[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FXX56AY9JMZATRFSZ2PVTS":3,"skill-same:01M6FXX56AY9JMZATRFSZ2PVTS":79},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6FXX56AY9JMZATRFSZ2PVTS","create-ui-experiment",null,"Own clickable UI experiment routes or project-native lightweight prototypes for one approved UI branch, using fake, fixture, local, or in-memory data to test the branch's first-value journey before prototype build-plan synthesis, UAT, or production planning.","GeorgeQLe\u002Fagentic-skills","GeorgeQLe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F21134126?v=4","01M6D2JP418S0VGJGF8M93EC3H","George Le","01M6D2JPBAKYD82TA5FS6HKQ3D",1,"MIT","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fproduct-design\u002Fcodex\u002Fbuild-ui-screens\u002Farchive\u002Fv0.0\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"create ui experiment","create","ui","experiment","plan","project","fixture","local","journey","alignment","branch","page","design","loop","first","execution","planning","test","prototype","memory","2026-11-10 10:12:30",false,"---\nname: create-ui-experiment\ndescription: Own clickable UI experiment routes or project-native lightweight prototypes for one approved UI branch, using fake, fixture, local, or in-memory data to test the branch's first-value journey before prototype build-plan synthesis, UAT, or production planning.\ntype: execution\nversion: v0.0\nrequired_conventions: [alignment-page, design-tree-loop]\nargument-hint: \"[approved-ui-experiment]\"\ncontext_intake: scoped\nvisual_tier: prototype\n---\n\n# Create UI Experiment\n\nInvoke as `$create-ui-experiment`.\n\nOwn clickable UI experiment routes or project-native lightweight prototypes for one approved UI branch. Use this skill after `$ui-interview [specific-ux-variation]` approves a UI experiment branch and the branch needs a clickable first-value route before the broader `$prototype` build ledger or production planning exists.\n\nThis skill is an experiment owner, not a default buildout path. It tests whether one approved branch's first-value journey works when the user can click through it with fake, fixture, local, or in-memory data. It must not introduce durable database\u002Fstorage, auth, payments, analytics, deployment, admin tooling, multi-tenancy, production observability, or other production infrastructure.\n\nFollow `DESIGN-TREE-LOOP.md` for design-tree routing, state storage, branch decisions, approval boundaries, and task classification. UI experiment branch state belongs in `design\u002F**\u002Fflow-tree-*.yaml`, not `tasks\u002Ftodo.md`.\n\n## Gate\n\nBefore building, verify the approved branch is explicit:\n\n- Read `design\u002F**\u002Fflow-tree-*.yaml` and resolve the named `ui_experiments[]` branch. If `$ARGUMENTS` is missing, choose the first approved UI experiment branch that has no clickable experiment evidence, honoring any recorded branch-order override.\n- Read the branch packet from `design\u002Fui-[topic].md`, `design\u002Fui-requirements-[topic].md`, or product-path-scoped equivalents.\n- Read the parent `design\u002Fux-variations-[topic].md`, `design\u002Fuser-flow-[topic].md`, and any relevant `design\u002Fdesign-inspirations-{topic}.md` when present.\n- Stop if no UI branch has an explicit approve decision. Route back to `$ui-interview [specific-ux-variation]`.\n- Stop if the requested work needs production infrastructure. Record the deferred infrastructure and route to prototype evidence first.\n\n## Process\n\n1. **Resolve scope.** Identify the product path, topic, parent user-flow branch, UX variation branch, and approved UI experiment branch. Preserve branch IDs from the flow-tree manifest.\n2. **Define the first-value journey.** Name the first-value moment, the primary task path, the entry route, the exit\u002Fsuccess state, and the evidence needed before moving deeper.\n3. **Choose the experiment home.** Prefer a project-native lightweight route when the app already has a safe local experiment surface. Otherwise create a disposable route under `experiments\u002F{topic}\u002F{ui-experiment-id}\u002F`. Keep the experiment easy to remove.\n4. **Build the clickable path.** Implement only the minimum interaction needed for a user to experience the first-value journey. Use fake, fixture, local, or in-memory data. Include realistic states only when they clarify the primary path.\n5. **Progressive reveal.** Introduce first value and the primary task path before dense secondary controls. Hide, defer, or stub secondary controls until the route proves the core journey.\n6. **Review evidence.** Produce a concise review note naming what the user should click, what decision the experiment tests, what worked, what remains unknown, and which deferred infrastructure stays out of scope.\n7. **Update branch state.** Add the experiment path and evidence note to the relevant `ui_experiments[]` branch in the flow-tree manifest. Do not create or update the prototype build plan unless the current run has explicit review evidence approving the experiment.\n8. **Build the alignment page.** Render the route, first-value journey, fake-data boundary, deferred infrastructure, and review gate in `alignment\u002Fcreate-ui-experiment-{topic}.html`.\n\n## Output\n\nThe skill may create or update:\n\n```text\nexperiments\u002F{topic}\u002F{ui-experiment-id}\u002F\ndesign\u002F**\u002Fflow-tree-*.yaml\nalignment\u002Fcreate-ui-experiment-{topic}.html\n```\n\nWhen using a project-native route instead of `experiments\u002F`, record the exact route path in the flow-tree manifest and in the alignment page.\n\n## Next Work\n\nAfter explicit review evidence exists, route based on what the evidence supports:\n\n- `$user-flow-map --prototype-build-plan [topic]` when approved UI experiments are ready to become prototype build-plan items.\n- `$prototype` when a prototype build plan already exists and names the approved UI experiment item.\n- `$uat --variant-evaluation` when the clickable experiment itself is being used as the evaluated variant artifact.\n\nDo not route to production planning, roadmap work, or durable infrastructure until experiment review evidence explicitly promotes the branch.\n\n## Constraints\n\n- Use fake, fixture, local, or in-memory data only.\n- Build one approved UI experiment branch per run.\n- Keep the route disposable and bounded to the first-value journey.\n- Use progressive reveal; do not expose dense secondary controls before the primary task path works.\n- Do not build production infrastructure, external account integrations, deployment automation, or durable storage.\n- Do not skip the review evidence gate before handing off to `$prototype`, `$uat --variant-evaluation`, or `$user-flow-map --prototype-build-plan`.\n- When recommending a skill from another pack, verify the pack is installed via `.agents\u002Fproject.json` `enabled_packs`. If not installed, recommend `npx skillpacks install \u003Cpack-name>` from the project shell before the target skill.\n\n## Alignment Page\n\nWhen this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment\u002Fcreate-ui-experiment-{topic}.html`.\n\nThe page must show the first-value journey, primary task path, clickable route path, fake-data boundary, deferred infrastructure, review evidence, and the exact downstream handoff gate.\n\n## Default Shipping Contract\n\nFollow the shared shipping contract convention in CLAUDE.md.\n","# Create UI Experiment\n\nInvoke as `$create-ui-experiment`.\n\nOwn clickable UI experiment routes or project-native lightweight prototypes for one approved UI branch. Use this skill after `$ui-interview [specific-ux-variation]` approves a UI experiment branch and the branch needs a clickable first-value route before the broader `$prototype` build ledger or production planning exists.\n\nThis skill is an experiment owner, not a default buildout path. It tests whether one approved branch's first-value journey works when the user can click through it with fake, fixture, local, or in-memory data. It must not introduce durable database\u002Fstorage, auth, payments, analytics, deployment, admin tooling, multi-tenancy, production observability, or other production infrastructure.\n\nFollow `DESIGN-TREE-LOOP.md` for design-tree routing, state storage, branch decisions, approval boundaries, and task classification. UI experiment branch state belongs in `design\u002F**\u002Fflow-tree-*.yaml`, not `tasks\u002Ftodo.md`.\n\n## Gate\n\nBefore building, verify the approved branch is explicit:\n\n- Read `design\u002F**\u002Fflow-tree-*.yaml` and resolve the named `ui_experiments[]` branch. If `$ARGUMENTS` is missing, choose the first approved UI experiment branch that has no clickable experiment evidence, honoring any recorded branch-order override.\n- Read the branch packet from `design\u002Fui-[topic].md`, `design\u002Fui-requirements-[topic].md`, or product-path-scoped equivalents.\n- Read the parent `design\u002Fux-variations-[topic].md`, `design\u002Fuser-flow-[topic].md`, and any relevant `design\u002Fdesign-inspirations-{topic}.md` when present.\n- Stop if no UI branch has an explicit approve decision. Route back to `$ui-interview [specific-ux-variation]`.\n- Stop if the requested work needs production infrastructure. Record the deferred infrastructure and route to prototype evidence first.\n\n## Process\n\n1. **Resolve scope.** Identify the product path, topic, parent user-flow branch, UX variation branch, and approved UI experiment branch. Preserve branch IDs from the flow-tree manifest.\n2. **Define the first-value journey.** Name the first-value moment, the primary task path, the entry route, the exit\u002Fsuccess state, and the evidence needed before moving deeper.\n3. **Choose the experiment home.** Prefer a project-native lightweight route when the app already has a safe local experiment surface. Otherwise create a disposable route under `experiments\u002F{topic}\u002F{ui-experiment-id}\u002F`. Keep the experiment easy to remove.\n4. **Build the clickable path.** Implement only the minimum interaction needed for a user to experience the first-value journey. Use fake, fixture, local, or in-memory data. Include realistic states only when they clarify the primary path.\n5. **Progressive reveal.** Introduce first value and the primary task path before dense secondary controls. Hide, defer, or stub secondary controls until the route proves the core journey.\n6. **Review evidence.** Produce a concise review note naming what the user should click, what decision the experiment tests, what worked, what remains unknown, and which deferred infrastructure stays out of scope.\n7. **Update branch state.** Add the experiment path and evidence note to the relevant `ui_experiments[]` branch in the flow-tree manifest. Do not create or update the prototype build plan unless the current run has explicit review evidence approving the experiment.\n8. **Build the alignment page.** Render the route, first-value journey, fake-data boundary, deferred infrastructure, and review gate in `alignment\u002Fcreate-ui-experiment-{topic}.html`.\n\n## Output\n\nThe skill may create or update:\n\n```text\nexperiments\u002F{topic}\u002F{ui-experiment-id}\u002F\ndesign\u002F**\u002Fflow-tree-*.yaml\nalignment\u002Fcreate-ui-experiment-{topic}.html\n```\n\nWhen using a project-native route instead of `experiments\u002F`, record the exact route path in the flow-tree manifest and in the alignment page.\n\n## Next Work\n\nAfter explicit review evidence exists, route based on what the evidence supports:\n\n- `$user-flow-map --prototype-build-plan [topic]` when approved UI experiments are ready to become prototype build-plan items.\n- `$prototype` when a prototype build plan already exists and names the approved UI experiment item.\n- `$uat --variant-evaluation` when the clickable experiment itself is being used as the evaluated variant artifact.\n\nDo not route to production planning, roadmap work, or durable infrastructure until experiment review evidence explicitly promotes the branch.\n\n## Constraints\n\n- Use fake, fixture, local, or in-memory data only.\n- Build one approved UI experiment branch per run.\n- Keep the route disposable and bounded to the first-value journey.\n- Use progressive reveal; do not expose dense secondary controls before the primary task path works.\n- Do not build production infrastructure, external account integrations, deployment automation, or durable storage.\n- Do not skip the review evidence gate before handing off to `$prototype`, `$uat --variant-evaluation`, or `$user-flow-map --prototype-build-plan`.\n- When recommending a skill from another pack, verify the pack is installed via `.agents\u002Fproject.json` `enabled_packs`. If not installed, recommend `npx skillpacks install \u003Cpack-name>` from the project shell before the target skill.\n\n## Alignment Page\n\nWhen this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment\u002Fcreate-ui-experiment-{topic}.html`.\n\nThe page must show the first-value journey, primary task path, clickable route path, fake-data boundary, deferred infrastructure, review evidence, and the exact downstream handoff gate.\n\n## Default Shipping Contract\n\nFollow the shared shipping contract convention in CLAUDE.md.\n",{"name":5,"type":39,"version":49,"description":7,"visual_tier":42,"argument-hint":50,"context_intake":51,"required_conventions":52},"v0.0","[approved-ui-experiment]","scoped",[53,54],"alignment-page","design-tree-loop","master","96e2912af886dd1606b1b97df707715aef062b02","packs\u002Fproduct-design\u002Fcodex\u002Fbuild-ui-screens\u002Farchive\u002Fv0.0",0,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills","https:\u002F\u002Fagentic-skills-blush.vercel.app","https:\u002F\u002Fgithub.com\u002FGeorgeQLe","georgeqle.com","George Le is a futurist and serial tech entrepreneur who wants to work toward a world where humanity is free from robotic tasks.","2026-11-10 04:07:24",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add GeorgeQLe\u002Fagentic-skills --skill create-ui-experiment",{"tool":71,"command":72},"bunx","bunx skills add GeorgeQLe\u002Fagentic-skills --skill create-ui-experiment",{"tool":74,"command":75},"pnpm","pnpm dlx skills add GeorgeQLe\u002Fagentic-skills --skill create-ui-experiment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fproduct-design\u002Fcodex\u002Fbuild-ui-screens\u002Farchive\u002Fv0.0\u002FSKILL.md",true,[],[80,92,102,114,129,140],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":44},"01M6G0NJES15RJKZE6YZ0TSYGF","source-checkout-allowed","Valid source-checkout-only fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fsource-checkout-allowed\u002FSKILL.md",[],[87,88,30,89,90,91],"source checkout allowed","checkout","only","v0","valid",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":44},"01M6G0NFZ3R1MNB1E3DVTM0WB7","deck-install-valid","Valid deck install fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fdeck-install\u002FSKILL.md",[],[99,100,101,91,30,90],"deck install valid","deck","install",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":44},"01M6G0ND3QZQC4MDZ9NVB97PT2","codex-pack-guard-valid","Valid Codex Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-pack-guard\u002FSKILL.md",[],[109,110,111,91,112,113,30,90],"codex pack guard valid","pack","guard","codex","availability",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":125,"publishedAt":44},"01M6G0NA9YB3NKGZKD3S96JMNB","codex-missing-skill-valid","Valid Codex missing skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-missing-skill-fallback\u002FSKILL.md",[120],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[126,127,91,112,90,128,30],"codex missing skill valid","missing","fallback",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":136,"publishedAt":44},"01M6G0N7PC0EKFD40ZWQAXSAQ9","codex-base-skill-fallback-valid","Valid Codex base skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-base-skill-fallback\u002FSKILL.md",[135],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},[91,112,128,137,138,139,90,30],"base skill","codex base skill fallback valid","base",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":44},"01M6G0N4VRR2YKZQ6N3Y6S2BQA","claude-pack-guard-valid","Valid Claude Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fclaude-pack-guard\u002FSKILL.md",[],[91,111,110,147,113,90,30],"claude pack guard valid"]