[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-writing-plans":3,"mdc-zfcblm-key":33,"related-repo-openai-writing-plans":1236,"related-org-openai-writing-plans":1360},{"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},"writing-plans","create implementation plans for complex tasks","Use when you have a spec or requirements for a multi-step task, before touching code",{"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},"Architecture","architecture",{"name":20,"slug":21,"type":15},"Engineering","engineering",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-04-16T05:11:48.231175",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\u002Fwriting-plans","---\nname: writing-plans\ndescription: Use when you have a spec or requirements for a multi-step task, before touching code\n---\n\n# Writing Plans\n\n## Overview\n\nWrite comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.\n\nAssume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.\n\n**Announce at start:** \"I'm using the writing-plans skill to create the implementation plan.\"\n\n**Context:** If working in an isolated worktree, it should have been created via the `superpowers:using-git-worktrees` skill at execution time.\n\n**Save plans to:** `docs\u002Fsuperpowers\u002Fplans\u002FYYYY-MM-DD-\u003Cfeature-name>.md`\n- (User preferences for plan location override this default)\n\n## Scope Check\n\nIf the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.\n\n## File Structure\n\nBefore defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.\n\n- Design units with clear boundaries and well-defined interfaces. Each file should have one clear responsibility.\n- You reason best about code you can hold in context at once, and your edits are more reliable when files are focused. Prefer smaller, focused files over large ones that do too much.\n- Files that change together should live together. Split by responsibility, not by technical layer.\n- In existing codebases, follow established patterns. If the codebase uses large files, don't unilaterally restructure - but if a file you're modifying has grown unwieldy, including a split in the plan is reasonable.\n\nThis structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.\n\n## Bite-Sized Task Granularity\n\n**Each step is one action (2-5 minutes):**\n- \"Write the failing test\" - step\n- \"Run it to make sure it fails\" - step\n- \"Implement the minimal code to make the test pass\" - step\n- \"Run the tests and make sure they pass\" - step\n- \"Commit\" - step\n\n## Plan Document Header\n\n**Every plan MUST start with this header:**\n\n```markdown\n# [Feature Name] Implementation Plan\n\n> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.\n\n**Goal:** [One sentence describing what this builds]\n\n**Architecture:** [2-3 sentences about approach]\n\n**Tech Stack:** [Key technologies\u002Flibraries]\n\n---\n```\n\n## Task Structure\n\n````markdown\n### Task N: [Component Name]\n\n**Files:**\n- Create: `exact\u002Fpath\u002Fto\u002Ffile.py`\n- Modify: `exact\u002Fpath\u002Fto\u002Fexisting.py:123-145`\n- Test: `tests\u002Fexact\u002Fpath\u002Fto\u002Ftest.py`\n\n- [ ] **Step 1: Write the failing test**\n\n```python\ndef test_specific_behavior():\n    result = function(input)\n    assert result == expected\n```\n\n- [ ] **Step 2: Run test to verify it fails**\n\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_name -v`\nExpected: FAIL with \"function not defined\"\n\n- [ ] **Step 3: Write minimal implementation**\n\n```python\ndef function(input):\n    return expected\n```\n\n- [ ] **Step 4: Run test to verify it passes**\n\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_name -v`\nExpected: PASS\n\n- [ ] **Step 5: Commit**\n\n```bash\ngit add tests\u002Fpath\u002Ftest.py src\u002Fpath\u002Ffile.py\ngit commit -m \"feat: add specific feature\"\n```\n````\n\n## No Placeholders\n\nEvery step must contain the actual content an engineer needs. These are **plan failures** — never write them:\n- \"TBD\", \"TODO\", \"implement later\", \"fill in details\"\n- \"Add appropriate error handling\" \u002F \"add validation\" \u002F \"handle edge cases\"\n- \"Write tests for the above\" (without actual test code)\n- \"Similar to Task N\" (repeat the code — the engineer may be reading tasks out of order)\n- Steps that describe what to do without showing how (code blocks required for code steps)\n- References to types, functions, or methods not defined in any task\n\n## Remember\n- Exact file paths always\n- Complete code in every step — if a step changes code, show the code\n- Exact commands with expected output\n- DRY, YAGNI, TDD, frequent commits\n\n## Self-Review\n\nAfter writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.\n\n**1. Spec coverage:** Skim each section\u002Frequirement in the spec. Can you point to a task that implements it? List any gaps.\n\n**2. Placeholder scan:** Search your plan for red flags — any of the patterns from the \"No Placeholders\" section above. Fix them.\n\n**3. Type consistency:** Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called `clearLayers()` in Task 3 but `clearFullLayers()` in Task 7 is a bug.\n\nIf you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.\n\n## Execution Handoff\n\nAfter saving the plan, offer execution choice:\n\n**\"Plan complete and saved to `docs\u002Fsuperpowers\u002Fplans\u002F\u003Cfilename>.md`. Two execution options:**\n\n**1. Subagent-Driven (recommended)** - I dispatch a fresh subagent per task, review between tasks, fast iteration\n\n**2. Inline Execution** - Execute tasks in this session using executing-plans, batch execution with checkpoints\n\n**Which approach?\"**\n\n**If Subagent-Driven chosen:**\n- **REQUIRED SUB-SKILL:** Use superpowers:subagent-driven-development\n- Fresh subagent per task + two-stage review\n\n**If Inline Execution chosen:**\n- **REQUIRED SUB-SKILL:** Use superpowers:executing-plans\n- Batch execution with checkpoints for review\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,46,53,59,64,75,94,110,120,126,131,137,142,165,170,176,184,212,218,226,426,432,982,988,1000,1033,1039,1062,1068,1073,1083,1093,1119,1124,1130,1135,1151,1161,1171,1179,1187,1205,1213,1230],{"type":39,"tag":40,"props":41,"children":42},"element","h1",{"id":4},[43],{"type":44,"value":45},"text","Writing Plans",{"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},"Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.",{"type":39,"tag":54,"props":60,"children":61},{},[62],{"type":44,"value":63},"Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.",{"type":39,"tag":54,"props":65,"children":66},{},[67,73],{"type":39,"tag":68,"props":69,"children":70},"strong",{},[71],{"type":44,"value":72},"Announce at start:",{"type":44,"value":74}," \"I'm using the writing-plans skill to create the implementation plan.\"",{"type":39,"tag":54,"props":76,"children":77},{},[78,83,85,92],{"type":39,"tag":68,"props":79,"children":80},{},[81],{"type":44,"value":82},"Context:",{"type":44,"value":84}," If working in an isolated worktree, it should have been created via the ",{"type":39,"tag":86,"props":87,"children":89},"code",{"className":88},[],[90],{"type":44,"value":91},"superpowers:using-git-worktrees",{"type":44,"value":93}," skill at execution time.",{"type":39,"tag":54,"props":95,"children":96},{},[97,102,104],{"type":39,"tag":68,"props":98,"children":99},{},[100],{"type":44,"value":101},"Save plans to:",{"type":44,"value":103}," ",{"type":39,"tag":86,"props":105,"children":107},{"className":106},[],[108],{"type":44,"value":109},"docs\u002Fsuperpowers\u002Fplans\u002FYYYY-MM-DD-\u003Cfeature-name>.md",{"type":39,"tag":111,"props":112,"children":113},"ul",{},[114],{"type":39,"tag":115,"props":116,"children":117},"li",{},[118],{"type":44,"value":119},"(User preferences for plan location override this default)",{"type":39,"tag":47,"props":121,"children":123},{"id":122},"scope-check",[124],{"type":44,"value":125},"Scope Check",{"type":39,"tag":54,"props":127,"children":128},{},[129],{"type":44,"value":130},"If the spec covers multiple independent subsystems, it should have been broken into sub-project specs during brainstorming. If it wasn't, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.",{"type":39,"tag":47,"props":132,"children":134},{"id":133},"file-structure",[135],{"type":44,"value":136},"File Structure",{"type":39,"tag":54,"props":138,"children":139},{},[140],{"type":44,"value":141},"Before defining tasks, map out which files will be created or modified and what each one is responsible for. This is where decomposition decisions get locked in.",{"type":39,"tag":111,"props":143,"children":144},{},[145,150,155,160],{"type":39,"tag":115,"props":146,"children":147},{},[148],{"type":44,"value":149},"Design units with clear boundaries and well-defined interfaces. Each file should have one clear responsibility.",{"type":39,"tag":115,"props":151,"children":152},{},[153],{"type":44,"value":154},"You reason best about code you can hold in context at once, and your edits are more reliable when files are focused. Prefer smaller, focused files over large ones that do too much.",{"type":39,"tag":115,"props":156,"children":157},{},[158],{"type":44,"value":159},"Files that change together should live together. Split by responsibility, not by technical layer.",{"type":39,"tag":115,"props":161,"children":162},{},[163],{"type":44,"value":164},"In existing codebases, follow established patterns. If the codebase uses large files, don't unilaterally restructure - but if a file you're modifying has grown unwieldy, including a split in the plan is reasonable.",{"type":39,"tag":54,"props":166,"children":167},{},[168],{"type":44,"value":169},"This structure informs the task decomposition. Each task should produce self-contained changes that make sense independently.",{"type":39,"tag":47,"props":171,"children":173},{"id":172},"bite-sized-task-granularity",[174],{"type":44,"value":175},"Bite-Sized Task Granularity",{"type":39,"tag":54,"props":177,"children":178},{},[179],{"type":39,"tag":68,"props":180,"children":181},{},[182],{"type":44,"value":183},"Each step is one action (2-5 minutes):",{"type":39,"tag":111,"props":185,"children":186},{},[187,192,197,202,207],{"type":39,"tag":115,"props":188,"children":189},{},[190],{"type":44,"value":191},"\"Write the failing test\" - step",{"type":39,"tag":115,"props":193,"children":194},{},[195],{"type":44,"value":196},"\"Run it to make sure it fails\" - step",{"type":39,"tag":115,"props":198,"children":199},{},[200],{"type":44,"value":201},"\"Implement the minimal code to make the test pass\" - step",{"type":39,"tag":115,"props":203,"children":204},{},[205],{"type":44,"value":206},"\"Run the tests and make sure they pass\" - step",{"type":39,"tag":115,"props":208,"children":209},{},[210],{"type":44,"value":211},"\"Commit\" - step",{"type":39,"tag":47,"props":213,"children":215},{"id":214},"plan-document-header",[216],{"type":44,"value":217},"Plan Document Header",{"type":39,"tag":54,"props":219,"children":220},{},[221],{"type":39,"tag":68,"props":222,"children":223},{},[224],{"type":44,"value":225},"Every plan MUST start with this header:",{"type":39,"tag":227,"props":228,"children":233},"pre",{"className":229,"code":230,"language":231,"meta":232,"style":232},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# [Feature Name] Implementation Plan\n\n> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.\n\n**Goal:** [One sentence describing what this builds]\n\n**Architecture:** [2-3 sentences about approach]\n\n**Tech Stack:** [Key technologies\u002Flibraries]\n\n---\n","markdown","",[234],{"type":39,"tag":86,"props":235,"children":236},{"__ignoreMap":232},[237,255,265,318,326,349,357,379,387,409,417],{"type":39,"tag":238,"props":239,"children":242},"span",{"class":240,"line":241},"line",1,[243,249],{"type":39,"tag":238,"props":244,"children":246},{"style":245},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[247],{"type":44,"value":248},"# ",{"type":39,"tag":238,"props":250,"children":252},{"style":251},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[253],{"type":44,"value":254},"[Feature Name] Implementation Plan\n",{"type":39,"tag":238,"props":256,"children":258},{"class":240,"line":257},2,[259],{"type":39,"tag":238,"props":260,"children":262},{"emptyLinePlaceholder":261},true,[263],{"type":44,"value":264},"\n",{"type":39,"tag":238,"props":266,"children":268},{"class":240,"line":267},3,[269,275,281,287,292,298,303,309,313],{"type":39,"tag":238,"props":270,"children":272},{"style":271},"--shiki-light:#FF5370;--shiki-light-font-style:italic;--shiki-default:#FF9CAC;--shiki-default-font-style:italic;--shiki-dark:#FF9CAC;--shiki-dark-font-style:italic",[273],{"type":44,"value":274},">",{"type":39,"tag":238,"props":276,"children":278},{"style":277},"--shiki-light:#39ADB5;--shiki-light-font-weight:bold;--shiki-default:#89DDFF;--shiki-default-font-weight:bold;--shiki-dark:#89DDFF;--shiki-dark-font-weight:bold",[279],{"type":44,"value":280}," **",{"type":39,"tag":238,"props":282,"children":284},{"style":283},"--shiki-light:#E53935;--shiki-light-font-weight:bold;--shiki-default:#F07178;--shiki-default-font-weight:bold;--shiki-dark:#F07178;--shiki-dark-font-weight:bold",[285],{"type":44,"value":286},"For agentic workers:",{"type":39,"tag":238,"props":288,"children":289},{"style":277},[290],{"type":44,"value":291},"**",{"type":39,"tag":238,"props":293,"children":295},{"style":294},"--shiki-light:#39ADB5;--shiki-light-font-style:italic;--shiki-default:#89DDFF;--shiki-default-font-style:italic;--shiki-dark:#89DDFF;--shiki-dark-font-style:italic",[296],{"type":44,"value":297}," REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (",{"type":39,"tag":238,"props":299,"children":300},{"style":294},[301],{"type":44,"value":302},"`",{"type":39,"tag":238,"props":304,"children":306},{"style":305},"--shiki-light:#91B859;--shiki-light-font-style:italic;--shiki-default:#C3E88D;--shiki-default-font-style:italic;--shiki-dark:#C3E88D;--shiki-dark-font-style:italic",[307],{"type":44,"value":308},"- [ ]",{"type":39,"tag":238,"props":310,"children":311},{"style":294},[312],{"type":44,"value":302},{"type":39,"tag":238,"props":314,"children":315},{"style":294},[316],{"type":44,"value":317},") syntax for tracking.\n",{"type":39,"tag":238,"props":319,"children":321},{"class":240,"line":320},4,[322],{"type":39,"tag":238,"props":323,"children":324},{"emptyLinePlaceholder":261},[325],{"type":44,"value":264},{"type":39,"tag":238,"props":327,"children":329},{"class":240,"line":328},5,[330,334,339,343],{"type":39,"tag":238,"props":331,"children":332},{"style":277},[333],{"type":44,"value":291},{"type":39,"tag":238,"props":335,"children":336},{"style":283},[337],{"type":44,"value":338},"Goal:",{"type":39,"tag":238,"props":340,"children":341},{"style":277},[342],{"type":44,"value":291},{"type":39,"tag":238,"props":344,"children":346},{"style":345},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[347],{"type":44,"value":348}," [One sentence describing what this builds]\n",{"type":39,"tag":238,"props":350,"children":352},{"class":240,"line":351},6,[353],{"type":39,"tag":238,"props":354,"children":355},{"emptyLinePlaceholder":261},[356],{"type":44,"value":264},{"type":39,"tag":238,"props":358,"children":360},{"class":240,"line":359},7,[361,365,370,374],{"type":39,"tag":238,"props":362,"children":363},{"style":277},[364],{"type":44,"value":291},{"type":39,"tag":238,"props":366,"children":367},{"style":283},[368],{"type":44,"value":369},"Architecture:",{"type":39,"tag":238,"props":371,"children":372},{"style":277},[373],{"type":44,"value":291},{"type":39,"tag":238,"props":375,"children":376},{"style":345},[377],{"type":44,"value":378}," [2-3 sentences about approach]\n",{"type":39,"tag":238,"props":380,"children":382},{"class":240,"line":381},8,[383],{"type":39,"tag":238,"props":384,"children":385},{"emptyLinePlaceholder":261},[386],{"type":44,"value":264},{"type":39,"tag":238,"props":388,"children":390},{"class":240,"line":389},9,[391,395,400,404],{"type":39,"tag":238,"props":392,"children":393},{"style":277},[394],{"type":44,"value":291},{"type":39,"tag":238,"props":396,"children":397},{"style":283},[398],{"type":44,"value":399},"Tech Stack:",{"type":39,"tag":238,"props":401,"children":402},{"style":277},[403],{"type":44,"value":291},{"type":39,"tag":238,"props":405,"children":406},{"style":345},[407],{"type":44,"value":408}," [Key technologies\u002Flibraries]\n",{"type":39,"tag":238,"props":410,"children":412},{"class":240,"line":411},10,[413],{"type":39,"tag":238,"props":414,"children":415},{"emptyLinePlaceholder":261},[416],{"type":44,"value":264},{"type":39,"tag":238,"props":418,"children":420},{"class":240,"line":419},11,[421],{"type":39,"tag":238,"props":422,"children":423},{"style":245},[424],{"type":44,"value":425},"---\n",{"type":39,"tag":47,"props":427,"children":429},{"id":428},"task-structure",[430],{"type":44,"value":431},"Task Structure",{"type":39,"tag":227,"props":433,"children":435},{"className":229,"code":434,"language":231,"meta":232,"style":232},"### Task N: [Component Name]\n\n**Files:**\n- Create: `exact\u002Fpath\u002Fto\u002Ffile.py`\n- Modify: `exact\u002Fpath\u002Fto\u002Fexisting.py:123-145`\n- Test: `tests\u002Fexact\u002Fpath\u002Fto\u002Ftest.py`\n\n- [ ] **Step 1: Write the failing test**\n\n```python\ndef test_specific_behavior():\n    result = function(input)\n    assert result == expected\n```\n\n- [ ] **Step 2: Run test to verify it fails**\n\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_name -v`\nExpected: FAIL with \"function not defined\"\n\n- [ ] **Step 3: Write minimal implementation**\n\n```python\ndef function(input):\n    return expected\n```\n\n- [ ] **Step 4: Run test to verify it passes**\n\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_name -v`\nExpected: PASS\n\n- [ ] **Step 5: Commit**\n\n```bash\ngit add tests\u002Fpath\u002Ftest.py src\u002Fpath\u002Ffile.py\ngit commit -m \"feat: add specific feature\"\n```\n",[436],{"type":39,"tag":86,"props":437,"children":438},{"__ignoreMap":232},[439,452,459,476,504,529,554,561,586,593,607,615,624,633,642,650,675,683,705,714,722,747,755,767,776,785,793,801,826,834,854,863,871,896,904,917,941,974],{"type":39,"tag":238,"props":440,"children":441},{"class":240,"line":241},[442,447],{"type":39,"tag":238,"props":443,"children":444},{"style":245},[445],{"type":44,"value":446},"### ",{"type":39,"tag":238,"props":448,"children":449},{"style":251},[450],{"type":44,"value":451},"Task N: [Component Name]\n",{"type":39,"tag":238,"props":453,"children":454},{"class":240,"line":257},[455],{"type":39,"tag":238,"props":456,"children":457},{"emptyLinePlaceholder":261},[458],{"type":44,"value":264},{"type":39,"tag":238,"props":460,"children":461},{"class":240,"line":267},[462,466,471],{"type":39,"tag":238,"props":463,"children":464},{"style":277},[465],{"type":44,"value":291},{"type":39,"tag":238,"props":467,"children":468},{"style":283},[469],{"type":44,"value":470},"Files:",{"type":39,"tag":238,"props":472,"children":473},{"style":277},[474],{"type":44,"value":475},"**\n",{"type":39,"tag":238,"props":477,"children":478},{"class":240,"line":320},[479,484,489,493,499],{"type":39,"tag":238,"props":480,"children":481},{"style":245},[482],{"type":44,"value":483},"-",{"type":39,"tag":238,"props":485,"children":486},{"style":345},[487],{"type":44,"value":488}," Create: ",{"type":39,"tag":238,"props":490,"children":491},{"style":245},[492],{"type":44,"value":302},{"type":39,"tag":238,"props":494,"children":496},{"style":495},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[497],{"type":44,"value":498},"exact\u002Fpath\u002Fto\u002Ffile.py",{"type":39,"tag":238,"props":500,"children":501},{"style":245},[502],{"type":44,"value":503},"`\n",{"type":39,"tag":238,"props":505,"children":506},{"class":240,"line":328},[507,511,516,520,525],{"type":39,"tag":238,"props":508,"children":509},{"style":245},[510],{"type":44,"value":483},{"type":39,"tag":238,"props":512,"children":513},{"style":345},[514],{"type":44,"value":515}," Modify: ",{"type":39,"tag":238,"props":517,"children":518},{"style":245},[519],{"type":44,"value":302},{"type":39,"tag":238,"props":521,"children":522},{"style":495},[523],{"type":44,"value":524},"exact\u002Fpath\u002Fto\u002Fexisting.py:123-145",{"type":39,"tag":238,"props":526,"children":527},{"style":245},[528],{"type":44,"value":503},{"type":39,"tag":238,"props":530,"children":531},{"class":240,"line":351},[532,536,541,545,550],{"type":39,"tag":238,"props":533,"children":534},{"style":245},[535],{"type":44,"value":483},{"type":39,"tag":238,"props":537,"children":538},{"style":345},[539],{"type":44,"value":540}," Test: ",{"type":39,"tag":238,"props":542,"children":543},{"style":245},[544],{"type":44,"value":302},{"type":39,"tag":238,"props":546,"children":547},{"style":495},[548],{"type":44,"value":549},"tests\u002Fexact\u002Fpath\u002Fto\u002Ftest.py",{"type":39,"tag":238,"props":551,"children":552},{"style":245},[553],{"type":44,"value":503},{"type":39,"tag":238,"props":555,"children":556},{"class":240,"line":359},[557],{"type":39,"tag":238,"props":558,"children":559},{"emptyLinePlaceholder":261},[560],{"type":44,"value":264},{"type":39,"tag":238,"props":562,"children":563},{"class":240,"line":381},[564,568,573,577,582],{"type":39,"tag":238,"props":565,"children":566},{"style":245},[567],{"type":44,"value":483},{"type":39,"tag":238,"props":569,"children":570},{"style":345},[571],{"type":44,"value":572}," [ ] ",{"type":39,"tag":238,"props":574,"children":575},{"style":277},[576],{"type":44,"value":291},{"type":39,"tag":238,"props":578,"children":579},{"style":283},[580],{"type":44,"value":581},"Step 1: Write the failing test",{"type":39,"tag":238,"props":583,"children":584},{"style":277},[585],{"type":44,"value":475},{"type":39,"tag":238,"props":587,"children":588},{"class":240,"line":389},[589],{"type":39,"tag":238,"props":590,"children":591},{"emptyLinePlaceholder":261},[592],{"type":44,"value":264},{"type":39,"tag":238,"props":594,"children":595},{"class":240,"line":411},[596,601],{"type":39,"tag":238,"props":597,"children":598},{"style":495},[599],{"type":44,"value":600},"```",{"type":39,"tag":238,"props":602,"children":604},{"style":603},"--shiki-light:#90A4AE90;--shiki-default:#EEFFFF90;--shiki-dark:#BABED890",[605],{"type":44,"value":606},"python\n",{"type":39,"tag":238,"props":608,"children":609},{"class":240,"line":419},[610],{"type":39,"tag":238,"props":611,"children":612},{"style":603},[613],{"type":44,"value":614},"def test_specific_behavior():\n",{"type":39,"tag":238,"props":616,"children":618},{"class":240,"line":617},12,[619],{"type":39,"tag":238,"props":620,"children":621},{"style":603},[622],{"type":44,"value":623},"    result = function(input)\n",{"type":39,"tag":238,"props":625,"children":627},{"class":240,"line":626},13,[628],{"type":39,"tag":238,"props":629,"children":630},{"style":603},[631],{"type":44,"value":632},"    assert result == expected\n",{"type":39,"tag":238,"props":634,"children":636},{"class":240,"line":635},14,[637],{"type":39,"tag":238,"props":638,"children":639},{"style":495},[640],{"type":44,"value":641},"```\n",{"type":39,"tag":238,"props":643,"children":645},{"class":240,"line":644},15,[646],{"type":39,"tag":238,"props":647,"children":648},{"emptyLinePlaceholder":261},[649],{"type":44,"value":264},{"type":39,"tag":238,"props":651,"children":653},{"class":240,"line":652},16,[654,658,662,666,671],{"type":39,"tag":238,"props":655,"children":656},{"style":245},[657],{"type":44,"value":483},{"type":39,"tag":238,"props":659,"children":660},{"style":345},[661],{"type":44,"value":572},{"type":39,"tag":238,"props":663,"children":664},{"style":277},[665],{"type":44,"value":291},{"type":39,"tag":238,"props":667,"children":668},{"style":283},[669],{"type":44,"value":670},"Step 2: Run test to verify it fails",{"type":39,"tag":238,"props":672,"children":673},{"style":277},[674],{"type":44,"value":475},{"type":39,"tag":238,"props":676,"children":678},{"class":240,"line":677},17,[679],{"type":39,"tag":238,"props":680,"children":681},{"emptyLinePlaceholder":261},[682],{"type":44,"value":264},{"type":39,"tag":238,"props":684,"children":686},{"class":240,"line":685},18,[687,692,696,701],{"type":39,"tag":238,"props":688,"children":689},{"style":345},[690],{"type":44,"value":691},"Run: ",{"type":39,"tag":238,"props":693,"children":694},{"style":245},[695],{"type":44,"value":302},{"type":39,"tag":238,"props":697,"children":698},{"style":495},[699],{"type":44,"value":700},"pytest tests\u002Fpath\u002Ftest.py::test_name -v",{"type":39,"tag":238,"props":702,"children":703},{"style":245},[704],{"type":44,"value":503},{"type":39,"tag":238,"props":706,"children":708},{"class":240,"line":707},19,[709],{"type":39,"tag":238,"props":710,"children":711},{"style":345},[712],{"type":44,"value":713},"Expected: FAIL with \"function not defined\"\n",{"type":39,"tag":238,"props":715,"children":717},{"class":240,"line":716},20,[718],{"type":39,"tag":238,"props":719,"children":720},{"emptyLinePlaceholder":261},[721],{"type":44,"value":264},{"type":39,"tag":238,"props":723,"children":725},{"class":240,"line":724},21,[726,730,734,738,743],{"type":39,"tag":238,"props":727,"children":728},{"style":245},[729],{"type":44,"value":483},{"type":39,"tag":238,"props":731,"children":732},{"style":345},[733],{"type":44,"value":572},{"type":39,"tag":238,"props":735,"children":736},{"style":277},[737],{"type":44,"value":291},{"type":39,"tag":238,"props":739,"children":740},{"style":283},[741],{"type":44,"value":742},"Step 3: Write minimal implementation",{"type":39,"tag":238,"props":744,"children":745},{"style":277},[746],{"type":44,"value":475},{"type":39,"tag":238,"props":748,"children":750},{"class":240,"line":749},22,[751],{"type":39,"tag":238,"props":752,"children":753},{"emptyLinePlaceholder":261},[754],{"type":44,"value":264},{"type":39,"tag":238,"props":756,"children":758},{"class":240,"line":757},23,[759,763],{"type":39,"tag":238,"props":760,"children":761},{"style":495},[762],{"type":44,"value":600},{"type":39,"tag":238,"props":764,"children":765},{"style":603},[766],{"type":44,"value":606},{"type":39,"tag":238,"props":768,"children":770},{"class":240,"line":769},24,[771],{"type":39,"tag":238,"props":772,"children":773},{"style":603},[774],{"type":44,"value":775},"def function(input):\n",{"type":39,"tag":238,"props":777,"children":779},{"class":240,"line":778},25,[780],{"type":39,"tag":238,"props":781,"children":782},{"style":603},[783],{"type":44,"value":784},"    return expected\n",{"type":39,"tag":238,"props":786,"children":788},{"class":240,"line":787},26,[789],{"type":39,"tag":238,"props":790,"children":791},{"style":495},[792],{"type":44,"value":641},{"type":39,"tag":238,"props":794,"children":796},{"class":240,"line":795},27,[797],{"type":39,"tag":238,"props":798,"children":799},{"emptyLinePlaceholder":261},[800],{"type":44,"value":264},{"type":39,"tag":238,"props":802,"children":804},{"class":240,"line":803},28,[805,809,813,817,822],{"type":39,"tag":238,"props":806,"children":807},{"style":245},[808],{"type":44,"value":483},{"type":39,"tag":238,"props":810,"children":811},{"style":345},[812],{"type":44,"value":572},{"type":39,"tag":238,"props":814,"children":815},{"style":277},[816],{"type":44,"value":291},{"type":39,"tag":238,"props":818,"children":819},{"style":283},[820],{"type":44,"value":821},"Step 4: Run test to verify it passes",{"type":39,"tag":238,"props":823,"children":824},{"style":277},[825],{"type":44,"value":475},{"type":39,"tag":238,"props":827,"children":829},{"class":240,"line":828},29,[830],{"type":39,"tag":238,"props":831,"children":832},{"emptyLinePlaceholder":261},[833],{"type":44,"value":264},{"type":39,"tag":238,"props":835,"children":837},{"class":240,"line":836},30,[838,842,846,850],{"type":39,"tag":238,"props":839,"children":840},{"style":345},[841],{"type":44,"value":691},{"type":39,"tag":238,"props":843,"children":844},{"style":245},[845],{"type":44,"value":302},{"type":39,"tag":238,"props":847,"children":848},{"style":495},[849],{"type":44,"value":700},{"type":39,"tag":238,"props":851,"children":852},{"style":245},[853],{"type":44,"value":503},{"type":39,"tag":238,"props":855,"children":857},{"class":240,"line":856},31,[858],{"type":39,"tag":238,"props":859,"children":860},{"style":345},[861],{"type":44,"value":862},"Expected: PASS\n",{"type":39,"tag":238,"props":864,"children":866},{"class":240,"line":865},32,[867],{"type":39,"tag":238,"props":868,"children":869},{"emptyLinePlaceholder":261},[870],{"type":44,"value":264},{"type":39,"tag":238,"props":872,"children":874},{"class":240,"line":873},33,[875,879,883,887,892],{"type":39,"tag":238,"props":876,"children":877},{"style":245},[878],{"type":44,"value":483},{"type":39,"tag":238,"props":880,"children":881},{"style":345},[882],{"type":44,"value":572},{"type":39,"tag":238,"props":884,"children":885},{"style":277},[886],{"type":44,"value":291},{"type":39,"tag":238,"props":888,"children":889},{"style":283},[890],{"type":44,"value":891},"Step 5: Commit",{"type":39,"tag":238,"props":893,"children":894},{"style":277},[895],{"type":44,"value":475},{"type":39,"tag":238,"props":897,"children":899},{"class":240,"line":898},34,[900],{"type":39,"tag":238,"props":901,"children":902},{"emptyLinePlaceholder":261},[903],{"type":44,"value":264},{"type":39,"tag":238,"props":905,"children":907},{"class":240,"line":906},35,[908,912],{"type":39,"tag":238,"props":909,"children":910},{"style":495},[911],{"type":44,"value":600},{"type":39,"tag":238,"props":913,"children":914},{"style":603},[915],{"type":44,"value":916},"bash\n",{"type":39,"tag":238,"props":918,"children":920},{"class":240,"line":919},36,[921,926,931,936],{"type":39,"tag":238,"props":922,"children":923},{"style":251},[924],{"type":44,"value":925},"git",{"type":39,"tag":238,"props":927,"children":928},{"style":495},[929],{"type":44,"value":930}," add",{"type":39,"tag":238,"props":932,"children":933},{"style":495},[934],{"type":44,"value":935}," tests\u002Fpath\u002Ftest.py",{"type":39,"tag":238,"props":937,"children":938},{"style":495},[939],{"type":44,"value":940}," src\u002Fpath\u002Ffile.py\n",{"type":39,"tag":238,"props":942,"children":944},{"class":240,"line":943},37,[945,949,954,959,964,969],{"type":39,"tag":238,"props":946,"children":947},{"style":251},[948],{"type":44,"value":925},{"type":39,"tag":238,"props":950,"children":951},{"style":495},[952],{"type":44,"value":953}," commit",{"type":39,"tag":238,"props":955,"children":956},{"style":495},[957],{"type":44,"value":958}," -m",{"type":39,"tag":238,"props":960,"children":961},{"style":245},[962],{"type":44,"value":963}," \"",{"type":39,"tag":238,"props":965,"children":966},{"style":495},[967],{"type":44,"value":968},"feat: add specific feature",{"type":39,"tag":238,"props":970,"children":971},{"style":245},[972],{"type":44,"value":973},"\"\n",{"type":39,"tag":238,"props":975,"children":977},{"class":240,"line":976},38,[978],{"type":39,"tag":238,"props":979,"children":980},{"style":495},[981],{"type":44,"value":641},{"type":39,"tag":47,"props":983,"children":985},{"id":984},"no-placeholders",[986],{"type":44,"value":987},"No Placeholders",{"type":39,"tag":54,"props":989,"children":990},{},[991,993,998],{"type":44,"value":992},"Every step must contain the actual content an engineer needs. These are ",{"type":39,"tag":68,"props":994,"children":995},{},[996],{"type":44,"value":997},"plan failures",{"type":44,"value":999}," — never write them:",{"type":39,"tag":111,"props":1001,"children":1002},{},[1003,1008,1013,1018,1023,1028],{"type":39,"tag":115,"props":1004,"children":1005},{},[1006],{"type":44,"value":1007},"\"TBD\", \"TODO\", \"implement later\", \"fill in details\"",{"type":39,"tag":115,"props":1009,"children":1010},{},[1011],{"type":44,"value":1012},"\"Add appropriate error handling\" \u002F \"add validation\" \u002F \"handle edge cases\"",{"type":39,"tag":115,"props":1014,"children":1015},{},[1016],{"type":44,"value":1017},"\"Write tests for the above\" (without actual test code)",{"type":39,"tag":115,"props":1019,"children":1020},{},[1021],{"type":44,"value":1022},"\"Similar to Task N\" (repeat the code — the engineer may be reading tasks out of order)",{"type":39,"tag":115,"props":1024,"children":1025},{},[1026],{"type":44,"value":1027},"Steps that describe what to do without showing how (code blocks required for code steps)",{"type":39,"tag":115,"props":1029,"children":1030},{},[1031],{"type":44,"value":1032},"References to types, functions, or methods not defined in any task",{"type":39,"tag":47,"props":1034,"children":1036},{"id":1035},"remember",[1037],{"type":44,"value":1038},"Remember",{"type":39,"tag":111,"props":1040,"children":1041},{},[1042,1047,1052,1057],{"type":39,"tag":115,"props":1043,"children":1044},{},[1045],{"type":44,"value":1046},"Exact file paths always",{"type":39,"tag":115,"props":1048,"children":1049},{},[1050],{"type":44,"value":1051},"Complete code in every step — if a step changes code, show the code",{"type":39,"tag":115,"props":1053,"children":1054},{},[1055],{"type":44,"value":1056},"Exact commands with expected output",{"type":39,"tag":115,"props":1058,"children":1059},{},[1060],{"type":44,"value":1061},"DRY, YAGNI, TDD, frequent commits",{"type":39,"tag":47,"props":1063,"children":1065},{"id":1064},"self-review",[1066],{"type":44,"value":1067},"Self-Review",{"type":39,"tag":54,"props":1069,"children":1070},{},[1071],{"type":44,"value":1072},"After writing the complete plan, look at the spec with fresh eyes and check the plan against it. This is a checklist you run yourself — not a subagent dispatch.",{"type":39,"tag":54,"props":1074,"children":1075},{},[1076,1081],{"type":39,"tag":68,"props":1077,"children":1078},{},[1079],{"type":44,"value":1080},"1. Spec coverage:",{"type":44,"value":1082}," Skim each section\u002Frequirement in the spec. Can you point to a task that implements it? List any gaps.",{"type":39,"tag":54,"props":1084,"children":1085},{},[1086,1091],{"type":39,"tag":68,"props":1087,"children":1088},{},[1089],{"type":44,"value":1090},"2. Placeholder scan:",{"type":44,"value":1092}," Search your plan for red flags — any of the patterns from the \"No Placeholders\" section above. Fix them.",{"type":39,"tag":54,"props":1094,"children":1095},{},[1096,1101,1103,1109,1111,1117],{"type":39,"tag":68,"props":1097,"children":1098},{},[1099],{"type":44,"value":1100},"3. Type consistency:",{"type":44,"value":1102}," Do the types, method signatures, and property names you used in later tasks match what you defined in earlier tasks? A function called ",{"type":39,"tag":86,"props":1104,"children":1106},{"className":1105},[],[1107],{"type":44,"value":1108},"clearLayers()",{"type":44,"value":1110}," in Task 3 but ",{"type":39,"tag":86,"props":1112,"children":1114},{"className":1113},[],[1115],{"type":44,"value":1116},"clearFullLayers()",{"type":44,"value":1118}," in Task 7 is a bug.",{"type":39,"tag":54,"props":1120,"children":1121},{},[1122],{"type":44,"value":1123},"If you find issues, fix them inline. No need to re-review — just fix and move on. If you find a spec requirement with no task, add the task.",{"type":39,"tag":47,"props":1125,"children":1127},{"id":1126},"execution-handoff",[1128],{"type":44,"value":1129},"Execution Handoff",{"type":39,"tag":54,"props":1131,"children":1132},{},[1133],{"type":44,"value":1134},"After saving the plan, offer execution choice:",{"type":39,"tag":54,"props":1136,"children":1137},{},[1138],{"type":39,"tag":68,"props":1139,"children":1140},{},[1141,1143,1149],{"type":44,"value":1142},"\"Plan complete and saved to ",{"type":39,"tag":86,"props":1144,"children":1146},{"className":1145},[],[1147],{"type":44,"value":1148},"docs\u002Fsuperpowers\u002Fplans\u002F\u003Cfilename>.md",{"type":44,"value":1150},". Two execution options:",{"type":39,"tag":54,"props":1152,"children":1153},{},[1154,1159],{"type":39,"tag":68,"props":1155,"children":1156},{},[1157],{"type":44,"value":1158},"1. Subagent-Driven (recommended)",{"type":44,"value":1160}," - I dispatch a fresh subagent per task, review between tasks, fast iteration",{"type":39,"tag":54,"props":1162,"children":1163},{},[1164,1169],{"type":39,"tag":68,"props":1165,"children":1166},{},[1167],{"type":44,"value":1168},"2. Inline Execution",{"type":44,"value":1170}," - Execute tasks in this session using executing-plans, batch execution with checkpoints",{"type":39,"tag":54,"props":1172,"children":1173},{},[1174],{"type":39,"tag":68,"props":1175,"children":1176},{},[1177],{"type":44,"value":1178},"Which approach?\"",{"type":39,"tag":54,"props":1180,"children":1181},{},[1182],{"type":39,"tag":68,"props":1183,"children":1184},{},[1185],{"type":44,"value":1186},"If Subagent-Driven chosen:",{"type":39,"tag":111,"props":1188,"children":1189},{},[1190,1200],{"type":39,"tag":115,"props":1191,"children":1192},{},[1193,1198],{"type":39,"tag":68,"props":1194,"children":1195},{},[1196],{"type":44,"value":1197},"REQUIRED SUB-SKILL:",{"type":44,"value":1199}," Use superpowers:subagent-driven-development",{"type":39,"tag":115,"props":1201,"children":1202},{},[1203],{"type":44,"value":1204},"Fresh subagent per task + two-stage review",{"type":39,"tag":54,"props":1206,"children":1207},{},[1208],{"type":39,"tag":68,"props":1209,"children":1210},{},[1211],{"type":44,"value":1212},"If Inline Execution chosen:",{"type":39,"tag":111,"props":1214,"children":1215},{},[1216,1225],{"type":39,"tag":115,"props":1217,"children":1218},{},[1219,1223],{"type":39,"tag":68,"props":1220,"children":1221},{},[1222],{"type":44,"value":1197},{"type":44,"value":1224}," Use superpowers:executing-plans",{"type":39,"tag":115,"props":1226,"children":1227},{},[1228],{"type":44,"value":1229},"Batch execution with checkpoints for review",{"type":39,"tag":1231,"props":1232,"children":1233},"style",{},[1234],{"type":44,"value":1235},"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":1237,"total":1359},[1238,1257,1273,1285,1305,1327,1347],{"slug":1239,"name":1239,"fn":1240,"description":1241,"org":1242,"tags":1243,"stars":22,"repoUrl":23,"updatedAt":1256},"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},[1244,1247,1250,1253],{"name":1245,"slug":1246,"type":15},"Accessibility","accessibility",{"name":1248,"slug":1249,"type":15},"Charts","charts",{"name":1251,"slug":1252,"type":15},"Data Visualization","data-visualization",{"name":1254,"slug":1255,"type":15},"Design","design","2026-06-30T19:00:57.102",{"slug":1258,"name":1258,"fn":1259,"description":1260,"org":1261,"tags":1262,"stars":22,"repoUrl":23,"updatedAt":1272},"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},[1263,1266,1269],{"name":1264,"slug":1265,"type":15},"Agents","agents",{"name":1267,"slug":1268,"type":15},"Browser Automation","browser-automation",{"name":1270,"slug":1271,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":1274,"name":1274,"fn":1275,"description":1276,"org":1277,"tags":1278,"stars":22,"repoUrl":23,"updatedAt":1284},"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},[1279,1280,1283],{"name":1267,"slug":1268,"type":15},{"name":1281,"slug":1282,"type":15},"Local Development","local-development",{"name":1270,"slug":1271,"type":15},"2026-04-06T18:41:17.526867",{"slug":1286,"name":1286,"fn":1287,"description":1288,"org":1289,"tags":1290,"stars":22,"repoUrl":23,"updatedAt":1304},"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},[1291,1292,1295,1298,1301],{"name":1264,"slug":1265,"type":15},{"name":1293,"slug":1294,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1296,"slug":1297,"type":15},"SDK","sdk",{"name":1299,"slug":1300,"type":15},"Serverless","serverless",{"name":1302,"slug":1303,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":1306,"name":1306,"fn":1307,"description":1308,"org":1309,"tags":1310,"stars":22,"repoUrl":23,"updatedAt":1326},"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},[1311,1314,1317,1320,1323],{"name":1312,"slug":1313,"type":15},"Frontend","frontend",{"name":1315,"slug":1316,"type":15},"React","react",{"name":1318,"slug":1319,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":1321,"slug":1322,"type":15},"UI Components","ui-components",{"name":1324,"slug":1325,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":1328,"name":1328,"fn":1329,"description":1330,"org":1331,"tags":1332,"stars":22,"repoUrl":23,"updatedAt":1346},"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},[1333,1336,1339,1342,1345],{"name":1334,"slug":1335,"type":15},"AI Infrastructure","ai-infrastructure",{"name":1337,"slug":1338,"type":15},"Cost Optimization","cost-optimization",{"name":1340,"slug":1341,"type":15},"LLM","llm",{"name":1343,"slug":1344,"type":15},"Performance","performance",{"name":1324,"slug":1325,"type":15},"2026-04-06T18:40:44.377464",{"slug":1348,"name":1348,"fn":1349,"description":1350,"org":1351,"tags":1352,"stars":22,"repoUrl":23,"updatedAt":1358},"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},[1353,1354,1357],{"name":1337,"slug":1338,"type":15},{"name":1355,"slug":1356,"type":15},"Database","database",{"name":1340,"slug":1341,"type":15},"2026-04-06T18:41:08.513425",600,{"items":1361,"total":1556},[1362,1383,1406,1423,1439,1456,1473,1485,1499,1513,1525,1540],{"slug":1363,"name":1363,"fn":1364,"description":1365,"org":1366,"tags":1367,"stars":1380,"repoUrl":1381,"updatedAt":1382},"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},[1368,1371,1374,1377],{"name":1369,"slug":1370,"type":15},"Documents","documents",{"name":1372,"slug":1373,"type":15},"Healthcare","healthcare",{"name":1375,"slug":1376,"type":15},"Insurance","insurance",{"name":1378,"slug":1379,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":1384,"name":1384,"fn":1385,"description":1386,"org":1387,"tags":1388,"stars":1403,"repoUrl":1404,"updatedAt":1405},"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},[1389,1392,1394,1397,1400],{"name":1390,"slug":1391,"type":15},".NET","dotnet",{"name":1393,"slug":1384,"type":15},"ASP.NET Core",{"name":1395,"slug":1396,"type":15},"Blazor","blazor",{"name":1398,"slug":1399,"type":15},"C#","csharp",{"name":1401,"slug":1402,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1407,"name":1407,"fn":1408,"description":1409,"org":1410,"tags":1411,"stars":1403,"repoUrl":1404,"updatedAt":1422},"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},[1412,1415,1418,1421],{"name":1413,"slug":1414,"type":15},"Apps SDK","apps-sdk",{"name":1416,"slug":1417,"type":15},"ChatGPT","chatgpt",{"name":1419,"slug":1420,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1424,"name":1424,"fn":1425,"description":1426,"org":1427,"tags":1428,"stars":1403,"repoUrl":1404,"updatedAt":1438},"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},[1429,1432,1435],{"name":1430,"slug":1431,"type":15},"API Development","api-development",{"name":1433,"slug":1434,"type":15},"CLI","cli",{"name":1436,"slug":1437,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1440,"name":1440,"fn":1441,"description":1442,"org":1443,"tags":1444,"stars":1403,"repoUrl":1404,"updatedAt":1455},"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},[1445,1448,1451,1452],{"name":1446,"slug":1447,"type":15},"Cloudflare","cloudflare",{"name":1449,"slug":1450,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1293,"slug":1294,"type":15},{"name":1453,"slug":1454,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1457,"name":1457,"fn":1458,"description":1459,"org":1460,"tags":1461,"stars":1403,"repoUrl":1404,"updatedAt":1472},"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},[1462,1463,1466,1469],{"name":13,"slug":14,"type":15},{"name":1464,"slug":1465,"type":15},"Project Management","project-management",{"name":1467,"slug":1468,"type":15},"Strategy","strategy",{"name":1470,"slug":1471,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1474,"name":1474,"fn":1475,"description":1476,"org":1477,"tags":1478,"stars":1403,"repoUrl":1404,"updatedAt":1484},"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},[1479,1480,1482,1483],{"name":1254,"slug":1255,"type":15},{"name":1481,"slug":1474,"type":15},"Figma",{"name":1312,"slug":1313,"type":15},{"name":1419,"slug":1420,"type":15},"2026-04-12T05:06:47.939943",{"slug":1486,"name":1486,"fn":1487,"description":1488,"org":1489,"tags":1490,"stars":1403,"repoUrl":1404,"updatedAt":1498},"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},[1491,1492,1495,1496,1497],{"name":1254,"slug":1255,"type":15},{"name":1493,"slug":1494,"type":15},"Design System","design-system",{"name":1481,"slug":1474,"type":15},{"name":1312,"slug":1313,"type":15},{"name":1321,"slug":1322,"type":15},"2026-05-10T05:59:52.971881",{"slug":1500,"name":1500,"fn":1501,"description":1502,"org":1503,"tags":1504,"stars":1403,"repoUrl":1404,"updatedAt":1512},"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},[1505,1506,1507,1510,1511],{"name":1254,"slug":1255,"type":15},{"name":1493,"slug":1494,"type":15},{"name":1508,"slug":1509,"type":15},"Documentation","documentation",{"name":1481,"slug":1474,"type":15},{"name":1312,"slug":1313,"type":15},"2026-05-16T06:07:47.821474",{"slug":1514,"name":1514,"fn":1515,"description":1516,"org":1517,"tags":1518,"stars":1403,"repoUrl":1404,"updatedAt":1524},"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},[1519,1520,1521,1522,1523],{"name":1254,"slug":1255,"type":15},{"name":1481,"slug":1474,"type":15},{"name":1312,"slug":1313,"type":15},{"name":1321,"slug":1322,"type":15},{"name":1401,"slug":1402,"type":15},"2026-05-16T06:07:40.583615",{"slug":1526,"name":1526,"fn":1527,"description":1528,"org":1529,"tags":1530,"stars":1403,"repoUrl":1404,"updatedAt":1539},"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},[1531,1534,1535,1538],{"name":1532,"slug":1533,"type":15},"Animation","animation",{"name":1436,"slug":1437,"type":15},{"name":1536,"slug":1537,"type":15},"Creative","creative",{"name":1254,"slug":1255,"type":15},"2026-05-02T05:31:48.48485",{"slug":1541,"name":1541,"fn":1542,"description":1543,"org":1544,"tags":1545,"stars":1403,"repoUrl":1404,"updatedAt":1555},"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},[1546,1547,1548,1551,1554],{"name":1536,"slug":1537,"type":15},{"name":1254,"slug":1255,"type":15},{"name":1549,"slug":1550,"type":15},"Image Generation","image-generation",{"name":1552,"slug":1553,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]