common Mistakes\n\n**❌ Too broad:** \"Fix all the tests\" - agent gets lost\n**✅ Specific:** \"Fix agent-tool-abort.test.ts\" - focused scope\n\n**❌ No context:** \"Fix the race condition\" - agent doesn't know where\n**✅ Context:** Paste the error messages and test names\n\n**❌ No constraints:** Agent might refactor everything\n**✅ Constraints:** \"Do NOT change production code\" or \"Fix tests only\"\n\n**❌ Vague output:** \"Fix it\" - you don't know what changed\n**✅ Specific:** \"Return summary of root cause and changes\"\n\n## When NOT to Use\n\n**Related failures:** Fixing one might fix others - investigate together first\n**Need full context:** Understanding requires seeing entire system\n**Exploratory debugging:** You don't know what's broken yet\n**Shared state:** Agents would interfere (editing same files, using same resources)\n\n## Real Example from Session\n\n**Scenario:** 6 test failures across 3 files after major refactoring\n\n**Failures:**\n- agent-tool-abort.test.ts: 3 failures (timing issues)\n- batch-completion-behavior.test.ts: 2 failures (tools not executing)\n- tool-approval-race-conditions.test.ts: 1 failure (execution count = 0)\n\n**Decision:** Independent domains - abort logic separate from batch completion separate from race conditions\n\n**Dispatch:**\n```\nAgent 1 → Fix agent-tool-abort.test.ts\nAgent 2 → Fix batch-completion-behavior.test.ts\nAgent 3 → Fix tool-approval-race-conditions.test.ts\n```\n\n**Results:**\n- Agent 1: Replaced timeouts with event-based waiting\n- Agent 2: Fixed event structure bug (threadId in wrong place)\n- Agent 3: Added wait for async tool execution to complete\n\n**Integration:** All fixes independent, no conflicts, full suite green\n\n**Time saved:** 3 problems solved in parallel vs sequentially\n\n## Key Benefits\n\n1. **Parallelization** - Multiple investigations happen simultaneously\n2. **Focus** - Each agent has narrow scope, less context to track\n3. **Independence** - Agents don't interfere with each other\n4. **Speed** - 3 problems solved in time of 1\n\n## Verification\n\nAfter agents return:\n1. **Review each summary** - Understand what changed\n2. **Check for conflicts** - Did agents edit same code?\n3. **Run full suite** - Verify all fixes work together\n4. **Spot check** - Agents can make systematic errors\n\n## Real-World Impact\n\nFrom debugging session (2025-10-03):\n- 6 failures across 3 files\n- 3 agents dispatched in parallel\n- All investigations completed concurrently\n- All fixes integrated successfully\n- Zero conflicts between agent changes\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,46,53,59,64,75,81,231,239,264,272,290,296,303,308,326,331,337,342,385,391,509,515,520,543,549,554,588,779,785,802,819,836,852,858,889,895,905,913,931,941,949,959,967,985,995,1005,1011,1054,1060,1065,1108,1114,1119,1147],{"type":39,"tag":40,"props":41,"children":42},"element","h1",{"id":4},[43],{"type":44,"value":45},"text","Dispatching Parallel Agents",{"type":39,"tag":47,"props":48,"children":50},"h2",{"id":49},"overview",[51],{"type":44,"value":52},"Overview",{"type":39,"tag":54,"props":55,"children":56},"p",{},[57],{"type":44,"value":58},"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":54,"props":60,"children":61},{},[62],{"type":44,"value":63},"When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.",{"type":39,"tag":54,"props":65,"children":66},{},[67,73],{"type":39,"tag":68,"props":69,"children":70},"strong",{},[71],{"type":44,"value":72},"Core principle:",{"type":44,"value":74}," Dispatch one agent per independent problem domain. Let them work concurrently.",{"type":39,"tag":47,"props":76,"children":78},{"id":77},"when-to-use",[79],{"type":44,"value":80},"When to Use",{"type":39,"tag":82,"props":83,"children":88},"pre",{"className":84,"code":85,"language":86,"meta":87,"style":87},"language-dot shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","digraph when_to_use {\n    \"Multiple failures?\" [shape=diamond];\n    \"Are they independent?\" [shape=diamond];\n    \"Single agent investigates all\" [shape=box];\n    \"One agent per problem domain\" [shape=box];\n    \"Can they work in parallel?\" [shape=diamond];\n    \"Sequential agents\" [shape=box];\n    \"Parallel dispatch\" [shape=box];\n\n    \"Multiple failures?\" -> \"Are they independent?\" [label=\"yes\"];\n    \"Are they independent?\" -> \"Single agent investigates all\" [label=\"no - related\"];\n    \"Are they independent?\" -> \"Can they work in parallel?\" [label=\"yes\"];\n    \"Can they work in parallel?\" -> \"Parallel dispatch\" [label=\"yes\"];\n    \"Can they work in parallel?\" -> \"Sequential agents\" [label=\"no - shared state\"];\n}\n","dot","",[89],{"type":39,"tag":90,"props":91,"children":92},"code",{"__ignoreMap":87},[93,104,113,122,131,140,149,158,167,177,186,195,204,213,222],{"type":39,"tag":94,"props":95,"children":98},"span",{"class":96,"line":97},"line",1,[99],{"type":39,"tag":94,"props":100,"children":101},{},[102],{"type":44,"value":103},"digraph when_to_use {\n",{"type":39,"tag":94,"props":105,"children":107},{"class":96,"line":106},2,[108],{"type":39,"tag":94,"props":109,"children":110},{},[111],{"type":44,"value":112},"    \"Multiple failures?\" [shape=diamond];\n",{"type":39,"tag":94,"props":114,"children":116},{"class":96,"line":115},3,[117],{"type":39,"tag":94,"props":118,"children":119},{},[120],{"type":44,"value":121},"    \"Are they independent?\" [shape=diamond];\n",{"type":39,"tag":94,"props":123,"children":125},{"class":96,"line":124},4,[126],{"type":39,"tag":94,"props":127,"children":128},{},[129],{"type":44,"value":130},"    \"Single agent investigates all\" [shape=box];\n",{"type":39,"tag":94,"props":132,"children":134},{"class":96,"line":133},5,[135],{"type":39,"tag":94,"props":136,"children":137},{},[138],{"type":44,"value":139},"    \"One agent per problem domain\" [shape=box];\n",{"type":39,"tag":94,"props":141,"children":143},{"class":96,"line":142},6,[144],{"type":39,"tag":94,"props":145,"children":146},{},[147],{"type":44,"value":148},"    \"Can they work in parallel?\" [shape=diamond];\n",{"type":39,"tag":94,"props":150,"children":152},{"class":96,"line":151},7,[153],{"type":39,"tag":94,"props":154,"children":155},{},[156],{"type":44,"value":157},"    \"Sequential agents\" [shape=box];\n",{"type":39,"tag":94,"props":159,"children":161},{"class":96,"line":160},8,[162],{"type":39,"tag":94,"props":163,"children":164},{},[165],{"type":44,"value":166},"    \"Parallel dispatch\" [shape=box];\n",{"type":39,"tag":94,"props":168,"children":170},{"class":96,"line":169},9,[171],{"type":39,"tag":94,"props":172,"children":174},{"emptyLinePlaceholder":173},true,[175],{"type":44,"value":176},"\n",{"type":39,"tag":94,"props":178,"children":180},{"class":96,"line":179},10,[181],{"type":39,"tag":94,"props":182,"children":183},{},[184],{"type":44,"value":185},"    \"Multiple failures?\" -> \"Are they independent?\" [label=\"yes\"];\n",{"type":39,"tag":94,"props":187,"children":189},{"class":96,"line":188},11,[190],{"type":39,"tag":94,"props":191,"children":192},{},[193],{"type":44,"value":194},"    \"Are they independent?\" -> \"Single agent investigates all\" [label=\"no - related\"];\n",{"type":39,"tag":94,"props":196,"children":198},{"class":96,"line":197},12,[199],{"type":39,"tag":94,"props":200,"children":201},{},[202],{"type":44,"value":203},"    \"Are they independent?\" -> \"Can they work in parallel?\" [label=\"yes\"];\n",{"type":39,"tag":94,"props":205,"children":207},{"class":96,"line":206},13,[208],{"type":39,"tag":94,"props":209,"children":210},{},[211],{"type":44,"value":212},"    \"Can they work in parallel?\" -> \"Parallel dispatch\" [label=\"yes\"];\n",{"type":39,"tag":94,"props":214,"children":216},{"class":96,"line":215},14,[217],{"type":39,"tag":94,"props":218,"children":219},{},[220],{"type":44,"value":221},"    \"Can they work in parallel?\" -> \"Sequential agents\" [label=\"no - shared state\"];\n",{"type":39,"tag":94,"props":223,"children":225},{"class":96,"line":224},15,[226],{"type":39,"tag":94,"props":227,"children":228},{},[229],{"type":44,"value":230},"}\n",{"type":39,"tag":54,"props":232,"children":233},{},[234],{"type":39,"tag":68,"props":235,"children":236},{},[237],{"type":44,"value":238},"Use when:",{"type":39,"tag":240,"props":241,"children":242},"ul",{},[243,249,254,259],{"type":39,"tag":244,"props":245,"children":246},"li",{},[247],{"type":44,"value":248},"3+ test files failing with different root causes",{"type":39,"tag":244,"props":250,"children":251},{},[252],{"type":44,"value":253},"Multiple subsystems broken independently",{"type":39,"tag":244,"props":255,"children":256},{},[257],{"type":44,"value":258},"Each problem can be understood without context from others",{"type":39,"tag":244,"props":260,"children":261},{},[262],{"type":44,"value":263},"No shared state between investigations",{"type":39,"tag":54,"props":265,"children":266},{},[267],{"type":39,"tag":68,"props":268,"children":269},{},[270],{"type":44,"value":271},"Don't use when:",{"type":39,"tag":240,"props":273,"children":274},{},[275,280,285],{"type":39,"tag":244,"props":276,"children":277},{},[278],{"type":44,"value":279},"Failures are related (fix one might fix others)",{"type":39,"tag":244,"props":281,"children":282},{},[283],{"type":44,"value":284},"Need to understand full system state",{"type":39,"tag":244,"props":286,"children":287},{},[288],{"type":44,"value":289},"Agents would interfere with each other",{"type":39,"tag":47,"props":291,"children":293},{"id":292},"the-pattern",[294],{"type":44,"value":295},"The Pattern",{"type":39,"tag":297,"props":298,"children":300},"h3",{"id":299},"_1-identify-independent-domains",[301],{"type":44,"value":302},"1. Identify Independent Domains",{"type":39,"tag":54,"props":304,"children":305},{},[306],{"type":44,"value":307},"Group failures by what's broken:",{"type":39,"tag":240,"props":309,"children":310},{},[311,316,321],{"type":39,"tag":244,"props":312,"children":313},{},[314],{"type":44,"value":315},"File A tests: Tool approval flow",{"type":39,"tag":244,"props":317,"children":318},{},[319],{"type":44,"value":320},"File B tests: Batch completion behavior",{"type":39,"tag":244,"props":322,"children":323},{},[324],{"type":44,"value":325},"File C tests: Abort functionality",{"type":39,"tag":54,"props":327,"children":328},{},[329],{"type":44,"value":330},"Each domain is independent - fixing tool approval doesn't affect abort tests.",{"type":39,"tag":297,"props":332,"children":334},{"id":333},"_2-create-focused-agent-tasks",[335],{"type":44,"value":336},"2. Create Focused Agent Tasks",{"type":39,"tag":54,"props":338,"children":339},{},[340],{"type":44,"value":341},"Each agent gets:",{"type":39,"tag":240,"props":343,"children":344},{},[345,355,365,375],{"type":39,"tag":244,"props":346,"children":347},{},[348,353],{"type":39,"tag":68,"props":349,"children":350},{},[351],{"type":44,"value":352},"Specific scope:",{"type":44,"value":354}," One test file or subsystem",{"type":39,"tag":244,"props":356,"children":357},{},[358,363],{"type":39,"tag":68,"props":359,"children":360},{},[361],{"type":44,"value":362},"Clear goal:",{"type":44,"value":364}," Make these tests pass",{"type":39,"tag":244,"props":366,"children":367},{},[368,373],{"type":39,"tag":68,"props":369,"children":370},{},[371],{"type":44,"value":372},"Constraints:",{"type":44,"value":374}," Don't change other code",{"type":39,"tag":244,"props":376,"children":377},{},[378,383],{"type":39,"tag":68,"props":379,"children":380},{},[381],{"type":44,"value":382},"Expected output:",{"type":44,"value":384}," Summary of what you found and fixed",{"type":39,"tag":297,"props":386,"children":388},{"id":387},"_3-dispatch-in-parallel",[389],{"type":44,"value":390},"3. Dispatch in Parallel",{"type":39,"tag":82,"props":392,"children":396},{"className":393,"code":394,"language":395,"meta":87,"style":87},"language-typescript shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","\u002F\u002F In Claude Code \u002F AI environment\nTask(\"Fix agent-tool-abort.test.ts failures\")\nTask(\"Fix batch-completion-behavior.test.ts failures\")\nTask(\"Fix tool-approval-race-conditions.test.ts failures\")\n\u002F\u002F All three run concurrently\n","typescript",[397],{"type":39,"tag":90,"props":398,"children":399},{"__ignoreMap":87},[400,409,445,473,501],{"type":39,"tag":94,"props":401,"children":402},{"class":96,"line":97},[403],{"type":39,"tag":94,"props":404,"children":406},{"style":405},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[407],{"type":44,"value":408},"\u002F\u002F In Claude Code \u002F AI environment\n",{"type":39,"tag":94,"props":410,"children":411},{"class":96,"line":106},[412,418,424,430,436,440],{"type":39,"tag":94,"props":413,"children":415},{"style":414},"--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF",[416],{"type":44,"value":417},"Task",{"type":39,"tag":94,"props":419,"children":421},{"style":420},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[422],{"type":44,"value":423},"(",{"type":39,"tag":94,"props":425,"children":427},{"style":426},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[428],{"type":44,"value":429},"\"",{"type":39,"tag":94,"props":431,"children":433},{"style":432},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[434],{"type":44,"value":435},"Fix agent-tool-abort.test.ts failures",{"type":39,"tag":94,"props":437,"children":438},{"style":426},[439],{"type":44,"value":429},{"type":39,"tag":94,"props":441,"children":442},{"style":420},[443],{"type":44,"value":444},")\n",{"type":39,"tag":94,"props":446,"children":447},{"class":96,"line":115},[448,452,456,460,465,469],{"type":39,"tag":94,"props":449,"children":450},{"style":414},[451],{"type":44,"value":417},{"type":39,"tag":94,"props":453,"children":454},{"style":420},[455],{"type":44,"value":423},{"type":39,"tag":94,"props":457,"children":458},{"style":426},[459],{"type":44,"value":429},{"type":39,"tag":94,"props":461,"children":462},{"style":432},[463],{"type":44,"value":464},"Fix batch-completion-behavior.test.ts failures",{"type":39,"tag":94,"props":466,"children":467},{"style":426},[468],{"type":44,"value":429},{"type":39,"tag":94,"props":470,"children":471},{"style":420},[472],{"type":44,"value":444},{"type":39,"tag":94,"props":474,"children":475},{"class":96,"line":124},[476,480,484,488,493,497],{"type":39,"tag":94,"props":477,"children":478},{"style":414},[479],{"type":44,"value":417},{"type":39,"tag":94,"props":481,"children":482},{"style":420},[483],{"type":44,"value":423},{"type":39,"tag":94,"props":485,"children":486},{"style":426},[487],{"type":44,"value":429},{"type":39,"tag":94,"props":489,"children":490},{"style":432},[491],{"type":44,"value":492},"Fix tool-approval-race-conditions.test.ts failures",{"type":39,"tag":94,"props":494,"children":495},{"style":426},[496],{"type":44,"value":429},{"type":39,"tag":94,"props":498,"children":499},{"style":420},[500],{"type":44,"value":444},{"type":39,"tag":94,"props":502,"children":503},{"class":96,"line":133},[504],{"type":39,"tag":94,"props":505,"children":506},{"style":405},[507],{"type":44,"value":508},"\u002F\u002F All three run concurrently\n",{"type":39,"tag":297,"props":510,"children":512},{"id":511},"_4-review-and-integrate",[513],{"type":44,"value":514},"4. Review and Integrate",{"type":39,"tag":54,"props":516,"children":517},{},[518],{"type":44,"value":519},"When agents return:",{"type":39,"tag":240,"props":521,"children":522},{},[523,528,533,538],{"type":39,"tag":244,"props":524,"children":525},{},[526],{"type":44,"value":527},"Read each summary",{"type":39,"tag":244,"props":529,"children":530},{},[531],{"type":44,"value":532},"Verify fixes don't conflict",{"type":39,"tag":244,"props":534,"children":535},{},[536],{"type":44,"value":537},"Run full test suite",{"type":39,"tag":244,"props":539,"children":540},{},[541],{"type":44,"value":542},"Integrate all changes",{"type":39,"tag":47,"props":544,"children":546},{"id":545},"agent-prompt-structure",[547],{"type":44,"value":548},"Agent Prompt Structure",{"type":39,"tag":54,"props":550,"children":551},{},[552],{"type":44,"value":553},"Good agent prompts are:",{"type":39,"tag":555,"props":556,"children":557},"ol",{},[558,568,578],{"type":39,"tag":244,"props":559,"children":560},{},[561,566],{"type":39,"tag":68,"props":562,"children":563},{},[564],{"type":44,"value":565},"Focused",{"type":44,"value":567}," - One clear problem domain",{"type":39,"tag":244,"props":569,"children":570},{},[571,576],{"type":39,"tag":68,"props":572,"children":573},{},[574],{"type":44,"value":575},"Self-contained",{"type":44,"value":577}," - All context needed to understand the problem",{"type":39,"tag":244,"props":579,"children":580},{},[581,586],{"type":39,"tag":68,"props":582,"children":583},{},[584],{"type":44,"value":585},"Specific about output",{"type":44,"value":587}," - What should the agent return?",{"type":39,"tag":82,"props":589,"children":593},{"className":590,"code":591,"language":592,"meta":87,"style":87},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","Fix the 3 failing tests in src\u002Fagents\u002Fagent-tool-abort.test.ts:\n\n1. \"should abort tool with partial output capture\" - expects 'interrupted at' in message\n2. \"should handle mixed completed and aborted tools\" - fast tool aborted instead of completed\n3. \"should properly track pendingToolCount\" - expects 3 results but gets 0\n\nThese are timing\u002Frace condition issues. Your task:\n\n1. Read the test file and understand what each test verifies\n2. Identify root cause - timing issues or actual bugs?\n3. Fix by:\n   - Replacing arbitrary timeouts with event-based waiting\n   - Fixing bugs in abort implementation if found\n   - Adjusting test expectations if testing changed behavior\n\nDo NOT just increase timeouts - find the real issue.\n\nReturn: Summary of what you found and what you fixed.\n","markdown",[594],{"type":39,"tag":90,"props":595,"children":596},{"__ignoreMap":87},[597,605,612,625,638,651,658,666,673,685,697,709,722,734,746,753,762,770],{"type":39,"tag":94,"props":598,"children":599},{"class":96,"line":97},[600],{"type":39,"tag":94,"props":601,"children":602},{"style":420},[603],{"type":44,"value":604},"Fix the 3 failing tests in src\u002Fagents\u002Fagent-tool-abort.test.ts:\n",{"type":39,"tag":94,"props":606,"children":607},{"class":96,"line":106},[608],{"type":39,"tag":94,"props":609,"children":610},{"emptyLinePlaceholder":173},[611],{"type":44,"value":176},{"type":39,"tag":94,"props":613,"children":614},{"class":96,"line":115},[615,620],{"type":39,"tag":94,"props":616,"children":617},{"style":426},[618],{"type":44,"value":619},"1.",{"type":39,"tag":94,"props":621,"children":622},{"style":420},[623],{"type":44,"value":624}," \"should abort tool with partial output capture\" - expects 'interrupted at' in message\n",{"type":39,"tag":94,"props":626,"children":627},{"class":96,"line":124},[628,633],{"type":39,"tag":94,"props":629,"children":630},{"style":426},[631],{"type":44,"value":632},"2.",{"type":39,"tag":94,"props":634,"children":635},{"style":420},[636],{"type":44,"value":637}," \"should handle mixed completed and aborted tools\" - fast tool aborted instead of completed\n",{"type":39,"tag":94,"props":639,"children":640},{"class":96,"line":133},[641,646],{"type":39,"tag":94,"props":642,"children":643},{"style":426},[644],{"type":44,"value":645},"3.",{"type":39,"tag":94,"props":647,"children":648},{"style":420},[649],{"type":44,"value":650}," \"should properly track pendingToolCount\" - expects 3 results but gets 0\n",{"type":39,"tag":94,"props":652,"children":653},{"class":96,"line":142},[654],{"type":39,"tag":94,"props":655,"children":656},{"emptyLinePlaceholder":173},[657],{"type":44,"value":176},{"type":39,"tag":94,"props":659,"children":660},{"class":96,"line":151},[661],{"type":39,"tag":94,"props":662,"children":663},{"style":420},[664],{"type":44,"value":665},"These are timing\u002Frace condition issues. Your task:\n",{"type":39,"tag":94,"props":667,"children":668},{"class":96,"line":160},[669],{"type":39,"tag":94,"props":670,"children":671},{"emptyLinePlaceholder":173},[672],{"type":44,"value":176},{"type":39,"tag":94,"props":674,"children":675},{"class":96,"line":169},[676,680],{"type":39,"tag":94,"props":677,"children":678},{"style":426},[679],{"type":44,"value":619},{"type":39,"tag":94,"props":681,"children":682},{"style":420},[683],{"type":44,"value":684}," Read the test file and understand what each test verifies\n",{"type":39,"tag":94,"props":686,"children":687},{"class":96,"line":179},[688,692],{"type":39,"tag":94,"props":689,"children":690},{"style":426},[691],{"type":44,"value":632},{"type":39,"tag":94,"props":693,"children":694},{"style":420},[695],{"type":44,"value":696}," Identify root cause - timing issues or actual bugs?\n",{"type":39,"tag":94,"props":698,"children":699},{"class":96,"line":188},[700,704],{"type":39,"tag":94,"props":701,"children":702},{"style":426},[703],{"type":44,"value":645},{"type":39,"tag":94,"props":705,"children":706},{"style":420},[707],{"type":44,"value":708}," Fix by:\n",{"type":39,"tag":94,"props":710,"children":711},{"class":96,"line":197},[712,717],{"type":39,"tag":94,"props":713,"children":714},{"style":426},[715],{"type":44,"value":716},"   -",{"type":39,"tag":94,"props":718,"children":719},{"style":420},[720],{"type":44,"value":721}," Replacing arbitrary timeouts with event-based waiting\n",{"type":39,"tag":94,"props":723,"children":724},{"class":96,"line":206},[725,729],{"type":39,"tag":94,"props":726,"children":727},{"style":426},[728],{"type":44,"value":716},{"type":39,"tag":94,"props":730,"children":731},{"style":420},[732],{"type":44,"value":733}," Fixing bugs in abort implementation if found\n",{"type":39,"tag":94,"props":735,"children":736},{"class":96,"line":215},[737,741],{"type":39,"tag":94,"props":738,"children":739},{"style":426},[740],{"type":44,"value":716},{"type":39,"tag":94,"props":742,"children":743},{"style":420},[744],{"type":44,"value":745}," Adjusting test expectations if testing changed behavior\n",{"type":39,"tag":94,"props":747,"children":748},{"class":96,"line":224},[749],{"type":39,"tag":94,"props":750,"children":751},{"emptyLinePlaceholder":173},[752],{"type":44,"value":176},{"type":39,"tag":94,"props":754,"children":756},{"class":96,"line":755},16,[757],{"type":39,"tag":94,"props":758,"children":759},{"style":420},[760],{"type":44,"value":761},"Do NOT just increase timeouts - find the real issue.\n",{"type":39,"tag":94,"props":763,"children":765},{"class":96,"line":764},17,[766],{"type":39,"tag":94,"props":767,"children":768},{"emptyLinePlaceholder":173},[769],{"type":44,"value":176},{"type":39,"tag":94,"props":771,"children":773},{"class":96,"line":772},18,[774],{"type":39,"tag":94,"props":775,"children":776},{"style":420},[777],{"type":44,"value":778},"Return: Summary of what you found and what you fixed.\n",{"type":39,"tag":47,"props":780,"children":782},{"id":781},"common-mistakes",[783],{"type":44,"value":784},"Common Mistakes",{"type":39,"tag":54,"props":786,"children":787},{},[788,793,795,800],{"type":39,"tag":68,"props":789,"children":790},{},[791],{"type":44,"value":792},"❌ Too broad:",{"type":44,"value":794}," \"Fix all the tests\" - agent gets lost\n",{"type":39,"tag":68,"props":796,"children":797},{},[798],{"type":44,"value":799},"✅ Specific:",{"type":44,"value":801}," \"Fix agent-tool-abort.test.ts\" - focused scope",{"type":39,"tag":54,"props":803,"children":804},{},[805,810,812,817],{"type":39,"tag":68,"props":806,"children":807},{},[808],{"type":44,"value":809},"❌ No context:",{"type":44,"value":811}," \"Fix the race condition\" - agent doesn't know where\n",{"type":39,"tag":68,"props":813,"children":814},{},[815],{"type":44,"value":816},"✅ Context:",{"type":44,"value":818}," Paste the error messages and test names",{"type":39,"tag":54,"props":820,"children":821},{},[822,827,829,834],{"type":39,"tag":68,"props":823,"children":824},{},[825],{"type":44,"value":826},"❌ No constraints:",{"type":44,"value":828}," Agent might refactor everything\n",{"type":39,"tag":68,"props":830,"children":831},{},[832],{"type":44,"value":833},"✅ Constraints:",{"type":44,"value":835}," \"Do NOT change production code\" or \"Fix tests only\"",{"type":39,"tag":54,"props":837,"children":838},{},[839,844,846,850],{"type":39,"tag":68,"props":840,"children":841},{},[842],{"type":44,"value":843},"❌ Vague output:",{"type":44,"value":845}," \"Fix it\" - you don't know what changed\n",{"type":39,"tag":68,"props":847,"children":848},{},[849],{"type":44,"value":799},{"type":44,"value":851}," \"Return summary of root cause and changes\"",{"type":39,"tag":47,"props":853,"children":855},{"id":854},"when-not-to-use",[856],{"type":44,"value":857},"When NOT to Use",{"type":39,"tag":54,"props":859,"children":860},{},[861,866,868,873,875,880,882,887],{"type":39,"tag":68,"props":862,"children":863},{},[864],{"type":44,"value":865},"Related failures:",{"type":44,"value":867}," Fixing one might fix others - investigate together first\n",{"type":39,"tag":68,"props":869,"children":870},{},[871],{"type":44,"value":872},"Need full context:",{"type":44,"value":874}," Understanding requires seeing entire system\n",{"type":39,"tag":68,"props":876,"children":877},{},[878],{"type":44,"value":879},"Exploratory debugging:",{"type":44,"value":881}," You don't know what's broken yet\n",{"type":39,"tag":68,"props":883,"children":884},{},[885],{"type":44,"value":886},"Shared state:",{"type":44,"value":888}," Agents would interfere (editing same files, using same resources)",{"type":39,"tag":47,"props":890,"children":892},{"id":891},"real-example-from-session",[893],{"type":44,"value":894},"Real Example from Session",{"type":39,"tag":54,"props":896,"children":897},{},[898,903],{"type":39,"tag":68,"props":899,"children":900},{},[901],{"type":44,"value":902},"Scenario:",{"type":44,"value":904}," 6 test failures across 3 files after major refactoring",{"type":39,"tag":54,"props":906,"children":907},{},[908],{"type":39,"tag":68,"props":909,"children":910},{},[911],{"type":44,"value":912},"Failures:",{"type":39,"tag":240,"props":914,"children":915},{},[916,921,926],{"type":39,"tag":244,"props":917,"children":918},{},[919],{"type":44,"value":920},"agent-tool-abort.test.ts: 3 failures (timing issues)",{"type":39,"tag":244,"props":922,"children":923},{},[924],{"type":44,"value":925},"batch-completion-behavior.test.ts: 2 failures (tools not executing)",{"type":39,"tag":244,"props":927,"children":928},{},[929],{"type":44,"value":930},"tool-approval-race-conditions.test.ts: 1 failure (execution count = 0)",{"type":39,"tag":54,"props":932,"children":933},{},[934,939],{"type":39,"tag":68,"props":935,"children":936},{},[937],{"type":44,"value":938},"Decision:",{"type":44,"value":940}," Independent domains - abort logic separate from batch completion separate from race conditions",{"type":39,"tag":54,"props":942,"children":943},{},[944],{"type":39,"tag":68,"props":945,"children":946},{},[947],{"type":44,"value":948},"Dispatch:",{"type":39,"tag":82,"props":950,"children":954},{"className":951,"code":953,"language":44},[952],"language-text","Agent 1 → Fix agent-tool-abort.test.ts\nAgent 2 → Fix batch-completion-behavior.test.ts\nAgent 3 → Fix tool-approval-race-conditions.test.ts\n",[955],{"type":39,"tag":90,"props":956,"children":957},{"__ignoreMap":87},[958],{"type":44,"value":953},{"type":39,"tag":54,"props":960,"children":961},{},[962],{"type":39,"tag":68,"props":963,"children":964},{},[965],{"type":44,"value":966},"Results:",{"type":39,"tag":240,"props":968,"children":969},{},[970,975,980],{"type":39,"tag":244,"props":971,"children":972},{},[973],{"type":44,"value":974},"Agent 1: Replaced timeouts with event-based waiting",{"type":39,"tag":244,"props":976,"children":977},{},[978],{"type":44,"value":979},"Agent 2: Fixed event structure bug (threadId in wrong place)",{"type":39,"tag":244,"props":981,"children":982},{},[983],{"type":44,"value":984},"Agent 3: Added wait for async tool execution to complete",{"type":39,"tag":54,"props":986,"children":987},{},[988,993],{"type":39,"tag":68,"props":989,"children":990},{},[991],{"type":44,"value":992},"Integration:",{"type":44,"value":994}," All fixes independent, no conflicts, full suite green",{"type":39,"tag":54,"props":996,"children":997},{},[998,1003],{"type":39,"tag":68,"props":999,"children":1000},{},[1001],{"type":44,"value":1002},"Time saved:",{"type":44,"value":1004}," 3 problems solved in parallel vs sequentially",{"type":39,"tag":47,"props":1006,"children":1008},{"id":1007},"key-benefits",[1009],{"type":44,"value":1010},"Key Benefits",{"type":39,"tag":555,"props":1012,"children":1013},{},[1014,1024,1034,1044],{"type":39,"tag":244,"props":1015,"children":1016},{},[1017,1022],{"type":39,"tag":68,"props":1018,"children":1019},{},[1020],{"type":44,"value":1021},"Parallelization",{"type":44,"value":1023}," - Multiple investigations happen simultaneously",{"type":39,"tag":244,"props":1025,"children":1026},{},[1027,1032],{"type":39,"tag":68,"props":1028,"children":1029},{},[1030],{"type":44,"value":1031},"Focus",{"type":44,"value":1033}," - Each agent has narrow scope, less context to track",{"type":39,"tag":244,"props":1035,"children":1036},{},[1037,1042],{"type":39,"tag":68,"props":1038,"children":1039},{},[1040],{"type":44,"value":1041},"Independence",{"type":44,"value":1043}," - Agents don't interfere with each other",{"type":39,"tag":244,"props":1045,"children":1046},{},[1047,1052],{"type":39,"tag":68,"props":1048,"children":1049},{},[1050],{"type":44,"value":1051},"Speed",{"type":44,"value":1053}," - 3 problems solved in time of 1",{"type":39,"tag":47,"props":1055,"children":1057},{"id":1056},"verification",[1058],{"type":44,"value":1059},"Verification",{"type":39,"tag":54,"props":1061,"children":1062},{},[1063],{"type":44,"value":1064},"After agents return:",{"type":39,"tag":555,"props":1066,"children":1067},{},[1068,1078,1088,1098],{"type":39,"tag":244,"props":1069,"children":1070},{},[1071,1076],{"type":39,"tag":68,"props":1072,"children":1073},{},[1074],{"type":44,"value":1075},"Review each summary",{"type":44,"value":1077}," - Understand what changed",{"type":39,"tag":244,"props":1079,"children":1080},{},[1081,1086],{"type":39,"tag":68,"props":1082,"children":1083},{},[1084],{"type":44,"value":1085},"Check for conflicts",{"type":44,"value":1087}," - Did agents edit same code?",{"type":39,"tag":244,"props":1089,"children":1090},{},[1091,1096],{"type":39,"tag":68,"props":1092,"children":1093},{},[1094],{"type":44,"value":1095},"Run full suite",{"type":44,"value":1097}," - Verify all fixes work together",{"type":39,"tag":244,"props":1099,"children":1100},{},[1101,1106],{"type":39,"tag":68,"props":1102,"children":1103},{},[1104],{"type":44,"value":1105},"Spot check",{"type":44,"value":1107}," - Agents can make systematic errors",{"type":39,"tag":47,"props":1109,"children":1111},{"id":1110},"real-world-impact",[1112],{"type":44,"value":1113},"Real-World Impact",{"type":39,"tag":54,"props":1115,"children":1116},{},[1117],{"type":44,"value":1118},"From debugging session (2025-10-03):",{"type":39,"tag":240,"props":1120,"children":1121},{},[1122,1127,1132,1137,1142],{"type":39,"tag":244,"props":1123,"children":1124},{},[1125],{"type":44,"value":1126},"6 failures across 3 files",{"type":39,"tag":244,"props":1128,"children":1129},{},[1130],{"type":44,"value":1131},"3 agents dispatched in parallel",{"type":39,"tag":244,"props":1133,"children":1134},{},[1135],{"type":44,"value":1136},"All investigations completed concurrently",{"type":39,"tag":244,"props":1138,"children":1139},{},[1140],{"type":44,"value":1141},"All fixes integrated successfully",{"type":39,"tag":244,"props":1143,"children":1144},{},[1145],{"type":44,"value":1146},"Zero conflicts between agent changes",{"type":39,"tag":1148,"props":1149,"children":1150},"style",{},[1151],{"type":44,"value":1152},"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":1154,"total":1357},[1155,1176,1199,1216,1232,1251,1268,1284,1300,1314,1326,1341],{"slug":1156,"name":1156,"fn":1157,"description":1158,"org":1159,"tags":1160,"stars":1173,"repoUrl":1174,"updatedAt":1175},"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},[1161,1164,1167,1170],{"name":1162,"slug":1163,"type":15},"Documents","documents",{"name":1165,"slug":1166,"type":15},"Healthcare","healthcare",{"name":1168,"slug":1169,"type":15},"Insurance","insurance",{"name":1171,"slug":1172,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":1177,"name":1177,"fn":1178,"description":1179,"org":1180,"tags":1181,"stars":1196,"repoUrl":1197,"updatedAt":1198},"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},[1182,1185,1187,1190,1193],{"name":1183,"slug":1184,"type":15},".NET","dotnet",{"name":1186,"slug":1177,"type":15},"ASP.NET Core",{"name":1188,"slug":1189,"type":15},"Blazor","blazor",{"name":1191,"slug":1192,"type":15},"C#","csharp",{"name":1194,"slug":1195,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1200,"name":1200,"fn":1201,"description":1202,"org":1203,"tags":1204,"stars":1196,"repoUrl":1197,"updatedAt":1215},"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},[1205,1208,1211,1214],{"name":1206,"slug":1207,"type":15},"Apps SDK","apps-sdk",{"name":1209,"slug":1210,"type":15},"ChatGPT","chatgpt",{"name":1212,"slug":1213,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1217,"name":1217,"fn":1218,"description":1219,"org":1220,"tags":1221,"stars":1196,"repoUrl":1197,"updatedAt":1231},"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},[1222,1225,1228],{"name":1223,"slug":1224,"type":15},"API Development","api-development",{"name":1226,"slug":1227,"type":15},"CLI","cli",{"name":1229,"slug":1230,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1233,"name":1233,"fn":1234,"description":1235,"org":1236,"tags":1237,"stars":1196,"repoUrl":1197,"updatedAt":1250},"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},[1238,1241,1244,1247],{"name":1239,"slug":1240,"type":15},"Cloudflare","cloudflare",{"name":1242,"slug":1243,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1245,"slug":1246,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1248,"slug":1249,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1252,"name":1252,"fn":1253,"description":1254,"org":1255,"tags":1256,"stars":1196,"repoUrl":1197,"updatedAt":1267},"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},[1257,1258,1261,1264],{"name":13,"slug":14,"type":15},{"name":1259,"slug":1260,"type":15},"Project Management","project-management",{"name":1262,"slug":1263,"type":15},"Strategy","strategy",{"name":1265,"slug":1266,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1269,"name":1269,"fn":1270,"description":1271,"org":1272,"tags":1273,"stars":1196,"repoUrl":1197,"updatedAt":1283},"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},[1274,1277,1279,1282],{"name":1275,"slug":1276,"type":15},"Design","design",{"name":1278,"slug":1269,"type":15},"Figma",{"name":1280,"slug":1281,"type":15},"Frontend","frontend",{"name":1212,"slug":1213,"type":15},"2026-04-12T05:06:47.939943",{"slug":1285,"name":1285,"fn":1286,"description":1287,"org":1288,"tags":1289,"stars":1196,"repoUrl":1197,"updatedAt":1299},"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},[1290,1291,1294,1295,1296],{"name":1275,"slug":1276,"type":15},{"name":1292,"slug":1293,"type":15},"Design System","design-system",{"name":1278,"slug":1269,"type":15},{"name":1280,"slug":1281,"type":15},{"name":1297,"slug":1298,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":1301,"name":1301,"fn":1302,"description":1303,"org":1304,"tags":1305,"stars":1196,"repoUrl":1197,"updatedAt":1313},"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},[1306,1307,1308,1311,1312],{"name":1275,"slug":1276,"type":15},{"name":1292,"slug":1293,"type":15},{"name":1309,"slug":1310,"type":15},"Documentation","documentation",{"name":1278,"slug":1269,"type":15},{"name":1280,"slug":1281,"type":15},"2026-05-16T06:07:47.821474",{"slug":1315,"name":1315,"fn":1316,"description":1317,"org":1318,"tags":1319,"stars":1196,"repoUrl":1197,"updatedAt":1325},"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},[1320,1321,1322,1323,1324],{"name":1275,"slug":1276,"type":15},{"name":1278,"slug":1269,"type":15},{"name":1280,"slug":1281,"type":15},{"name":1297,"slug":1298,"type":15},{"name":1194,"slug":1195,"type":15},"2026-05-16T06:07:40.583615",{"slug":1327,"name":1327,"fn":1328,"description":1329,"org":1330,"tags":1331,"stars":1196,"repoUrl":1197,"updatedAt":1340},"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},[1332,1335,1336,1339],{"name":1333,"slug":1334,"type":15},"Animation","animation",{"name":1229,"slug":1230,"type":15},{"name":1337,"slug":1338,"type":15},"Creative","creative",{"name":1275,"slug":1276,"type":15},"2026-05-02T05:31:48.48485",{"slug":1342,"name":1342,"fn":1343,"description":1344,"org":1345,"tags":1346,"stars":1196,"repoUrl":1197,"updatedAt":1356},"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},[1347,1348,1349,1352,1355],{"name":1337,"slug":1338,"type":15},{"name":1275,"slug":1276,"type":15},{"name":1350,"slug":1351,"type":15},"Image Generation","image-generation",{"name":1353,"slug":1354,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675,{"items":1359,"total":1471},[1360,1377,1391,1403,1421,1439,1459],{"slug":1361,"name":1361,"fn":1362,"description":1363,"org":1364,"tags":1365,"stars":22,"repoUrl":23,"updatedAt":1376},"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},[1366,1369,1372,1375],{"name":1367,"slug":1368,"type":15},"Accessibility","accessibility",{"name":1370,"slug":1371,"type":15},"Charts","charts",{"name":1373,"slug":1374,"type":15},"Data Visualization","data-visualization",{"name":1275,"slug":1276,"type":15},"2026-06-30T19:00:57.102",{"slug":1378,"name":1378,"fn":1379,"description":1380,"org":1381,"tags":1382,"stars":22,"repoUrl":23,"updatedAt":1390},"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},[1383,1384,1387],{"name":17,"slug":18,"type":15},{"name":1385,"slug":1386,"type":15},"Browser Automation","browser-automation",{"name":1388,"slug":1389,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":1392,"name":1392,"fn":1393,"description":1394,"org":1395,"tags":1396,"stars":22,"repoUrl":23,"updatedAt":1402},"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},[1397,1398,1401],{"name":1385,"slug":1386,"type":15},{"name":1399,"slug":1400,"type":15},"Local Development","local-development",{"name":1388,"slug":1389,"type":15},"2026-04-06T18:41:17.526867",{"slug":1404,"name":1404,"fn":1405,"description":1406,"org":1407,"tags":1408,"stars":22,"repoUrl":23,"updatedAt":1420},"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},[1409,1410,1411,1414,1417],{"name":17,"slug":18,"type":15},{"name":1245,"slug":1246,"type":15},{"name":1412,"slug":1413,"type":15},"SDK","sdk",{"name":1415,"slug":1416,"type":15},"Serverless","serverless",{"name":1418,"slug":1419,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":1422,"name":1422,"fn":1423,"description":1424,"org":1425,"tags":1426,"stars":22,"repoUrl":23,"updatedAt":1438},"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},[1427,1428,1431,1434,1435],{"name":1280,"slug":1281,"type":15},{"name":1429,"slug":1430,"type":15},"React","react",{"name":1432,"slug":1433,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":1297,"slug":1298,"type":15},{"name":1436,"slug":1437,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":1440,"name":1440,"fn":1441,"description":1442,"org":1443,"tags":1444,"stars":22,"repoUrl":23,"updatedAt":1458},"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},[1445,1448,1451,1454,1457],{"name":1446,"slug":1447,"type":15},"AI Infrastructure","ai-infrastructure",{"name":1449,"slug":1450,"type":15},"Cost Optimization","cost-optimization",{"name":1452,"slug":1453,"type":15},"LLM","llm",{"name":1455,"slug":1456,"type":15},"Performance","performance",{"name":1436,"slug":1437,"type":15},"2026-04-06T18:40:44.377464",{"slug":1460,"name":1460,"fn":1461,"description":1462,"org":1463,"tags":1464,"stars":22,"repoUrl":23,"updatedAt":1470},"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},[1465,1466,1469],{"name":1449,"slug":1450,"type":15},{"name":1467,"slug":1468,"type":15},"Database","database",{"name":1452,"slug":1453,"type":15},"2026-04-06T18:41:08.513425",600]