[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-brainstorming":3,"mdc-ffq4y6-key":33,"related-org-openai-brainstorming":961,"related-repo-openai-brainstorming":1166},{"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},"brainstorming","brainstorm features and requirements","You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.",{"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},"Ideation","ideation","tag",{"name":17,"slug":18,"type":15},"Product Management","product-management",{"name":20,"slug":21,"type":15},"Design","design",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-04-16T05:11:52.284891",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\u002Fbrainstorming","---\nname: brainstorming\ndescription: \"You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.\"\n---\n\n# Brainstorming Ideas Into Designs\n\nHelp turn ideas into fully formed designs and specs through natural collaborative dialogue.\n\nStart by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.\n\n\u003CHARD-GATE>\nDo NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity.\n\u003C\u002FHARD-GATE>\n\n## Anti-Pattern: \"This Is Too Simple To Need A Design\"\n\nEvery project goes through this process. A todo list, a single-function utility, a config change — all of them. \"Simple\" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.\n\n## Checklist\n\nYou MUST create a task for each of these items and complete them in order:\n\n1. **Explore project context** — check files, docs, recent commits\n2. **Offer visual companion** (if topic will involve visual questions) — this is its own message, not combined with a clarifying question. See the Visual Companion section below.\n3. **Ask clarifying questions** — one at a time, understand purpose\u002Fconstraints\u002Fsuccess criteria\n4. **Propose 2-3 approaches** — with trade-offs and your recommendation\n5. **Present design** — in sections scaled to their complexity, get user approval after each section\n6. **Write design doc** — save to `docs\u002Fsuperpowers\u002Fspecs\u002FYYYY-MM-DD-\u003Ctopic>-design.md` and commit\n7. **Spec self-review** — quick inline check for placeholders, contradictions, ambiguity, scope (see below)\n8. **User reviews written spec** — ask user to review the spec file before proceeding\n9. **Transition to implementation** — invoke writing-plans skill to create implementation plan\n\n## Process Flow\n\n```dot\ndigraph brainstorming {\n    \"Explore project context\" [shape=box];\n    \"Visual questions ahead?\" [shape=diamond];\n    \"Offer Visual Companion\\n(own message, no other content)\" [shape=box];\n    \"Ask clarifying questions\" [shape=box];\n    \"Propose 2-3 approaches\" [shape=box];\n    \"Present design sections\" [shape=box];\n    \"User approves design?\" [shape=diamond];\n    \"Write design doc\" [shape=box];\n    \"Spec self-review\\n(fix inline)\" [shape=box];\n    \"User reviews spec?\" [shape=diamond];\n    \"Invoke writing-plans skill\" [shape=doublecircle];\n\n    \"Explore project context\" -> \"Visual questions ahead?\";\n    \"Visual questions ahead?\" -> \"Offer Visual Companion\\n(own message, no other content)\" [label=\"yes\"];\n    \"Visual questions ahead?\" -> \"Ask clarifying questions\" [label=\"no\"];\n    \"Offer Visual Companion\\n(own message, no other content)\" -> \"Ask clarifying questions\";\n    \"Ask clarifying questions\" -> \"Propose 2-3 approaches\";\n    \"Propose 2-3 approaches\" -> \"Present design sections\";\n    \"Present design sections\" -> \"User approves design?\";\n    \"User approves design?\" -> \"Present design sections\" [label=\"no, revise\"];\n    \"User approves design?\" -> \"Write design doc\" [label=\"yes\"];\n    \"Write design doc\" -> \"Spec self-review\\n(fix inline)\";\n    \"Spec self-review\\n(fix inline)\" -> \"User reviews spec?\";\n    \"User reviews spec?\" -> \"Write design doc\" [label=\"changes requested\"];\n    \"User reviews spec?\" -> \"Invoke writing-plans skill\" [label=\"approved\"];\n}\n```\n\n**The terminal state is invoking writing-plans.** Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans.\n\n## The Process\n\n**Understanding the idea:**\n\n- Check out the current project state first (files, docs, recent commits)\n- Before asking detailed questions, assess scope: if the request describes multiple independent subsystems (e.g., \"build a platform with chat, file storage, billing, and analytics\"), flag this immediately. Don't spend questions refining details of a project that needs to be decomposed first.\n- If the project is too large for a single spec, help the user decompose into sub-projects: what are the independent pieces, how do they relate, what order should they be built? Then brainstorm the first sub-project through the normal design flow. Each sub-project gets its own spec → plan → implementation cycle.\n- For appropriately-scoped projects, ask questions one at a time to refine the idea\n- Prefer multiple choice questions when possible, but open-ended is fine too\n- Only one question per message - if a topic needs more exploration, break it into multiple questions\n- Focus on understanding: purpose, constraints, success criteria\n\n**Exploring approaches:**\n\n- Propose 2-3 different approaches with trade-offs\n- Present options conversationally with your recommendation and reasoning\n- Lead with your recommended option and explain why\n\n**Presenting the design:**\n\n- Once you believe you understand what you're building, present the design\n- Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced\n- Ask after each section whether it looks right so far\n- Cover: architecture, components, data flow, error handling, testing\n- Be ready to go back and clarify if something doesn't make sense\n\n**Design for isolation and clarity:**\n\n- Break the system into smaller units that each have one clear purpose, communicate through well-defined interfaces, and can be understood and tested independently\n- For each unit, you should be able to answer: what does it do, how do you use it, and what does it depend on?\n- Can someone understand what a unit does without reading its internals? Can you change the internals without breaking consumers? If not, the boundaries need work.\n- Smaller, well-bounded units are also easier for you to work with - you reason better about code you can hold in context at once, and your edits are more reliable when files are focused. When a file grows large, that's often a signal that it's doing too much.\n\n**Working in existing codebases:**\n\n- Explore the current structure before proposing changes. Follow existing patterns.\n- Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in.\n- Don't propose unrelated refactoring. Stay focused on what serves the current goal.\n\n## After the Design\n\n**Documentation:**\n\n- Write the validated design (spec) to `docs\u002Fsuperpowers\u002Fspecs\u002FYYYY-MM-DD-\u003Ctopic>-design.md`\n  - (User preferences for spec location override this default)\n- Use elements-of-style:writing-clearly-and-concisely skill if available\n- Commit the design document to git\n\n**Spec Self-Review:**\nAfter writing the spec document, look at it with fresh eyes:\n\n1. **Placeholder scan:** Any \"TBD\", \"TODO\", incomplete sections, or vague requirements? Fix them.\n2. **Internal consistency:** Do any sections contradict each other? Does the architecture match the feature descriptions?\n3. **Scope check:** Is this focused enough for a single implementation plan, or does it need decomposition?\n4. **Ambiguity check:** Could any requirement be interpreted two different ways? If so, pick one and make it explicit.\n\nFix any issues inline. No need to re-review — just fix and move on.\n\n**User Review Gate:**\nAfter the spec review loop passes, ask the user to review the written spec before proceeding:\n\n> \"Spec written and committed to `\u003Cpath>`. Please review it and let me know if you want to make any changes before we start writing out the implementation plan.\"\n\nWait for the user's response. If they request changes, make them and re-run the spec review loop. Only proceed once the user approves.\n\n**Implementation:**\n\n- Invoke the writing-plans skill to create a detailed implementation plan\n- Do NOT invoke any other skill. writing-plans is the next step.\n\n## Key Principles\n\n- **One question at a time** - Don't overwhelm with multiple questions\n- **Multiple choice preferred** - Easier to answer than open-ended when possible\n- **YAGNI ruthlessly** - Remove unnecessary features from all designs\n- **Explore alternatives** - Always propose 2-3 approaches before settling\n- **Incremental validation** - Present design, get approval before moving on\n- **Be flexible** - Go back and clarify when something doesn't make sense\n\n## Visual Companion\n\nA browser-based companion for showing mockups, diagrams, and visual options during brainstorming. Available as a tool — not a mode. Accepting the companion means it's available for questions that benefit from visual treatment; it does NOT mean every question goes through the browser.\n\n**Offering the companion:** When you anticipate that upcoming questions will involve visual content (mockups, layouts, diagrams), offer it once for consent:\n> \"Some of what we're working on might be easier to explain if I can show it to you in a web browser. I can put together mockups, diagrams, comparisons, and other visuals as we go. This feature is still new and can be token-intensive. Want to try it? (Requires opening a local URL)\"\n\n**This offer MUST be its own message.** Do not combine it with clarifying questions, context summaries, or any other content. The message should contain ONLY the offer above and nothing else. Wait for the user's response before continuing. If they decline, proceed with text-only brainstorming.\n\n**Per-question decision:** Even after the user accepts, decide FOR EACH QUESTION whether to use the browser or the terminal. The test: **would the user understand this better by seeing it than reading it?**\n\n- **Use the browser** for content that IS visual — mockups, wireframes, layout comparisons, architecture diagrams, side-by-side visual designs\n- **Use the terminal** for content that is text — requirements questions, conceptual choices, tradeoff lists, A\u002FB\u002FC\u002FD text options, scope decisions\n\nA question about a UI topic is not automatically a visual question. \"What does personality mean in this context?\" is a conceptual question — use the terminal. \"Which wizard layout works better?\" is a visual question — use the browser.\n\nIf they agree to the companion, read the detailed guide before proceeding:\n`skills\u002Fbrainstorming\u002Fvisual-companion.md`\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,53,58,64,71,76,82,87,192,198,455,465,471,479,518,526,544,552,580,588,611,619,637,643,651,682,692,735,740,750,767,772,780,793,799,862,868,873,883,891,901,916,939,944,955],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"brainstorming-ideas-into-designs",[44],{"type":45,"value":46},"text","Brainstorming Ideas Into Designs",{"type":39,"tag":48,"props":49,"children":50},"p",{},[51],{"type":45,"value":52},"Help turn ideas into fully formed designs and specs through natural collaborative dialogue.",{"type":39,"tag":48,"props":54,"children":55},{},[56],{"type":45,"value":57},"Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.",{"type":39,"tag":59,"props":60,"children":61},"hard-gate",{},[62],{"type":45,"value":63},"\nDo NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity.\n",{"type":39,"tag":65,"props":66,"children":68},"h2",{"id":67},"anti-pattern-this-is-too-simple-to-need-a-design",[69],{"type":45,"value":70},"Anti-Pattern: \"This Is Too Simple To Need A Design\"",{"type":39,"tag":48,"props":72,"children":73},{},[74],{"type":45,"value":75},"Every project goes through this process. A todo list, a single-function utility, a config change — all of them. \"Simple\" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.",{"type":39,"tag":65,"props":77,"children":79},{"id":78},"checklist",[80],{"type":45,"value":81},"Checklist",{"type":39,"tag":48,"props":83,"children":84},{},[85],{"type":45,"value":86},"You MUST create a task for each of these items and complete them in order:",{"type":39,"tag":88,"props":89,"children":90},"ol",{},[91,103,113,123,133,143,162,172,182],{"type":39,"tag":92,"props":93,"children":94},"li",{},[95,101],{"type":39,"tag":96,"props":97,"children":98},"strong",{},[99],{"type":45,"value":100},"Explore project context",{"type":45,"value":102}," — check files, docs, recent commits",{"type":39,"tag":92,"props":104,"children":105},{},[106,111],{"type":39,"tag":96,"props":107,"children":108},{},[109],{"type":45,"value":110},"Offer visual companion",{"type":45,"value":112}," (if topic will involve visual questions) — this is its own message, not combined with a clarifying question. See the Visual Companion section below.",{"type":39,"tag":92,"props":114,"children":115},{},[116,121],{"type":39,"tag":96,"props":117,"children":118},{},[119],{"type":45,"value":120},"Ask clarifying questions",{"type":45,"value":122}," — one at a time, understand purpose\u002Fconstraints\u002Fsuccess criteria",{"type":39,"tag":92,"props":124,"children":125},{},[126,131],{"type":39,"tag":96,"props":127,"children":128},{},[129],{"type":45,"value":130},"Propose 2-3 approaches",{"type":45,"value":132}," — with trade-offs and your recommendation",{"type":39,"tag":92,"props":134,"children":135},{},[136,141],{"type":39,"tag":96,"props":137,"children":138},{},[139],{"type":45,"value":140},"Present design",{"type":45,"value":142}," — in sections scaled to their complexity, get user approval after each section",{"type":39,"tag":92,"props":144,"children":145},{},[146,151,153,160],{"type":39,"tag":96,"props":147,"children":148},{},[149],{"type":45,"value":150},"Write design doc",{"type":45,"value":152}," — save to ",{"type":39,"tag":154,"props":155,"children":157},"code",{"className":156},[],[158],{"type":45,"value":159},"docs\u002Fsuperpowers\u002Fspecs\u002FYYYY-MM-DD-\u003Ctopic>-design.md",{"type":45,"value":161}," and commit",{"type":39,"tag":92,"props":163,"children":164},{},[165,170],{"type":39,"tag":96,"props":166,"children":167},{},[168],{"type":45,"value":169},"Spec self-review",{"type":45,"value":171}," — quick inline check for placeholders, contradictions, ambiguity, scope (see below)",{"type":39,"tag":92,"props":173,"children":174},{},[175,180],{"type":39,"tag":96,"props":176,"children":177},{},[178],{"type":45,"value":179},"User reviews written spec",{"type":45,"value":181}," — ask user to review the spec file before proceeding",{"type":39,"tag":92,"props":183,"children":184},{},[185,190],{"type":39,"tag":96,"props":186,"children":187},{},[188],{"type":45,"value":189},"Transition to implementation",{"type":45,"value":191}," — invoke writing-plans skill to create implementation plan",{"type":39,"tag":65,"props":193,"children":195},{"id":194},"process-flow",[196],{"type":45,"value":197},"Process Flow",{"type":39,"tag":199,"props":200,"children":205},"pre",{"className":201,"code":202,"language":203,"meta":204,"style":204},"language-dot shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","digraph brainstorming {\n    \"Explore project context\" [shape=box];\n    \"Visual questions ahead?\" [shape=diamond];\n    \"Offer Visual Companion\\n(own message, no other content)\" [shape=box];\n    \"Ask clarifying questions\" [shape=box];\n    \"Propose 2-3 approaches\" [shape=box];\n    \"Present design sections\" [shape=box];\n    \"User approves design?\" [shape=diamond];\n    \"Write design doc\" [shape=box];\n    \"Spec self-review\\n(fix inline)\" [shape=box];\n    \"User reviews spec?\" [shape=diamond];\n    \"Invoke writing-plans skill\" [shape=doublecircle];\n\n    \"Explore project context\" -> \"Visual questions ahead?\";\n    \"Visual questions ahead?\" -> \"Offer Visual Companion\\n(own message, no other content)\" [label=\"yes\"];\n    \"Visual questions ahead?\" -> \"Ask clarifying questions\" [label=\"no\"];\n    \"Offer Visual Companion\\n(own message, no other content)\" -> \"Ask clarifying questions\";\n    \"Ask clarifying questions\" -> \"Propose 2-3 approaches\";\n    \"Propose 2-3 approaches\" -> \"Present design sections\";\n    \"Present design sections\" -> \"User approves design?\";\n    \"User approves design?\" -> \"Present design sections\" [label=\"no, revise\"];\n    \"User approves design?\" -> \"Write design doc\" [label=\"yes\"];\n    \"Write design doc\" -> \"Spec self-review\\n(fix inline)\";\n    \"Spec self-review\\n(fix inline)\" -> \"User reviews spec?\";\n    \"User reviews spec?\" -> \"Write design doc\" [label=\"changes requested\"];\n    \"User reviews spec?\" -> \"Invoke writing-plans skill\" [label=\"approved\"];\n}\n","dot","",[206],{"type":39,"tag":154,"props":207,"children":208},{"__ignoreMap":204},[209,220,229,238,247,256,265,274,283,292,301,310,319,329,338,347,356,365,374,383,392,401,410,419,428,437,446],{"type":39,"tag":210,"props":211,"children":214},"span",{"class":212,"line":213},"line",1,[215],{"type":39,"tag":210,"props":216,"children":217},{},[218],{"type":45,"value":219},"digraph brainstorming {\n",{"type":39,"tag":210,"props":221,"children":223},{"class":212,"line":222},2,[224],{"type":39,"tag":210,"props":225,"children":226},{},[227],{"type":45,"value":228},"    \"Explore project context\" [shape=box];\n",{"type":39,"tag":210,"props":230,"children":232},{"class":212,"line":231},3,[233],{"type":39,"tag":210,"props":234,"children":235},{},[236],{"type":45,"value":237},"    \"Visual questions ahead?\" [shape=diamond];\n",{"type":39,"tag":210,"props":239,"children":241},{"class":212,"line":240},4,[242],{"type":39,"tag":210,"props":243,"children":244},{},[245],{"type":45,"value":246},"    \"Offer Visual Companion\\n(own message, no other content)\" [shape=box];\n",{"type":39,"tag":210,"props":248,"children":250},{"class":212,"line":249},5,[251],{"type":39,"tag":210,"props":252,"children":253},{},[254],{"type":45,"value":255},"    \"Ask clarifying questions\" [shape=box];\n",{"type":39,"tag":210,"props":257,"children":259},{"class":212,"line":258},6,[260],{"type":39,"tag":210,"props":261,"children":262},{},[263],{"type":45,"value":264},"    \"Propose 2-3 approaches\" [shape=box];\n",{"type":39,"tag":210,"props":266,"children":268},{"class":212,"line":267},7,[269],{"type":39,"tag":210,"props":270,"children":271},{},[272],{"type":45,"value":273},"    \"Present design sections\" [shape=box];\n",{"type":39,"tag":210,"props":275,"children":277},{"class":212,"line":276},8,[278],{"type":39,"tag":210,"props":279,"children":280},{},[281],{"type":45,"value":282},"    \"User approves design?\" [shape=diamond];\n",{"type":39,"tag":210,"props":284,"children":286},{"class":212,"line":285},9,[287],{"type":39,"tag":210,"props":288,"children":289},{},[290],{"type":45,"value":291},"    \"Write design doc\" [shape=box];\n",{"type":39,"tag":210,"props":293,"children":295},{"class":212,"line":294},10,[296],{"type":39,"tag":210,"props":297,"children":298},{},[299],{"type":45,"value":300},"    \"Spec self-review\\n(fix inline)\" [shape=box];\n",{"type":39,"tag":210,"props":302,"children":304},{"class":212,"line":303},11,[305],{"type":39,"tag":210,"props":306,"children":307},{},[308],{"type":45,"value":309},"    \"User reviews spec?\" [shape=diamond];\n",{"type":39,"tag":210,"props":311,"children":313},{"class":212,"line":312},12,[314],{"type":39,"tag":210,"props":315,"children":316},{},[317],{"type":45,"value":318},"    \"Invoke writing-plans skill\" [shape=doublecircle];\n",{"type":39,"tag":210,"props":320,"children":322},{"class":212,"line":321},13,[323],{"type":39,"tag":210,"props":324,"children":326},{"emptyLinePlaceholder":325},true,[327],{"type":45,"value":328},"\n",{"type":39,"tag":210,"props":330,"children":332},{"class":212,"line":331},14,[333],{"type":39,"tag":210,"props":334,"children":335},{},[336],{"type":45,"value":337},"    \"Explore project context\" -> \"Visual questions ahead?\";\n",{"type":39,"tag":210,"props":339,"children":341},{"class":212,"line":340},15,[342],{"type":39,"tag":210,"props":343,"children":344},{},[345],{"type":45,"value":346},"    \"Visual questions ahead?\" -> \"Offer Visual Companion\\n(own message, no other content)\" [label=\"yes\"];\n",{"type":39,"tag":210,"props":348,"children":350},{"class":212,"line":349},16,[351],{"type":39,"tag":210,"props":352,"children":353},{},[354],{"type":45,"value":355},"    \"Visual questions ahead?\" -> \"Ask clarifying questions\" [label=\"no\"];\n",{"type":39,"tag":210,"props":357,"children":359},{"class":212,"line":358},17,[360],{"type":39,"tag":210,"props":361,"children":362},{},[363],{"type":45,"value":364},"    \"Offer Visual Companion\\n(own message, no other content)\" -> \"Ask clarifying questions\";\n",{"type":39,"tag":210,"props":366,"children":368},{"class":212,"line":367},18,[369],{"type":39,"tag":210,"props":370,"children":371},{},[372],{"type":45,"value":373},"    \"Ask clarifying questions\" -> \"Propose 2-3 approaches\";\n",{"type":39,"tag":210,"props":375,"children":377},{"class":212,"line":376},19,[378],{"type":39,"tag":210,"props":379,"children":380},{},[381],{"type":45,"value":382},"    \"Propose 2-3 approaches\" -> \"Present design sections\";\n",{"type":39,"tag":210,"props":384,"children":386},{"class":212,"line":385},20,[387],{"type":39,"tag":210,"props":388,"children":389},{},[390],{"type":45,"value":391},"    \"Present design sections\" -> \"User approves design?\";\n",{"type":39,"tag":210,"props":393,"children":395},{"class":212,"line":394},21,[396],{"type":39,"tag":210,"props":397,"children":398},{},[399],{"type":45,"value":400},"    \"User approves design?\" -> \"Present design sections\" [label=\"no, revise\"];\n",{"type":39,"tag":210,"props":402,"children":404},{"class":212,"line":403},22,[405],{"type":39,"tag":210,"props":406,"children":407},{},[408],{"type":45,"value":409},"    \"User approves design?\" -> \"Write design doc\" [label=\"yes\"];\n",{"type":39,"tag":210,"props":411,"children":413},{"class":212,"line":412},23,[414],{"type":39,"tag":210,"props":415,"children":416},{},[417],{"type":45,"value":418},"    \"Write design doc\" -> \"Spec self-review\\n(fix inline)\";\n",{"type":39,"tag":210,"props":420,"children":422},{"class":212,"line":421},24,[423],{"type":39,"tag":210,"props":424,"children":425},{},[426],{"type":45,"value":427},"    \"Spec self-review\\n(fix inline)\" -> \"User reviews spec?\";\n",{"type":39,"tag":210,"props":429,"children":431},{"class":212,"line":430},25,[432],{"type":39,"tag":210,"props":433,"children":434},{},[435],{"type":45,"value":436},"    \"User reviews spec?\" -> \"Write design doc\" [label=\"changes requested\"];\n",{"type":39,"tag":210,"props":438,"children":440},{"class":212,"line":439},26,[441],{"type":39,"tag":210,"props":442,"children":443},{},[444],{"type":45,"value":445},"    \"User reviews spec?\" -> \"Invoke writing-plans skill\" [label=\"approved\"];\n",{"type":39,"tag":210,"props":447,"children":449},{"class":212,"line":448},27,[450],{"type":39,"tag":210,"props":451,"children":452},{},[453],{"type":45,"value":454},"}\n",{"type":39,"tag":48,"props":456,"children":457},{},[458,463],{"type":39,"tag":96,"props":459,"children":460},{},[461],{"type":45,"value":462},"The terminal state is invoking writing-plans.",{"type":45,"value":464}," Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans.",{"type":39,"tag":65,"props":466,"children":468},{"id":467},"the-process",[469],{"type":45,"value":470},"The Process",{"type":39,"tag":48,"props":472,"children":473},{},[474],{"type":39,"tag":96,"props":475,"children":476},{},[477],{"type":45,"value":478},"Understanding the idea:",{"type":39,"tag":480,"props":481,"children":482},"ul",{},[483,488,493,498,503,508,513],{"type":39,"tag":92,"props":484,"children":485},{},[486],{"type":45,"value":487},"Check out the current project state first (files, docs, recent commits)",{"type":39,"tag":92,"props":489,"children":490},{},[491],{"type":45,"value":492},"Before asking detailed questions, assess scope: if the request describes multiple independent subsystems (e.g., \"build a platform with chat, file storage, billing, and analytics\"), flag this immediately. Don't spend questions refining details of a project that needs to be decomposed first.",{"type":39,"tag":92,"props":494,"children":495},{},[496],{"type":45,"value":497},"If the project is too large for a single spec, help the user decompose into sub-projects: what are the independent pieces, how do they relate, what order should they be built? Then brainstorm the first sub-project through the normal design flow. Each sub-project gets its own spec → plan → implementation cycle.",{"type":39,"tag":92,"props":499,"children":500},{},[501],{"type":45,"value":502},"For appropriately-scoped projects, ask questions one at a time to refine the idea",{"type":39,"tag":92,"props":504,"children":505},{},[506],{"type":45,"value":507},"Prefer multiple choice questions when possible, but open-ended is fine too",{"type":39,"tag":92,"props":509,"children":510},{},[511],{"type":45,"value":512},"Only one question per message - if a topic needs more exploration, break it into multiple questions",{"type":39,"tag":92,"props":514,"children":515},{},[516],{"type":45,"value":517},"Focus on understanding: purpose, constraints, success criteria",{"type":39,"tag":48,"props":519,"children":520},{},[521],{"type":39,"tag":96,"props":522,"children":523},{},[524],{"type":45,"value":525},"Exploring approaches:",{"type":39,"tag":480,"props":527,"children":528},{},[529,534,539],{"type":39,"tag":92,"props":530,"children":531},{},[532],{"type":45,"value":533},"Propose 2-3 different approaches with trade-offs",{"type":39,"tag":92,"props":535,"children":536},{},[537],{"type":45,"value":538},"Present options conversationally with your recommendation and reasoning",{"type":39,"tag":92,"props":540,"children":541},{},[542],{"type":45,"value":543},"Lead with your recommended option and explain why",{"type":39,"tag":48,"props":545,"children":546},{},[547],{"type":39,"tag":96,"props":548,"children":549},{},[550],{"type":45,"value":551},"Presenting the design:",{"type":39,"tag":480,"props":553,"children":554},{},[555,560,565,570,575],{"type":39,"tag":92,"props":556,"children":557},{},[558],{"type":45,"value":559},"Once you believe you understand what you're building, present the design",{"type":39,"tag":92,"props":561,"children":562},{},[563],{"type":45,"value":564},"Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced",{"type":39,"tag":92,"props":566,"children":567},{},[568],{"type":45,"value":569},"Ask after each section whether it looks right so far",{"type":39,"tag":92,"props":571,"children":572},{},[573],{"type":45,"value":574},"Cover: architecture, components, data flow, error handling, testing",{"type":39,"tag":92,"props":576,"children":577},{},[578],{"type":45,"value":579},"Be ready to go back and clarify if something doesn't make sense",{"type":39,"tag":48,"props":581,"children":582},{},[583],{"type":39,"tag":96,"props":584,"children":585},{},[586],{"type":45,"value":587},"Design for isolation and clarity:",{"type":39,"tag":480,"props":589,"children":590},{},[591,596,601,606],{"type":39,"tag":92,"props":592,"children":593},{},[594],{"type":45,"value":595},"Break the system into smaller units that each have one clear purpose, communicate through well-defined interfaces, and can be understood and tested independently",{"type":39,"tag":92,"props":597,"children":598},{},[599],{"type":45,"value":600},"For each unit, you should be able to answer: what does it do, how do you use it, and what does it depend on?",{"type":39,"tag":92,"props":602,"children":603},{},[604],{"type":45,"value":605},"Can someone understand what a unit does without reading its internals? Can you change the internals without breaking consumers? If not, the boundaries need work.",{"type":39,"tag":92,"props":607,"children":608},{},[609],{"type":45,"value":610},"Smaller, well-bounded units are also easier for you to work with - you reason better about code you can hold in context at once, and your edits are more reliable when files are focused. When a file grows large, that's often a signal that it's doing too much.",{"type":39,"tag":48,"props":612,"children":613},{},[614],{"type":39,"tag":96,"props":615,"children":616},{},[617],{"type":45,"value":618},"Working in existing codebases:",{"type":39,"tag":480,"props":620,"children":621},{},[622,627,632],{"type":39,"tag":92,"props":623,"children":624},{},[625],{"type":45,"value":626},"Explore the current structure before proposing changes. Follow existing patterns.",{"type":39,"tag":92,"props":628,"children":629},{},[630],{"type":45,"value":631},"Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in.",{"type":39,"tag":92,"props":633,"children":634},{},[635],{"type":45,"value":636},"Don't propose unrelated refactoring. Stay focused on what serves the current goal.",{"type":39,"tag":65,"props":638,"children":640},{"id":639},"after-the-design",[641],{"type":45,"value":642},"After the Design",{"type":39,"tag":48,"props":644,"children":645},{},[646],{"type":39,"tag":96,"props":647,"children":648},{},[649],{"type":45,"value":650},"Documentation:",{"type":39,"tag":480,"props":652,"children":653},{},[654,672,677],{"type":39,"tag":92,"props":655,"children":656},{},[657,659,664],{"type":45,"value":658},"Write the validated design (spec) to ",{"type":39,"tag":154,"props":660,"children":662},{"className":661},[],[663],{"type":45,"value":159},{"type":39,"tag":480,"props":665,"children":666},{},[667],{"type":39,"tag":92,"props":668,"children":669},{},[670],{"type":45,"value":671},"(User preferences for spec location override this default)",{"type":39,"tag":92,"props":673,"children":674},{},[675],{"type":45,"value":676},"Use elements-of-style:writing-clearly-and-concisely skill if available",{"type":39,"tag":92,"props":678,"children":679},{},[680],{"type":45,"value":681},"Commit the design document to git",{"type":39,"tag":48,"props":683,"children":684},{},[685,690],{"type":39,"tag":96,"props":686,"children":687},{},[688],{"type":45,"value":689},"Spec Self-Review:",{"type":45,"value":691},"\nAfter writing the spec document, look at it with fresh eyes:",{"type":39,"tag":88,"props":693,"children":694},{},[695,705,715,725],{"type":39,"tag":92,"props":696,"children":697},{},[698,703],{"type":39,"tag":96,"props":699,"children":700},{},[701],{"type":45,"value":702},"Placeholder scan:",{"type":45,"value":704}," Any \"TBD\", \"TODO\", incomplete sections, or vague requirements? Fix them.",{"type":39,"tag":92,"props":706,"children":707},{},[708,713],{"type":39,"tag":96,"props":709,"children":710},{},[711],{"type":45,"value":712},"Internal consistency:",{"type":45,"value":714}," Do any sections contradict each other? Does the architecture match the feature descriptions?",{"type":39,"tag":92,"props":716,"children":717},{},[718,723],{"type":39,"tag":96,"props":719,"children":720},{},[721],{"type":45,"value":722},"Scope check:",{"type":45,"value":724}," Is this focused enough for a single implementation plan, or does it need decomposition?",{"type":39,"tag":92,"props":726,"children":727},{},[728,733],{"type":39,"tag":96,"props":729,"children":730},{},[731],{"type":45,"value":732},"Ambiguity check:",{"type":45,"value":734}," Could any requirement be interpreted two different ways? If so, pick one and make it explicit.",{"type":39,"tag":48,"props":736,"children":737},{},[738],{"type":45,"value":739},"Fix any issues inline. No need to re-review — just fix and move on.",{"type":39,"tag":48,"props":741,"children":742},{},[743,748],{"type":39,"tag":96,"props":744,"children":745},{},[746],{"type":45,"value":747},"User Review Gate:",{"type":45,"value":749},"\nAfter the spec review loop passes, ask the user to review the written spec before proceeding:",{"type":39,"tag":751,"props":752,"children":753},"blockquote",{},[754],{"type":39,"tag":48,"props":755,"children":756},{},[757,759,765],{"type":45,"value":758},"\"Spec written and committed to ",{"type":39,"tag":154,"props":760,"children":762},{"className":761},[],[763],{"type":45,"value":764},"\u003Cpath>",{"type":45,"value":766},". Please review it and let me know if you want to make any changes before we start writing out the implementation plan.\"",{"type":39,"tag":48,"props":768,"children":769},{},[770],{"type":45,"value":771},"Wait for the user's response. If they request changes, make them and re-run the spec review loop. Only proceed once the user approves.",{"type":39,"tag":48,"props":773,"children":774},{},[775],{"type":39,"tag":96,"props":776,"children":777},{},[778],{"type":45,"value":779},"Implementation:",{"type":39,"tag":480,"props":781,"children":782},{},[783,788],{"type":39,"tag":92,"props":784,"children":785},{},[786],{"type":45,"value":787},"Invoke the writing-plans skill to create a detailed implementation plan",{"type":39,"tag":92,"props":789,"children":790},{},[791],{"type":45,"value":792},"Do NOT invoke any other skill. writing-plans is the next step.",{"type":39,"tag":65,"props":794,"children":796},{"id":795},"key-principles",[797],{"type":45,"value":798},"Key Principles",{"type":39,"tag":480,"props":800,"children":801},{},[802,812,822,832,842,852],{"type":39,"tag":92,"props":803,"children":804},{},[805,810],{"type":39,"tag":96,"props":806,"children":807},{},[808],{"type":45,"value":809},"One question at a time",{"type":45,"value":811}," - Don't overwhelm with multiple questions",{"type":39,"tag":92,"props":813,"children":814},{},[815,820],{"type":39,"tag":96,"props":816,"children":817},{},[818],{"type":45,"value":819},"Multiple choice preferred",{"type":45,"value":821}," - Easier to answer than open-ended when possible",{"type":39,"tag":92,"props":823,"children":824},{},[825,830],{"type":39,"tag":96,"props":826,"children":827},{},[828],{"type":45,"value":829},"YAGNI ruthlessly",{"type":45,"value":831}," - Remove unnecessary features from all designs",{"type":39,"tag":92,"props":833,"children":834},{},[835,840],{"type":39,"tag":96,"props":836,"children":837},{},[838],{"type":45,"value":839},"Explore alternatives",{"type":45,"value":841}," - Always propose 2-3 approaches before settling",{"type":39,"tag":92,"props":843,"children":844},{},[845,850],{"type":39,"tag":96,"props":846,"children":847},{},[848],{"type":45,"value":849},"Incremental validation",{"type":45,"value":851}," - Present design, get approval before moving on",{"type":39,"tag":92,"props":853,"children":854},{},[855,860],{"type":39,"tag":96,"props":856,"children":857},{},[858],{"type":45,"value":859},"Be flexible",{"type":45,"value":861}," - Go back and clarify when something doesn't make sense",{"type":39,"tag":65,"props":863,"children":865},{"id":864},"visual-companion",[866],{"type":45,"value":867},"Visual Companion",{"type":39,"tag":48,"props":869,"children":870},{},[871],{"type":45,"value":872},"A browser-based companion for showing mockups, diagrams, and visual options during brainstorming. Available as a tool — not a mode. Accepting the companion means it's available for questions that benefit from visual treatment; it does NOT mean every question goes through the browser.",{"type":39,"tag":48,"props":874,"children":875},{},[876,881],{"type":39,"tag":96,"props":877,"children":878},{},[879],{"type":45,"value":880},"Offering the companion:",{"type":45,"value":882}," When you anticipate that upcoming questions will involve visual content (mockups, layouts, diagrams), offer it once for consent:",{"type":39,"tag":751,"props":884,"children":885},{},[886],{"type":39,"tag":48,"props":887,"children":888},{},[889],{"type":45,"value":890},"\"Some of what we're working on might be easier to explain if I can show it to you in a web browser. I can put together mockups, diagrams, comparisons, and other visuals as we go. This feature is still new and can be token-intensive. Want to try it? (Requires opening a local URL)\"",{"type":39,"tag":48,"props":892,"children":893},{},[894,899],{"type":39,"tag":96,"props":895,"children":896},{},[897],{"type":45,"value":898},"This offer MUST be its own message.",{"type":45,"value":900}," Do not combine it with clarifying questions, context summaries, or any other content. The message should contain ONLY the offer above and nothing else. Wait for the user's response before continuing. If they decline, proceed with text-only brainstorming.",{"type":39,"tag":48,"props":902,"children":903},{},[904,909,911],{"type":39,"tag":96,"props":905,"children":906},{},[907],{"type":45,"value":908},"Per-question decision:",{"type":45,"value":910}," Even after the user accepts, decide FOR EACH QUESTION whether to use the browser or the terminal. The test: ",{"type":39,"tag":96,"props":912,"children":913},{},[914],{"type":45,"value":915},"would the user understand this better by seeing it than reading it?",{"type":39,"tag":480,"props":917,"children":918},{},[919,929],{"type":39,"tag":92,"props":920,"children":921},{},[922,927],{"type":39,"tag":96,"props":923,"children":924},{},[925],{"type":45,"value":926},"Use the browser",{"type":45,"value":928}," for content that IS visual — mockups, wireframes, layout comparisons, architecture diagrams, side-by-side visual designs",{"type":39,"tag":92,"props":930,"children":931},{},[932,937],{"type":39,"tag":96,"props":933,"children":934},{},[935],{"type":45,"value":936},"Use the terminal",{"type":45,"value":938}," for content that is text — requirements questions, conceptual choices, tradeoff lists, A\u002FB\u002FC\u002FD text options, scope decisions",{"type":39,"tag":48,"props":940,"children":941},{},[942],{"type":45,"value":943},"A question about a UI topic is not automatically a visual question. \"What does personality mean in this context?\" is a conceptual question — use the terminal. \"Which wizard layout works better?\" is a visual question — use the browser.",{"type":39,"tag":48,"props":945,"children":946},{},[947,949],{"type":45,"value":948},"If they agree to the companion, read the detailed guide before proceeding:\n",{"type":39,"tag":154,"props":950,"children":952},{"className":951},[],[953],{"type":45,"value":954},"skills\u002Fbrainstorming\u002Fvisual-companion.md",{"type":39,"tag":956,"props":957,"children":958},"style",{},[959],{"type":45,"value":960},"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":962,"total":1165},[963,984,1007,1024,1040,1059,1078,1092,1108,1122,1134,1149],{"slug":964,"name":964,"fn":965,"description":966,"org":967,"tags":968,"stars":981,"repoUrl":982,"updatedAt":983},"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},[969,972,975,978],{"name":970,"slug":971,"type":15},"Documents","documents",{"name":973,"slug":974,"type":15},"Healthcare","healthcare",{"name":976,"slug":977,"type":15},"Insurance","insurance",{"name":979,"slug":980,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":985,"name":985,"fn":986,"description":987,"org":988,"tags":989,"stars":1004,"repoUrl":1005,"updatedAt":1006},"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},[990,993,995,998,1001],{"name":991,"slug":992,"type":15},".NET","dotnet",{"name":994,"slug":985,"type":15},"ASP.NET Core",{"name":996,"slug":997,"type":15},"Blazor","blazor",{"name":999,"slug":1000,"type":15},"C#","csharp",{"name":1002,"slug":1003,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1008,"name":1008,"fn":1009,"description":1010,"org":1011,"tags":1012,"stars":1004,"repoUrl":1005,"updatedAt":1023},"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},[1013,1016,1019,1022],{"name":1014,"slug":1015,"type":15},"Apps SDK","apps-sdk",{"name":1017,"slug":1018,"type":15},"ChatGPT","chatgpt",{"name":1020,"slug":1021,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1025,"name":1025,"fn":1026,"description":1027,"org":1028,"tags":1029,"stars":1004,"repoUrl":1005,"updatedAt":1039},"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},[1030,1033,1036],{"name":1031,"slug":1032,"type":15},"API Development","api-development",{"name":1034,"slug":1035,"type":15},"CLI","cli",{"name":1037,"slug":1038,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1041,"name":1041,"fn":1042,"description":1043,"org":1044,"tags":1045,"stars":1004,"repoUrl":1005,"updatedAt":1058},"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},[1046,1049,1052,1055],{"name":1047,"slug":1048,"type":15},"Cloudflare","cloudflare",{"name":1050,"slug":1051,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1053,"slug":1054,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1056,"slug":1057,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1060,"name":1060,"fn":1061,"description":1062,"org":1063,"tags":1064,"stars":1004,"repoUrl":1005,"updatedAt":1077},"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},[1065,1068,1071,1074],{"name":1066,"slug":1067,"type":15},"Productivity","productivity",{"name":1069,"slug":1070,"type":15},"Project Management","project-management",{"name":1072,"slug":1073,"type":15},"Strategy","strategy",{"name":1075,"slug":1076,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1079,"name":1079,"fn":1080,"description":1081,"org":1082,"tags":1083,"stars":1004,"repoUrl":1005,"updatedAt":1091},"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},[1084,1085,1087,1090],{"name":20,"slug":21,"type":15},{"name":1086,"slug":1079,"type":15},"Figma",{"name":1088,"slug":1089,"type":15},"Frontend","frontend",{"name":1020,"slug":1021,"type":15},"2026-04-12T05:06:47.939943",{"slug":1093,"name":1093,"fn":1094,"description":1095,"org":1096,"tags":1097,"stars":1004,"repoUrl":1005,"updatedAt":1107},"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},[1098,1099,1102,1103,1104],{"name":20,"slug":21,"type":15},{"name":1100,"slug":1101,"type":15},"Design System","design-system",{"name":1086,"slug":1079,"type":15},{"name":1088,"slug":1089,"type":15},{"name":1105,"slug":1106,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":1109,"name":1109,"fn":1110,"description":1111,"org":1112,"tags":1113,"stars":1004,"repoUrl":1005,"updatedAt":1121},"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},[1114,1115,1116,1119,1120],{"name":20,"slug":21,"type":15},{"name":1100,"slug":1101,"type":15},{"name":1117,"slug":1118,"type":15},"Documentation","documentation",{"name":1086,"slug":1079,"type":15},{"name":1088,"slug":1089,"type":15},"2026-05-16T06:07:47.821474",{"slug":1123,"name":1123,"fn":1124,"description":1125,"org":1126,"tags":1127,"stars":1004,"repoUrl":1005,"updatedAt":1133},"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},[1128,1129,1130,1131,1132],{"name":20,"slug":21,"type":15},{"name":1086,"slug":1079,"type":15},{"name":1088,"slug":1089,"type":15},{"name":1105,"slug":1106,"type":15},{"name":1002,"slug":1003,"type":15},"2026-05-16T06:07:40.583615",{"slug":1135,"name":1135,"fn":1136,"description":1137,"org":1138,"tags":1139,"stars":1004,"repoUrl":1005,"updatedAt":1148},"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},[1140,1143,1144,1147],{"name":1141,"slug":1142,"type":15},"Animation","animation",{"name":1037,"slug":1038,"type":15},{"name":1145,"slug":1146,"type":15},"Creative","creative",{"name":20,"slug":21,"type":15},"2026-05-02T05:31:48.48485",{"slug":1150,"name":1150,"fn":1151,"description":1152,"org":1153,"tags":1154,"stars":1004,"repoUrl":1005,"updatedAt":1164},"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},[1155,1156,1157,1160,1163],{"name":1145,"slug":1146,"type":15},{"name":20,"slug":21,"type":15},{"name":1158,"slug":1159,"type":15},"Image Generation","image-generation",{"name":1161,"slug":1162,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675,{"items":1167,"total":1281},[1168,1185,1201,1213,1231,1249,1269],{"slug":1169,"name":1169,"fn":1170,"description":1171,"org":1172,"tags":1173,"stars":22,"repoUrl":23,"updatedAt":1184},"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},[1174,1177,1180,1183],{"name":1175,"slug":1176,"type":15},"Accessibility","accessibility",{"name":1178,"slug":1179,"type":15},"Charts","charts",{"name":1181,"slug":1182,"type":15},"Data Visualization","data-visualization",{"name":20,"slug":21,"type":15},"2026-06-30T19:00:57.102",{"slug":1186,"name":1186,"fn":1187,"description":1188,"org":1189,"tags":1190,"stars":22,"repoUrl":23,"updatedAt":1200},"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},[1191,1194,1197],{"name":1192,"slug":1193,"type":15},"Agents","agents",{"name":1195,"slug":1196,"type":15},"Browser Automation","browser-automation",{"name":1198,"slug":1199,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":1202,"name":1202,"fn":1203,"description":1204,"org":1205,"tags":1206,"stars":22,"repoUrl":23,"updatedAt":1212},"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},[1207,1208,1211],{"name":1195,"slug":1196,"type":15},{"name":1209,"slug":1210,"type":15},"Local Development","local-development",{"name":1198,"slug":1199,"type":15},"2026-04-06T18:41:17.526867",{"slug":1214,"name":1214,"fn":1215,"description":1216,"org":1217,"tags":1218,"stars":22,"repoUrl":23,"updatedAt":1230},"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},[1219,1220,1221,1224,1227],{"name":1192,"slug":1193,"type":15},{"name":1053,"slug":1054,"type":15},{"name":1222,"slug":1223,"type":15},"SDK","sdk",{"name":1225,"slug":1226,"type":15},"Serverless","serverless",{"name":1228,"slug":1229,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":1232,"name":1232,"fn":1233,"description":1234,"org":1235,"tags":1236,"stars":22,"repoUrl":23,"updatedAt":1248},"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},[1237,1238,1241,1244,1245],{"name":1088,"slug":1089,"type":15},{"name":1239,"slug":1240,"type":15},"React","react",{"name":1242,"slug":1243,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":1105,"slug":1106,"type":15},{"name":1246,"slug":1247,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":1250,"name":1250,"fn":1251,"description":1252,"org":1253,"tags":1254,"stars":22,"repoUrl":23,"updatedAt":1268},"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},[1255,1258,1261,1264,1267],{"name":1256,"slug":1257,"type":15},"AI Infrastructure","ai-infrastructure",{"name":1259,"slug":1260,"type":15},"Cost Optimization","cost-optimization",{"name":1262,"slug":1263,"type":15},"LLM","llm",{"name":1265,"slug":1266,"type":15},"Performance","performance",{"name":1246,"slug":1247,"type":15},"2026-04-06T18:40:44.377464",{"slug":1270,"name":1270,"fn":1271,"description":1272,"org":1273,"tags":1274,"stars":22,"repoUrl":23,"updatedAt":1280},"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},[1275,1276,1279],{"name":1259,"slug":1260,"type":15},{"name":1277,"slug":1278,"type":15},"Database","database",{"name":1262,"slug":1263,"type":15},"2026-04-06T18:41:08.513425",600]