[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72TFK31NZPWCHR0W2DQCEZ2":3,"skill-same:01M72TFK31NZPWCHR0W2DQCEZ2":101},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M72TFK31NZPWCHR0W2DQCEZ2","ywc-ui-ux-review",null,"(ywc) Use when the user wants a UI\u002FUX review combining static code analysis with live UI exploration across IA, visual design, usability, and accessibility. Triggers: \"UI\u002FUX review\", \"UX 점검\", \"UI 검토\", \"usability audit\", \"design review\", \"accessibility review\", \"사용성 점검\", \"UX 監査\", \"UI レビュー\". Do not use for backend\u002FAPI review (use ywc-impl-review), product\u002Fbusiness strategy review (use ywc-product-review), visual redesign (use ywc-design-renew), or code-only review without a running UI.","yongwoon\u002Fywc-agent-toolkit","yongwoon","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9317029?v=4","01M72SZSF6VKANKG5QTMV4V95S","01M72SZSG8HHC3W2CV5P7EJ5AH",8,"MIT","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: ywc-ui-ux-review\ndescription: >-\n  (ywc) Use when the user wants a UI\u002FUX review combining static code analysis\n  with live UI exploration across IA, visual design, usability, and\n  accessibility. Triggers: \"UI\u002FUX review\", \"UX 점검\", \"UI 검토\", \"usability\n  audit\", \"design review\", \"accessibility review\", \"사용성 점검\", \"UX 監査\",\n  \"UI レビュー\". Do not use for backend\u002FAPI review (use ywc-impl-review),\n  product\u002Fbusiness strategy review (use ywc-product-review), visual redesign\n  (use ywc-design-renew), or code-only review without a running UI.\n---\n\n# UI\u002FUX Review — Hybrid (Code + Live UI)\n\n**Announce at start:** \"I'm using the ywc-ui-ux-review skill to combine static code analysis with live UI exploration.\"\n\nConduct a prioritized UI\u002FUX review of a project by combining static code analysis with live UI exploration. Focus areas: Information Architecture and Visual Design. Output: a four-tier (Critical \u002F High \u002F Medium \u002F Low) Markdown report.\n\n## Rationalization Defense\n\nWhen tempted to skip a step, check this table first:\n\n| Excuse | Reality |\n|---|---|\n| \"Code-only review is enough, no need to launch the browser\" | Hybrid means **both**. Static analysis cannot detect runtime layout shift, focus traps, or hover state breakage. |\n| \"WCAG checks are exhaustive, skip them on internal tools\" | Internal tools have employees with disabilities too. WCAG 2.2 AA is the minimum, not an opt-in. |\n| \"Reduced motion \u002F dark mode are edge cases, drop them\" | These are accessibility requirements, not edge cases. Test both. |\n| \"Severity feels Critical, mark it Critical regardless of impact\" | Critical = blocks core flow or violates accessibility law. Reserve it. Inflated severity buries real critical findings. |\n| \"Visual taste is subjective, do not flag design inconsistency\" | Inconsistency in tokens (color, spacing, typography) is objective. Always flag. |\n| \"Live exploration is risky on production, skip it\" | Use a staging or preview URL. Skipping live exploration drops half the value of this skill. |\n| \"IA and Visual Design share context, run them together\" | They share evidence but use distinct checklists; parallel subagents each read only one checklist, reducing context load and preventing cross-domain finding drift. |\n\n**Violating the letter of these rules is violating the spirit.** Static-only review with no live UI is design auditing on paper.\n\n## Triggers\n\n- \"Review the UI\u002FUX of this project\"\n- \"Audit usability of {feature\u002Fpage}\"\n- Information Architecture or navigation evaluation\n- Visual hierarchy \u002F typography \u002F spacing \u002F color audit\n- Pre-release UX checks against WCAG 2.2 AA\n- Cross-cutting design review against an internal design system\n\n## Workflow\n\nRun the six phases in order. Skip a phase only with explicit user consent.\n\n### Phase 1 — Scope & Context\n\nConfirm the following with the user before any analysis. When ambiguous, ask:\n\n- **Target**: pages, routes, or feature flows in scope\n- **Primary user journey**: the one or two flows that matter most\n- **Stack**: framework (React \u002F Vue \u002F Flutter \u002F Astro \u002F etc.) and design system in use\n- **Live URL**: a running URL or local dev server (required for Phase 3)\n- **Internal design system**: location of tokens, components, design guidelines (if any)\n\nIf no live URL is available, note it in the report and proceed with code-only review (degrade gracefully).\n\n### Phase 2 — Code Reconnaissance\n\nUse Codex file and shell tools to map. Prefer `rg`, `rg --files`, `find`, and targeted file reads:\n\n- Routing tree and navigation structure (router config, route files)\n- Top-level layouts and shell components\n- Design tokens (colors, typography, spacing) — typically `tokens.css`, `theme.ts`, `tailwind.config.*`, `*.tokens.json`, `design-system\u002F`\n- Shared UI components and their variants\n- Localization \u002F i18n surface, if any\n\nCapture findings as raw notes — do not score yet.\n\n### Phase 3 - Live UI Exploration\n\nUse the best available Codex browser capability for inspection-focused analysis. Prefer Playwright or a browser MCP when available; use available browser tooling if the environment exposes it. If no browser tool is available, note the limitation and continue with code-only review.\n\nRecommended browser evidence sequence:\n\n1. `browser open\u002Fnavigation tool` or `navigate_page` — open the target URL\n2. `browser accessibility or DOM snapshot tool` — get accessibility tree (token-efficient, structured)\n3. `browser screenshot tool` — capture visual evidence per breakpoint\n4. `browser resize tool` — repeat for 360 \u002F 768 \u002F 1280 \u002F 1920\n5. `browser audit tool` — automated accessibility \u002F performance scoring\n6. `browser console inspection tool` — surface runtime errors\n7. `browser script evaluation tool` — pull computed styles, contrast, focus chain when needed\n\nFor each piece of evidence record: URL, breakpoint, screenshot reference, snapshot excerpt.\n\n### Phase 4 — Per-Domain Review (Parallel)\n\nUse Codex subagent delegation when the current session exposes a delegation tool to run 2 review workers in parallel. If no delegation tool is available, run the same two review passes inline and record the fallback in the report. Pass each worker the code reconnaissance notes from Phase 2 and the live UI evidence from Phase 3:\n\n| Worker | Scope | Reference |\n|---|---|---|\n| IA Reviewer | Navigation, hierarchy, labels, and flow structure | `references\u002Fia-checklist.md` |\n| Visual Design Reviewer | Layout, typography, contrast, spacing, and component polish | `references\u002Fvisual-design-checklist.md` |\n\nEach worker returns findings with:\n- Concrete location (file path + line number, OR screen + selector)\n- Observed behavior\n- Expected behavior (per heuristic)\n- Preliminary heuristic citation\n\n### Phase 4b — Merge & Cross-Check\n\nCombine findings from both subagents. Cross-check each finding against `references\u002Fheuristics-combined.md` to attach an authoritative citation (Nielsen \u002F WCAG \u002F Material \u002F HIG \u002F internal design system). Deduplicate findings that share the same location.\n\n### Phase 5 — Severity Triage\n\nLoad `references\u002Fseverity-rubric.md` and classify every finding into one of: Critical \u002F High \u002F Medium \u002F Low. The rubric is the single source of truth — do not invent custom levels.\n\n### Phase 6 — Report Generation\n\nGenerate the report using `assets\u002Freport-template.md` as the structural template. Fill all placeholders. Default output path: `claudedocs\u002Fui-ux-review-{YYYY-MM-DD}.md` unless the user specifies otherwise.\n\n## Reference Files\n\n| File | When to load |\n|---|---|\n| `references\u002Fia-checklist.md` | Phase 4, IA review |\n| `references\u002Fvisual-design-checklist.md` | Phase 4, Visual Design review |\n| `references\u002Fheuristics-combined.md` | Phase 4b, attaching authoritative citation |\n| `references\u002Fseverity-rubric.md` | Phase 5, severity classification |\n| `assets\u002Freport-template.md` | Phase 6, report scaffolding |\n\n## Output Rules\n\n- **Every finding cites a heuristic** (Nielsen #N \u002F WCAG SC X.X.X \u002F Material spec \u002F HIG section \u002F internal token name)\n- **Every finding has a location** (file:line OR screen:selector)\n- **Every finding has a concrete recommendation** — code snippet or design change, not just \"improve UX\"\n- Group findings under the four severity tiers exactly as the template defines\n- Lead the report with an executive summary: count per tier, top 3 systemic patterns, top 5 recommended actions\n- Keep tone factual and respectful — review the work, not the people\n\n## Advisor Escalation Policy\n\n**Budget**: up to **2 high-capability advisor calls per invocation**.\n\nEscalate to an high-capability advisor only when the executor cannot resolve the severity classification from `references\u002Fseverity-rubric.md` alone. Two conditions qualify:\n\n| Condition | Example |\n|---|---|\n| **Borderline Critical vs High** | An accessibility issue blocks assistive-technology users on a primary flow, but only under a specific screen-reader \u002F browser combination that the rubric does not explicitly address — both Critical and High are defensible |\n| **Heuristic conflict** | Nielsen's \"Visibility of system status\" (#1) and Apple HIG's \"Clarity\" principle produce opposite recommendations for the same UI element (e.g., a persistent loading indicator that aids status visibility but creates visual noise per HIG clarity) |\n\nFor all other borderline cases — High vs Medium, Medium vs Low, uncertain evidence from code-only analysis — choose the more conservative (lower) tier and add a brief inline note explaining the uncertainty. Do not spend advisor budget on these cases.\n\n## Boundaries\n\n**Will:**\n\n- Review IA, Visual Design, accessibility, and usability of the target project\n- Combine static code evidence with live UI evidence\n- Produce a prioritized, citation-backed Markdown report\n\n**Will Not:**\n\n- Re-design or refactor code on the user's behalf (review only — implementation is a separate task)\n- Fabricate findings without code or runtime evidence\n- Replace formal user testing with real users\n- Score subjective beauty — every judgment is anchored to a heuristic\n\n## Validation\n\nBefore finalizing, report:\n\n```text\nStatus: \u003CDONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT>\nScope: \u003Cscreens\u002Ffiles reviewed>\nFindings: \u003Ccounts by severity tier>\nEvidence: \u003Cstatic and\u002For live UI evidence used>\nValidation: \u003Cheuristic citations and location checks>\nNext action: \u003Ctop recommended fix or \"none\">\n```\n\nVerify that every finding has a heuristic citation, a concrete location, and a specific recommendation; static-only limitations are disclosed; and no redesign or code refactor is performed by this review-only skill.\n","# UI\u002FUX Review — Hybrid (Code + Live UI)\n\n**Announce at start:** \"I'm using the ywc-ui-ux-review skill to combine static code analysis with live UI exploration.\"\n\nConduct a prioritized UI\u002FUX review of a project by combining static code analysis with live UI exploration. Focus areas: Information Architecture and Visual Design. Output: a four-tier (Critical \u002F High \u002F Medium \u002F Low) Markdown report.\n\n## Rationalization Defense\n\nWhen tempted to skip a step, check this table first:\n\n| Excuse | Reality |\n|---|---|\n| \"Code-only review is enough, no need to launch the browser\" | Hybrid means **both**. Static analysis cannot detect runtime layout shift, focus traps, or hover state breakage. |\n| \"WCAG checks are exhaustive, skip them on internal tools\" | Internal tools have employees with disabilities too. WCAG 2.2 AA is the minimum, not an opt-in. |\n| \"Reduced motion \u002F dark mode are edge cases, drop them\" | These are accessibility requirements, not edge cases. Test both. |\n| \"Severity feels Critical, mark it Critical regardless of impact\" | Critical = blocks core flow or violates accessibility law. Reserve it. Inflated severity buries real critical findings. |\n| \"Visual taste is subjective, do not flag design inconsistency\" | Inconsistency in tokens (color, spacing, typography) is objective. Always flag. |\n| \"Live exploration is risky on production, skip it\" | Use a staging or preview URL. Skipping live exploration drops half the value of this skill. |\n| \"IA and Visual Design share context, run them together\" | They share evidence but use distinct checklists; parallel subagents each read only one checklist, reducing context load and preventing cross-domain finding drift. |\n\n**Violating the letter of these rules is violating the spirit.** Static-only review with no live UI is design auditing on paper.\n\n## Triggers\n\n- \"Review the UI\u002FUX of this project\"\n- \"Audit usability of {feature\u002Fpage}\"\n- Information Architecture or navigation evaluation\n- Visual hierarchy \u002F typography \u002F spacing \u002F color audit\n- Pre-release UX checks against WCAG 2.2 AA\n- Cross-cutting design review against an internal design system\n\n## Workflow\n\nRun the six phases in order. Skip a phase only with explicit user consent.\n\n### Phase 1 — Scope & Context\n\nConfirm the following with the user before any analysis. When ambiguous, ask:\n\n- **Target**: pages, routes, or feature flows in scope\n- **Primary user journey**: the one or two flows that matter most\n- **Stack**: framework (React \u002F Vue \u002F Flutter \u002F Astro \u002F etc.) and design system in use\n- **Live URL**: a running URL or local dev server (required for Phase 3)\n- **Internal design system**: location of tokens, components, design guidelines (if any)\n\nIf no live URL is available, note it in the report and proceed with code-only review (degrade gracefully).\n\n### Phase 2 — Code Reconnaissance\n\nUse Codex file and shell tools to map. Prefer `rg`, `rg --files`, `find`, and targeted file reads:\n\n- Routing tree and navigation structure (router config, route files)\n- Top-level layouts and shell components\n- Design tokens (colors, typography, spacing) — typically `tokens.css`, `theme.ts`, `tailwind.config.*`, `*.tokens.json`, `design-system\u002F`\n- Shared UI components and their variants\n- Localization \u002F i18n surface, if any\n\nCapture findings as raw notes — do not score yet.\n\n### Phase 3 - Live UI Exploration\n\nUse the best available Codex browser capability for inspection-focused analysis. Prefer Playwright or a browser MCP when available; use available browser tooling if the environment exposes it. If no browser tool is available, note the limitation and continue with code-only review.\n\nRecommended browser evidence sequence:\n\n1. `browser open\u002Fnavigation tool` or `navigate_page` — open the target URL\n2. `browser accessibility or DOM snapshot tool` — get accessibility tree (token-efficient, structured)\n3. `browser screenshot tool` — capture visual evidence per breakpoint\n4. `browser resize tool` — repeat for 360 \u002F 768 \u002F 1280 \u002F 1920\n5. `browser audit tool` — automated accessibility \u002F performance scoring\n6. `browser console inspection tool` — surface runtime errors\n7. `browser script evaluation tool` — pull computed styles, contrast, focus chain when needed\n\nFor each piece of evidence record: URL, breakpoint, screenshot reference, snapshot excerpt.\n\n### Phase 4 — Per-Domain Review (Parallel)\n\nUse Codex subagent delegation when the current session exposes a delegation tool to run 2 review workers in parallel. If no delegation tool is available, run the same two review passes inline and record the fallback in the report. Pass each worker the code reconnaissance notes from Phase 2 and the live UI evidence from Phase 3:\n\n| Worker | Scope | Reference |\n|---|---|---|\n| IA Reviewer | Navigation, hierarchy, labels, and flow structure | `references\u002Fia-checklist.md` |\n| Visual Design Reviewer | Layout, typography, contrast, spacing, and component polish | `references\u002Fvisual-design-checklist.md` |\n\nEach worker returns findings with:\n- Concrete location (file path + line number, OR screen + selector)\n- Observed behavior\n- Expected behavior (per heuristic)\n- Preliminary heuristic citation\n\n### Phase 4b — Merge & Cross-Check\n\nCombine findings from both subagents. Cross-check each finding against `references\u002Fheuristics-combined.md` to attach an authoritative citation (Nielsen \u002F WCAG \u002F Material \u002F HIG \u002F internal design system). Deduplicate findings that share the same location.\n\n### Phase 5 — Severity Triage\n\nLoad `references\u002Fseverity-rubric.md` and classify every finding into one of: Critical \u002F High \u002F Medium \u002F Low. The rubric is the single source of truth — do not invent custom levels.\n\n### Phase 6 — Report Generation\n\nGenerate the report using `assets\u002Freport-template.md` as the structural template. Fill all placeholders. Default output path: `claudedocs\u002Fui-ux-review-{YYYY-MM-DD}.md` unless the user specifies otherwise.\n\n## Reference Files\n\n| File | When to load |\n|---|---|\n| `references\u002Fia-checklist.md` | Phase 4, IA review |\n| `references\u002Fvisual-design-checklist.md` | Phase 4, Visual Design review |\n| `references\u002Fheuristics-combined.md` | Phase 4b, attaching authoritative citation |\n| `references\u002Fseverity-rubric.md` | Phase 5, severity classification |\n| `assets\u002Freport-template.md` | Phase 6, report scaffolding |\n\n## Output Rules\n\n- **Every finding cites a heuristic** (Nielsen #N \u002F WCAG SC X.X.X \u002F Material spec \u002F HIG section \u002F internal token name)\n- **Every finding has a location** (file:line OR screen:selector)\n- **Every finding has a concrete recommendation** — code snippet or design change, not just \"improve UX\"\n- Group findings under the four severity tiers exactly as the template defines\n- Lead the report with an executive summary: count per tier, top 3 systemic patterns, top 5 recommended actions\n- Keep tone factual and respectful — review the work, not the people\n\n## Advisor Escalation Policy\n\n**Budget**: up to **2 high-capability advisor calls per invocation**.\n\nEscalate to an high-capability advisor only when the executor cannot resolve the severity classification from `references\u002Fseverity-rubric.md` alone. Two conditions qualify:\n\n| Condition | Example |\n|---|---|\n| **Borderline Critical vs High** | An accessibility issue blocks assistive-technology users on a primary flow, but only under a specific screen-reader \u002F browser combination that the rubric does not explicitly address — both Critical and High are defensible |\n| **Heuristic conflict** | Nielsen's \"Visibility of system status\" (#1) and Apple HIG's \"Clarity\" principle produce opposite recommendations for the same UI element (e.g., a persistent loading indicator that aids status visibility but creates visual noise per HIG clarity) |\n\nFor all other borderline cases — High vs Medium, Medium vs Low, uncertain evidence from code-only analysis — choose the more conservative (lower) tier and add a brief inline note explaining the uncertainty. Do not spend advisor budget on these cases.\n\n## Boundaries\n\n**Will:**\n\n- Review IA, Visual Design, accessibility, and usability of the target project\n- Combine static code evidence with live UI evidence\n- Produce a prioritized, citation-backed Markdown report\n\n**Will Not:**\n\n- Re-design or refactor code on the user's behalf (review only — implementation is a separate task)\n- Fabricate findings without code or runtime evidence\n- Replace formal user testing with real users\n- Score subjective beauty — every judgment is anchored to a heuristic\n\n## Validation\n\nBefore finalizing, report:\n\n```text\nStatus: \u003CDONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT>\nScope: \u003Cscreens\u002Ffiles reviewed>\nFindings: \u003Ccounts by severity tier>\nEvidence: \u003Cstatic and\u002For live UI evidence used>\nValidation: \u003Cheuristic citations and location checks>\nNext action: \u003Ctop recommended fix or \"none\">\n```\n\nVerify that every finding has a heuristic citation, a concrete location, and a specific recommendation; static-only limitations are disclosed; and no redesign or code refactor is performed by this review-only skill.\n",{"name":5,"description":7},"main","7e8ac872e53df8c89d75663e031626281a2a2f5c","codex\u002Fskills\u002Fywc-ui-ux-review",1,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit","https:\u002F\u002Fgithub.com\u002Fyongwoon","https:\u002F\u002Fwww.webhani.com","2026-11-08 17:14:59",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add yongwoon\u002Fywc-agent-toolkit --skill ywc-ui-ux-review",{"tool":37,"command":38},"bunx","bunx skills add yongwoon\u002Fywc-agent-toolkit --skill ywc-ui-ux-review",{"tool":40,"command":41},"pnpm","pnpm dlx skills add yongwoon\u002Fywc-agent-toolkit --skill ywc-ui-ux-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002FSKILL.md",true,[45,51,57,61,65,69,73,77,81,85,89,93,97],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",250,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002Fagents\u002Fopenai.yaml",{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"assets\u002Freport-template.md","ASSET","资产文件",2770,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002Fassets\u002Freport-template.md",{"path":58,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002Fevals.json",880,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002Fevals\u002Fevals.json",{"path":62,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":63,"sourceHtmlUrl":64},"README.en.md",1634,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002FREADME.en.md",{"path":66,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":67,"sourceHtmlUrl":68},"README.es.md",2133,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002FREADME.es.md",{"path":70,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":71,"sourceHtmlUrl":72},"README.ja.md",1819,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002FREADME.ja.md",{"path":74,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":75,"sourceHtmlUrl":76},"README.ko.md",1719,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002FREADME.ko.md",{"path":78,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":79,"sourceHtmlUrl":80},"README.md",6273,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002FREADME.md",{"path":82,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":83,"sourceHtmlUrl":84},"README.zh.md",1774,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002FREADME.zh.md",{"path":86,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fheuristics-combined.md",4600,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002Freferences\u002Fheuristics-combined.md",{"path":90,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fia-checklist.md",4137,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002Freferences\u002Fia-checklist.md",{"path":94,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fseverity-rubric.md",3333,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002Freferences\u002Fseverity-rubric.md",{"path":98,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fvisual-design-checklist.md",8637,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fcodex\u002Fskills\u002Fywc-ui-ux-review\u002Freferences\u002Fvisual-design-checklist.md",[102,108,114,121,128,135],{"skillNo":103,"name":104,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":18},"01M72TQ84GTCPCV2VJ778V17TW","missing-frontmatter","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fcodex-description-limit\u002Fmissing-frontmatter\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M72TQ6M4BFWE7P9EPW0GZDCM","malformed-frontmatter","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fcodex-description-limit\u002Fmalformed-frontmatter\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":18},"01M72TQ3ESGKXZ4QRWGTX92BKJ","fixture-501-fail","(ywc) Use when aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa Do not use for x.","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fcodex-description-limit\u002F501-fail\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":18},"01M72TQ0HJ8H3R37J9WPWGKJZR","fixture-500-pass","(ywc) Use when aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa Do not use for x.","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fcodex-description-limit\u002F500-pass\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":18},"01M72TPWNCC7NEYD0D9N12KSQS","ywc-worktrees","(ywc) Use when creating, auditing, pruning, or resolving git worktrees for isolated task workspaces, whether delegated from an executor or used standalone. Triggers: \"worktree 생성\", \"worktree audit\", \"worktree 정리\", \"worktree prune\", \"ywc-worktrees\", \"create worktree\". Do not use for branch creation\u002Fdeletion alone, PR creation (use ywc-create-pr), CI or merge delivery (use ywc-finish-branch), task orchestration (use ywc-sequential-executor or ywc-parallel-executor), or non-git isolation.","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-worktrees\u002FSKILL.md",[],[],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":18},"01M72TPRNR3E6QWB91GM98ABBV","ywc-wayfinder","(ywc) Use when a large or uncertain change needs multi-session discovery with a deterministic local map and exactly one active ticket before planning or implementation. Triggers: \"wayfinder\", \"길찾기\", \"discovery map\", \"multi-session discovery\", \"탐색 ticket\", \"経路整理\", \"探索マップ\", \"ywc-wayfinder\". Do not use for ordinary planning (use ywc-plan), idea clarification (use ywc-brainstorm), direct implementation, or tracker\u002Fdatabase writes outside the local Markdown map.","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-wayfinder\u002FSKILL.md",[],[]]