[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BX4Y45AMD2VH4BPJV7WQN0":3,"skill-same:01M6BX4Y45AMD2VH4BPJV7WQN0":87},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6BX4Y45AMD2VH4BPJV7WQN0","grilling",null,"Resolve material product and design decisions before planning or implementing an ambiguous large feature. Use when the user asks to be grilled or when several valid interpretations would produce meaningfully different behavior, architecture, cost, or migration work; do not use for questions, small changes, or facts the repository can answer.","yrahul3910\u002Fdotfiles","yrahul3910","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F8930954?v=4","01M6BX4Q28SQREB3XFY3BAQ6YC","Rahul Yedida","01M6BX4Q737JXBCN69KPPT5TG9",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fyrahul3910\u002Fdotfiles\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Fgrilling\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"cost","when","changes","for","implementing","facts","can","answer","material","feature","do","design","use","decisions","work","repository","produce","product","planning","architecture","valid","2026-11-10 10:12:30",false,"---\nname: create-prototype\ndescription: \"Builds new UI prototypes and makes targeted changes to existing prototypes using consumer-owned context. Use when asked to build a prototype, mock up a UI, or add, change, refine or recreate part of an existing prototype. Do not use for unrelated tasks, routine commands, Git lifecycle actions, acknowledgements or infrastructure work.\"\n---\n\n# Create prototype\n\nWhen asked to create controls for variants, scenarios, adjustable previews or data-source\nswitches, read the adjacent [prototype-controls skill](..\u002Fprototype-controls\u002FSKILL.md),\neven when the request never says \"canvas controls\". Product UI form fields and\nfilters alone stay in this skill. Controls guidance does not establish panel availability.\n\n## Dispatch before reading workflows\n\nDetermine the branch from the original request, prior answers and current\ntarget before loading any workflow files. Use a short, targeted lookup of\nconsumer repository instructions or the named target if needed, not a broad\nrepository tour. The word \"new\" alone does not decide: \"add a new tab to this\nprototype\" is iteration.\n\n| Request                                                                                           | Required read, only for this branch                                              |\n| ------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- |\n| Clear new build, such as \"build an offline inventory prototype\"                                   | [create](.\u002Fworkflows\u002Fcreate.md)                                                  |\n| Change to an existing prototype, such as \"add filtering to this page\"                             | [iterate](.\u002Fworkflows\u002Fiterate.md)                                                |\n| Candidate narrow edit to an existing prototype                                                   | [iterate](.\u002Fworkflows\u002Fiterate.md), then apply the root instructions' narrow-edit path |\n| Consequential missing information, including an unresolved target or create-versus-iterate choice | [clarify](.\u002Fworkflows\u002Fclarify.md), then the selected build or iteration workflow |\n| Behavior-preserving test-only work                                                                | Use the root instructions' task-scope guidance; do not load a prototype workflow |\n| Unrelated task or routine command                                                                 | Stop using this skill and continue the original task                             |\n\nLoad only the selected workflow, not all companions as a required-read bundle.\nClarification is conditional, not a startup step. Either build or iteration\ncan need it later, but a clear request skips it entirely. Do not load the\nother branch for orientation. If the selected companion is missing, report its\nexact installed path and stop. Do not improvise it or use the other branch.\n\nPreserve the original request and every answer in session context throughout\nthe work. A choice answers only its question, not unrelated scope. There is no\nmandatory brief file, schema, build-mode quiz or separate intake skill.\n\nStay in the current target and worktree unless the user explicitly requests a\ndifferent destination. A reference URL is not permission to fork, duplicate,\npublish, delete or activate anything. Approved references are 1:1 requirements\nexcept for the requested delta, not design inspiration.\n\nThe selected create or normal iteration workflow reads the shared\n[authoring reference](.\u002Freferences\u002Fauthoring.md) before implementation. A\ncandidate narrow edit follows the iteration workflow's classification step and,\nwhen eligible, skips that reference and its context dependencies.\nIt owns context resolution, design evidence, data boundaries and completion.\nIt does not load another workflow. Install `product-design`, `setup-skills`\nand the `context-templates` library alongside this skill.\nMissing installed dependencies stop\nthe affected work with their exact paths, never trigger automatic installation.\n\nContext research uses the centralized library through setup-skills.\nThe shared authoring reference declares this consumer's context reads. Templates are setup\ninputs, not additional per-task reads or active product facts.\n","# Create prototype\n\nWhen asked to create controls for variants, scenarios, adjustable previews or data-source\nswitches, read the adjacent [prototype-controls skill](..\u002Fprototype-controls\u002FSKILL.md),\neven when the request never says \"canvas controls\". Product UI form fields and\nfilters alone stay in this skill. Controls guidance does not establish panel availability.\n\n## Dispatch before reading workflows\n\nDetermine the branch from the original request, prior answers and current\ntarget before loading any workflow files. Use a short, targeted lookup of\nconsumer repository instructions or the named target if needed, not a broad\nrepository tour. The word \"new\" alone does not decide: \"add a new tab to this\nprototype\" is iteration.\n\n| Request                                                                                           | Required read, only for this branch                                              |\n| ------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- |\n| Clear new build, such as \"build an offline inventory prototype\"                                   | [create](.\u002Fworkflows\u002Fcreate.md)                                                  |\n| Change to an existing prototype, such as \"add filtering to this page\"                             | [iterate](.\u002Fworkflows\u002Fiterate.md)                                                |\n| Candidate narrow edit to an existing prototype                                                   | [iterate](.\u002Fworkflows\u002Fiterate.md), then apply the root instructions' narrow-edit path |\n| Consequential missing information, including an unresolved target or create-versus-iterate choice | [clarify](.\u002Fworkflows\u002Fclarify.md), then the selected build or iteration workflow |\n| Behavior-preserving test-only work                                                                | Use the root instructions' task-scope guidance; do not load a prototype workflow |\n| Unrelated task or routine command                                                                 | Stop using this skill and continue the original task                             |\n\nLoad only the selected workflow, not all companions as a required-read bundle.\nClarification is conditional, not a startup step. Either build or iteration\ncan need it later, but a clear request skips it entirely. Do not load the\nother branch for orientation. If the selected companion is missing, report its\nexact installed path and stop. Do not improvise it or use the other branch.\n\nPreserve the original request and every answer in session context throughout\nthe work. A choice answers only its question, not unrelated scope. There is no\nmandatory brief file, schema, build-mode quiz or separate intake skill.\n\nStay in the current target and worktree unless the user explicitly requests a\ndifferent destination. A reference URL is not permission to fork, duplicate,\npublish, delete or activate anything. Approved references are 1:1 requirements\nexcept for the requested delta, not design inspiration.\n\nThe selected create or normal iteration workflow reads the shared\n[authoring reference](.\u002Freferences\u002Fauthoring.md) before implementation. A\ncandidate narrow edit follows the iteration workflow's classification step and,\nwhen eligible, skips that reference and its context dependencies.\nIt owns context resolution, design evidence, data boundaries and completion.\nIt does not load another workflow. Install `product-design`, `setup-skills`\nand the `context-templates` library alongside this skill.\nMissing installed dependencies stop\nthe affected work with their exact paths, never trigger automatic installation.\n\nContext research uses the centralized library through setup-skills.\nThe shared authoring reference declares this consumer's context reads. Templates are setup\ninputs, not additional per-task reads or active product facts.\n",{"name":45,"description":46},"create-prototype","Builds new UI prototypes and makes targeted changes to existing prototypes using consumer-owned context. Use when asked to build a prototype, mock up a UI, or add, change, refine or recreate part of an existing prototype. Do not use for unrelated tasks, routine commands, Git lifecycle actions, acknowledgements or infrastructure work.","main","0e8bdbd952ce0d93c8976876fa59e9f119614ae8",".agents\u002Fskills\u002Fgrilling","https:\u002F\u002Fgithub.com\u002Fyrahul3910\u002Fdotfiles","https:\u002F\u002Fgithub.com\u002Fyrahul3910","https:\u002F\u002Fryedida.me","CS PhD @ NC State; Sr. Data Scientist @ LexisNexis","2026-11-13 01:37:12",{"source":8,"skillName":45,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add yrahul3910\u002Fdotfiles --skill create-prototype",{"tool":61,"command":62},"bunx","bunx skills add yrahul3910\u002Fdotfiles --skill create-prototype",{"tool":64,"command":65},"pnpm","pnpm dlx skills add yrahul3910\u002Fdotfiles --skill create-prototype","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fyrahul3910\u002Fdotfiles\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Fgrilling\u002FSKILL.md",true,[69,75,79,83],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fauthoring.md","REFERENCE","参考文档",12259,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Freplica\u002Fblob\u002Fmain\u002Fstarters\u002Fshared\u002F.agents\u002Fskills\u002Fcreate-prototype\u002Freferences\u002Fauthoring.md",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"workflows\u002Fclarify.md",2198,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Freplica\u002Fblob\u002Fmain\u002Fstarters\u002Fshared\u002F.agents\u002Fskills\u002Fcreate-prototype\u002Fworkflows\u002Fclarify.md",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"workflows\u002Fcreate.md",2986,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Freplica\u002Fblob\u002Fmain\u002Fstarters\u002Fshared\u002F.agents\u002Fskills\u002Fcreate-prototype\u002Fworkflows\u002Fcreate.md",{"path":84,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":85,"sourceHtmlUrl":86},"workflows\u002Fiterate.md",2901,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Freplica\u002Fblob\u002Fmain\u002Fstarters\u002Fshared\u002F.agents\u002Fskills\u002Fcreate-prototype\u002Fworkflows\u002Fiterate.md",[88,117,149,179,200,229],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":40},"01M6BX5T7VBBNA50W28PGXFVBK","pr-babysit","Watch a GitHub pull request through CI and bot reviews (Copilot, Codex, Claude, Greptile), fix feedback locally as it arrives, and push only once everything has settled. Use when asked to babysit, shepherd, or watch a PR until it is green and reviewed. Not for a one-off look at PR comments or CI status.","https:\u002F\u002Fgithub.com\u002Fyrahul3910\u002Fdotfiles\u002Fblob\u002Fmaster\u002F.pi\u002Fagent\u002Fskills\u002Fpr-babysit\u002FSKILL.md",[],[95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,31,111,112,113,114,115,116,22,20],"pr","pr babysit","babysit","bot","github","codex","status","copilot","pull request","pull","push","ci","pr comments","feedback","ci status","fix","only","green","shepherd","as","comments","reviews",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":40},"01M6BX5PZTGZCZMWB46DEZY1RB","okf","Read, create, and update Open Knowledge Format (OKF) knowledge bundles — wikis of markdown concept files with YAML frontmatter, per Google's OKF v0.1 spec. Use when browsing or consuming an OKF bundle, when asked to create a knowledge wiki for a codebase or data system, or when editing a directory of .md files that carry `type:` frontmatter alongside index.md\u002Flog.md files. Covers the frontmatter schema, bundle-root-relative linking, index.md maintenance, and log.md changelog conventions.","https:\u002F\u002Fgithub.com\u002Fyrahul3910\u002Fdotfiles\u002Fblob\u002Fmaster\u002F.pi\u002Fagent\u002Fskills\u002Fokf\u002FSKILL.md",[],[119,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,31,140,141,142,143,144,145,146,147,22,148,20],"directory","google","spec","create","update","changelog","index","yaml","data","open","markdown","wiki","knowledge","system","format","editing","schema","maintenance","log","files","type","wikis","with","concept","browsing",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":165,"publishedAt":40},"01M6BX5MWN3YRXQ447DBGGTHM5","design-doc","Write an explicit design document, RFC, or consequential architecture proposal with adversarial review. Use for decisions with material ownership, compatibility, migration, or operational consequences. Do not activate for ordinary comparisons, syntax questions, or small implementation choices.","https:\u002F\u002Fgithub.com\u002Fyrahul3910\u002Fdotfiles\u002Fblob\u002Fmaster\u002F.pi\u002Fagent\u002Fskills\u002Fdesign-doc\u002FSKILL.md",[155,160],{"categoryNo":156,"categoryName":157,"taxonomyType":158,"taxonomyTypeDesc":159},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":161,"categoryName":162,"taxonomyType":163,"taxonomyTypeDesc":164},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[30,166,167,168,38,169,170,171,32,172,31,173,174,175,29,27,176,146,177,22,178],"doc","design doc","review","adversarial review","RFC","syntax","write","migration","document","activate","proposal","questions","adversarial",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":40},"01M6BX5K2H9A93MD355DKQ21MV","background-terminals","Run and manage long-lived shell commands in background terminals. Use for dev servers, watchers, streaming builds, and other commands that should keep running while the agent continues working.","https:\u002F\u002Fgithub.com\u002Fyrahul3910\u002Fdotfiles\u002Fblob\u002Fmaster\u002F.pi\u002Fagent\u002Fskills\u002Fbackground-terminals\u002FSKILL.md",[],[186,187,188,189,190,191,31,192,193,194,195,196,197,22,198,199],"background terminals","background","run","dev","streaming","shell","manage","commands","watchers","long","keep","dev servers","servers","running",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":215,"publishedAt":40},"01M6BX5H39CTKJKDXRA35MNGRW","writing-for-agents","Write or revise skills, AGENTS.md, CLAUDE.md, prompts, and other instructions consumed by coding agents. Use when agent behavior, skill routing, instruction structure, or prompt maintenance is part of the task.","https:\u002F\u002Fgithub.com\u002Fyrahul3910\u002Fdotfiles\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[206,209,212],{"categoryNo":207,"categoryName":208,"taxonomyType":158,"taxonomyTypeDesc":159},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":210,"categoryName":211,"taxonomyType":158,"taxonomyTypeDesc":159},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":213,"categoryName":214,"taxonomyType":163,"taxonomyTypeDesc":164},"01JBSEEDCAT000000000000036","内容创作者",[216,217,22,218,219,220,221,172,222,223,31,224,141,225,226,227,228,20],"writing","writing for agents","coding agents","routing","coding","prompt","instructions","behavior","prompts","task","structure","revise","skill routing",{"skillNo":230,"name":231,"nameZh":6,"description":232,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":233,"categories":234,"keywords":235,"publishedAt":40},"01M6BX5FE0MPK7EXN5ZT590428","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fyrahul3910\u002Fdotfiles\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[236,237,238,239,240,241,242,243,244,245],"wait what","wait","land","stop","message","pitch","it","re","last","true"]