[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M786WD31A9A7YAPWAXGMGSCJ":3,"skill-same:01M786WD31A9A7YAPWAXGMGSCJ":48},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M786WD31A9A7YAPWAXGMGSCJ","spec-kit-ui-design",null,"Use when UI, UX, visual design, design-system, accessibility, component, platform interface, TUI, or CLI output quality matters in a Spec Kit Plus project.","chenziyang110\u002Flaunchdeck","chenziyang110","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43693913?v=4","01M7863EBWK1D0P6A29YGEMAS4","Robin11","01M7863ECM1VB6RXDMHTW90D2T",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fspec-kit-ui-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"spec-kit-ui-design\"\ndescription: \"Use when UI, UX, visual design, design-system, accessibility, component, platform interface, TUI, or CLI output quality matters in a Spec Kit Plus project.\"\ncompatibility: \"Requires spec-kit project structure with .specify\u002F directory\"\nmetadata:\n  author: \"github-spec-kit\"\n  source: \"templates\u002Fpassive-skills\u002Fspec-kit-ui-design\u002FSKILL.md\"\n---\n\n\n# Spec Kit UI Design\n\nThis passive skill keeps UI work aligned with the product's design system before\nimplementation invents generic one-off styling. Use it whenever UI, UX, visual\ndesign, design-system, accessibility, component coverage, platform interface,\nTUI, or CLI output quality affects the outcome.\n\n## Design System Gate\n\n- Before substantive UI work, look for `DESIGN.md` or an equivalent committed\n  design-system source. Treat `DESIGN.md` as the expected design contract name\n  when documenting or testing this gate.\n- If `DESIGN.md` is present, implementation must follow it for layout,\n  component usage, color, typography, motion, density, interaction states,\n  accessibility expectations, and evidence requirements.\n- A `DESIGN.md` with `design_system.status: bootstrap` is only an initialized\n  seed. Do not let its generic tokens suppress project-specific design work or\n  treat it as an approved product direction.\n- If `DESIGN.md` is missing, contradictory, or too thin for high-risk UI work,\n  recommend `sp-design` and the projected invocation `$sp-design` before\n  implementation. Do not let implementation invent a substitute visual system.\n- Small UI work may proceed without `sp-design` only when the existing design\n  intent is clear and the change is a narrow component variant, copy\u002Fstate\n  adjustment, internal form refinement, or low-risk TUI\u002FCLI wording update.\n  Record the soft risk and the design assumption in the closeout.\n\n## UI Reference Input Gate\n\n- UI quality applies to every changed user-visible screen, component, layout,\n  interaction, responsive state, TUI layout, or CLI presentation—not only work\n  with an external screenshot. Substantive UI work needs a feature\n  `ui-brief.md`; narrow existing-pattern fixes may record a compact inline\n  contract instead.\n- Treat screenshots, HTML\u002FCSS mockups, UI framework snippets, Figma exports,\n  reference URLs, existing pages, and \"make it like this\" language as UI\n  reference input.\n- In `sp-specify`, UI reference input requires\n  `choose_ui_reference_lane_dispatch` and `lane_mode: ui-reference-artifact`.\n- The UI reference lane writes `ui-reference-notes.md`, `ui-brief.md`, and\n  optional `ui-target.html`.\n- `approximate` is the default fidelity mode. `high` requires visual\n  comparison; `inspiration` extracts principles only.\n- If the environment cannot prove visual similarity, the workflow must record\n  `pending-human-review`.\n- The agent must not claim a UI visually matches a reference without agent\n  visual comparison or human approval.\n\n## Platform Rules\n\n- Web work must respect responsive layout, semantic markup, keyboard operation,\n  focus states, contrast, motion preferences, viewport screenshots, and browser\n  console cleanliness.\n- Mobile work must respect platform navigation, touch targets, safe areas,\n  density, offline\u002Floading\u002Ferror states, screen-reader labels, and device-form\n  evidence.\n- Desktop work must respect resize behavior, keyboard shortcuts, menus,\n  platform conventions, window density, high-DPI rendering, and pointer\u002Ffocus\n  interaction evidence.\n- TUI work must respect terminal widths, color fallback, readable alignment,\n  non-color indicators, progressive output, error states, and copyable command\n  output.\n- CLI work must respect command help clarity, stable text contracts,\n  machine-readable output when applicable, error\u002Faction pairing, localization\n  concerns, and accessible plain-text formatting.\n\n## Component Coverage\n\n- Cover every user-visible component state that the task can affect: default,\n  hover, focus, active, disabled, selected, loading, empty, error, success, and\n  permission-limited states where relevant.\n- Keep component decisions tied to the design system. Reuse existing tokens,\n  components, spacing rules, and interaction patterns before adding new ones.\n- If a new component or design token is required, name the source design problem\n  and how the new element fits the system.\n- Avoid generic one-off styling, unexplained palette shifts, and unrelated bold\n  aesthetics that solve presentation but not the product interface problem.\n\n## Evidence\n\n- UI closeout needs platform-appropriate evidence, not only code or unit tests.\n- For web, capture viewport screenshots at the relevant desktop and mobile\n  widths, check for layout overflow, inspect console errors, and include\n  accessibility checks when the surface is interactive.\n- For mobile and desktop, include simulator\u002Fdevice\u002Fwindow evidence for the\n  affected states and screen sizes.\n- For TUI and CLI, include representative terminal captures or exact command\n  output for narrow and normal widths, including errors and help text when\n  touched.\n- Evidence should be visual regression-friendly where screenshots are available:\n  use stable paths, deterministic state, and names that describe viewport,\n  route, and scenario.\n- Before closeout, iterate through real entry point -> capture -> visual inspect\n  -> repair -> recapture. Do not equate automated behavior checks with visual\n  or interaction acceptance.\n","# Spec Kit UI Design\n\nThis passive skill keeps UI work aligned with the product's design system before\nimplementation invents generic one-off styling. Use it whenever UI, UX, visual\ndesign, design-system, accessibility, component coverage, platform interface,\nTUI, or CLI output quality affects the outcome.\n\n## Design System Gate\n\n- Before substantive UI work, look for `DESIGN.md` or an equivalent committed\n  design-system source. Treat `DESIGN.md` as the expected design contract name\n  when documenting or testing this gate.\n- If `DESIGN.md` is present, implementation must follow it for layout,\n  component usage, color, typography, motion, density, interaction states,\n  accessibility expectations, and evidence requirements.\n- A `DESIGN.md` with `design_system.status: bootstrap` is only an initialized\n  seed. Do not let its generic tokens suppress project-specific design work or\n  treat it as an approved product direction.\n- If `DESIGN.md` is missing, contradictory, or too thin for high-risk UI work,\n  recommend `sp-design` and the projected invocation `$sp-design` before\n  implementation. Do not let implementation invent a substitute visual system.\n- Small UI work may proceed without `sp-design` only when the existing design\n  intent is clear and the change is a narrow component variant, copy\u002Fstate\n  adjustment, internal form refinement, or low-risk TUI\u002FCLI wording update.\n  Record the soft risk and the design assumption in the closeout.\n\n## UI Reference Input Gate\n\n- UI quality applies to every changed user-visible screen, component, layout,\n  interaction, responsive state, TUI layout, or CLI presentation—not only work\n  with an external screenshot. Substantive UI work needs a feature\n  `ui-brief.md`; narrow existing-pattern fixes may record a compact inline\n  contract instead.\n- Treat screenshots, HTML\u002FCSS mockups, UI framework snippets, Figma exports,\n  reference URLs, existing pages, and \"make it like this\" language as UI\n  reference input.\n- In `sp-specify`, UI reference input requires\n  `choose_ui_reference_lane_dispatch` and `lane_mode: ui-reference-artifact`.\n- The UI reference lane writes `ui-reference-notes.md`, `ui-brief.md`, and\n  optional `ui-target.html`.\n- `approximate` is the default fidelity mode. `high` requires visual\n  comparison; `inspiration` extracts principles only.\n- If the environment cannot prove visual similarity, the workflow must record\n  `pending-human-review`.\n- The agent must not claim a UI visually matches a reference without agent\n  visual comparison or human approval.\n\n## Platform Rules\n\n- Web work must respect responsive layout, semantic markup, keyboard operation,\n  focus states, contrast, motion preferences, viewport screenshots, and browser\n  console cleanliness.\n- Mobile work must respect platform navigation, touch targets, safe areas,\n  density, offline\u002Floading\u002Ferror states, screen-reader labels, and device-form\n  evidence.\n- Desktop work must respect resize behavior, keyboard shortcuts, menus,\n  platform conventions, window density, high-DPI rendering, and pointer\u002Ffocus\n  interaction evidence.\n- TUI work must respect terminal widths, color fallback, readable alignment,\n  non-color indicators, progressive output, error states, and copyable command\n  output.\n- CLI work must respect command help clarity, stable text contracts,\n  machine-readable output when applicable, error\u002Faction pairing, localization\n  concerns, and accessible plain-text formatting.\n\n## Component Coverage\n\n- Cover every user-visible component state that the task can affect: default,\n  hover, focus, active, disabled, selected, loading, empty, error, success, and\n  permission-limited states where relevant.\n- Keep component decisions tied to the design system. Reuse existing tokens,\n  components, spacing rules, and interaction patterns before adding new ones.\n- If a new component or design token is required, name the source design problem\n  and how the new element fits the system.\n- Avoid generic one-off styling, unexplained palette shifts, and unrelated bold\n  aesthetics that solve presentation but not the product interface problem.\n\n## Evidence\n\n- UI closeout needs platform-appropriate evidence, not only code or unit tests.\n- For web, capture viewport screenshots at the relevant desktop and mobile\n  widths, check for layout overflow, inspect console errors, and include\n  accessibility checks when the surface is interactive.\n- For mobile and desktop, include simulator\u002Fdevice\u002Fwindow evidence for the\n  affected states and screen sizes.\n- For TUI and CLI, include representative terminal captures or exact command\n  output for narrow and normal widths, including errors and help text when\n  touched.\n- Evidence should be visual regression-friendly where screenshots are available:\n  use stable paths, deterministic state, and names that describe viewport,\n  route, and scenario.\n- Before closeout, iterate through real entry point -> capture -> visual inspect\n  -> repair -> recapture. Do not equate automated behavior checks with visual\n  or interaction acceptance.\n",{"name":5,"metadata":24,"description":7,"compatibility":27},{"author":25,"source":26},"github-spec-kit","templates\u002Fpassive-skills\u002Fspec-kit-ui-design\u002FSKILL.md","Requires spec-kit project structure with .specify\u002F directory","main","021f5cbe02157229460a577e9a585f2da6d78cb0",".codex\u002Fskills\u002Fspec-kit-ui-design","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck","https:\u002F\u002Fgithub.com\u002Fchenziyang110","2026-08-07 18:10:54",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add chenziyang110\u002Flaunchdeck --skill spec-kit-ui-design",{"tool":40,"command":41},"bunx","bunx skills add chenziyang110\u002Flaunchdeck --skill spec-kit-ui-design",{"tool":43,"command":44},"pnpm","pnpm dlx skills add chenziyang110\u002Flaunchdeck --skill spec-kit-ui-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fspec-kit-ui-design\u002FSKILL.md",true,[],[49,56,62,68,75,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7875F3HQ1GF5F6BR36KY3JE","launchdeck-agent","Codex host adapter contract fixture for Launchdeck.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fagent-hosts\u002Fcodex\u002Fskill\u002FSKILL.md",[],[],{"skillNo":57,"name":51,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7875DV2DQR33K1NFJHKAMZP","Claude host adapter contract fixture for Launchdeck.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fagent-hosts\u002Fclaude\u002Fskill\u002FSKILL.md",[],[],{"skillNo":63,"name":51,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M78759JQ7A6FQ8KDQTNYS3X9","Use this skill aggressively for local project lifecycle operations even when the user does not mention Launchdeck: start this project, run the dev server, dev, build, test, restart service, stop service, show logs, inspect ports, port is occupied, clean cache; and when the user explicitly asks to configure this local project for Launchdeck or create or generate a project-adapted `.launchdeck.yml`, including 为这个项目生成 Launchdeck 配置. Do not use for ordinary code edits, docs-only work, general explanations, API design discussion, or production deployment unless the user also asks to operate or configure a local project or service.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Fagent\u002Finstaller-payload\u002Fskill\u002Flaunchdeck-agent\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M78753ZJQ7G2CZT1W1G8WRJV","zig-testing","Use ONLY when user explicitly requests Zig test code, built-in test runner configuration,\ntest failure diagnosis, or coverage for Zig projects.\n\nTriggers: \"write test zig\", \"zig test\", \"testing.allocator\", \"zig coverage\",\n\"comptime test\", \"zig expectError\", \"zig snapshot test\", \"zig fuzz\".\n\nDo NOT activate for: general Zig coding without test context, build.zig configuration\nfor non-test targets, Zig compiler errors, or Zig build system setup.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fzig-testing\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M78750JXY4Z5D5W1EX3PQ31Z","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7874X2T83EQQFRCEY5SJJVC","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fverification-before-completion\u002FSKILL.md",[],[]]