[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DYTF25FREB518SGYRX0HD":3,"skill-same:01M79DYTF25FREB518SGYRX0HD":45},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M79DYTF25FREB518SGYRX0HD","design-mockup",null,"Produce on-brand UI mockups with the Stitch design-to-code tool BEFORE writing any implementation code, so design decisions get made and approved visually first. Auto-detects THIS project's design source of truth (a design.md \u002F design spec, design tokens, Tailwind\u002Ftheme config, or a live design-system page), seeds a Stitch design system from it, generates the requested screens, downloads and actually LOOKS AT each screenshot to verify brand fidelity, and presents a review gallery + the Stitch storyboard link. Use when the user says \"mock this up\", \"design mockups\", \"stitch mockups\", \"let's design the screens\", or wants to see a feature's UI before it's built. NOT for tiny visual tweaks to existing shipped UI. Portable: it reads whatever project you're in and never hardcodes one project's brand.","sharepointoscar\u002Fagent-workflow-skills","sharepointoscar","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1544014?v=4","01M79DYNNSWKW6C81A3C9QF0FQ","Oscar Medina","01M79DYNPDXTKQ5RFX4071RBM8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsharepointoscar\u002Fagent-workflow-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fdevopsoscar\u002Fskills\u002Fdesign-mockup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: design-mockup\ndescription: >-\n  Produce on-brand UI mockups with the Stitch design-to-code tool BEFORE writing any\n  implementation code, so design decisions get made and approved visually first. Auto-detects\n  THIS project's design source of truth (a design.md \u002F design spec, design tokens, Tailwind\u002Ftheme\n  config, or a live design-system page), seeds a Stitch design system from it, generates the\n  requested screens, downloads and actually LOOKS AT each screenshot to verify brand fidelity,\n  and presents a review gallery + the Stitch storyboard link. Use when the user says \"mock this\n  up\", \"design mockups\", \"stitch mockups\", \"let's design the screens\", or wants to see a\n  feature's UI before it's built. NOT for tiny visual tweaks to existing shipped UI. Portable:\n  it reads whatever project you're in and never hardcodes one project's brand.\n---\n\n# Design-mockup — Stitch mockups, on this project's brand\n\nMockup-first: for any new UI or feature, produce and get approval on **visual mockups** before\nimplementation. This skill is **project-agnostic** — it adapts to the repo you're in.\n\nRequires the Stitch MCP tools (`mcp__stitch__*`). Load them first with ToolSearch if deferred.\n\n## STEP 0 — Find THIS project's design source of truth (always first)\n\nNever invent a brand. Look, in priority order, for what the project already defines:\n- A written design spec — `docs\u002Fdesign.md`, `DESIGN.md`, a style guide, or brand guidelines.\n- **Design tokens** — a tokens file (`tokens.css`\u002F`tokens.ts`), CSS `:root` custom properties,\n  a Tailwind\u002Ftheme config, `components.json` (shadcn), `globals.css`. Extract the real hex values.\n- A **live design-system \u002F storybook page** — often the truest \"how to compose screens\" reference.\n- `CLAUDE.md` for any stated brand\u002FUX rules.\n\nCapture: primary\u002Fsecondary\u002Faccent brand colors (real hexes), neutrals, typeface(s), corner radius\nscale, light\u002Fdark support, and the reusable component vocabulary.\n\n**If NO design source exists:** offer to author a `design.md` from whatever tokens\u002Fassets do exist\n(sample brand colors straight from the logo asset if needed — don't eyeball). Get the user to\nconfirm the palette before generating. A wrong brand wastes every screen.\n\n## STEP 1 — Stitch design system (once per brand)\n\n- Reuse an existing project if appropriate, else `create_project`.\n- `create_design_system` with the project's real tokens mapped to Stitch params:\n  - `colorMode` LIGHT\u002FDARK to match the project (many are light-only).\n  - `headlineFont`\u002F`bodyFont`\u002F`labelFont` → the project's typeface (enum, e.g. `INTER`).\n  - `roundness` → closest to the project's radii (`ROUND_FOUR` for ~4–6px, `ROUND_EIGHT` for ~8px).\n  - `customColor` + `overridePrimaryColor` = brand primary; `overrideSecondaryColor` = secondary\u002Fink;\n    `overrideTertiaryColor` = accent; `overrideNeutralColor` = a representative neutral.\n  - `colorVariant: FIDELITY` to hold close to the seed colors.\n  - `designMd`: a COMPACT brand spec (palette + type + shape + a few usage rules + product tone).\n- Keep the returned `assets\u002F\u003Cid>` — pass it as `designSystem` to every generation for consistency.\n\n## STEP 2 — Generate screens\n\n- For each screen: `generate_screen_from_text` with `projectId`, the `designSystem` id, `deviceType`\n  (DESKTOP\u002FMOBILE\u002FTABLET), and a detailed prompt.\n- **Prompt recipe:** name the screen's job; specify layout top-to-bottom; give REAL copy (plain-English,\n  outcome-focused, never system jargon); call out brand usage explicitly (one primary action in the\n  primary color per screen, accent used sparingly, ink for headings); for in-context screens, describe\n  the app chrome (sidebar\u002Ftop bar) so it reads grounded; restate shape (small radii, no pills) and tone.\n- **Generate ONE screen first, verify the brand, THEN batch the rest** — cheaper to fix the design\n  system once than N times.\n\n## STEP 3 — Verify by LOOKING (non-negotiable)\n\nFor every generated screen, download the `screenshot.downloadUrl` and **Read the PNG to actually view\nit.** Confirm the brand colors, type, radii, and copy are right. TypeScript\u002Ftests can't catch a\nwrong-looking screen — your eyes are the gate. If a screen is off, fix via `edit_screens` (targeted\nchange) or `generate_variants` (explore alternatives), not a blind re-generate.\n\n## STEP 4 — Present for review\n\n- Build a single **review gallery** (a self-contained HTML Artifact with the screenshots embedded as\n  data URIs, annotated with each screen's role in the flow) so the user reviews everything in one place.\n- Also give the **Stitch project link** (`https:\u002F\u002Fstitch.withgoogle.com\u002Fprojects\u002F\u003CprojectId>`) as the\n  editable storyboard.\n- These are **mockups, not implementation.** Get the user's approval \u002F edits before any code is written.\n  On approval, hand off to implementation (or the project's ship\u002Fbuild flow). Never present a mockup as\n  a shipped feature.\n\n## Gotchas (learned in practice)\n\n- Call Stitch tools with **structured params**, never a raw-JSON string wrapper — it fails to parse.\n- A one-off **\"Request contains an invalid argument\"** is usually transient — **retry once** before\n  diagnosing; the second identical call typically succeeds.\n- `list_screens` can return empty even when screens exist — rely on each generation's returned screen\n  id\u002Fname, not on list_screens.\n- Each generation **echoes the full `designMd`** back in the response — keep that markdown tight to\n  avoid bloating context across many screens.\n- Screenshot URLs are large signed Google URLs — `curl -L` them; they may expire, so download promptly.\n- **`edit_screens` on text-only changes patches the live DOM but does NOT refresh the exported\n  screenshot\u002FhtmlCode** — the API keeps serving the pre-edit snapshot (same file id), so a downloaded\n  thumbnail lags even though the Stitch web app shows the change. Layout-level edits (e.g. removing a\n  sidebar) DO trigger a full re-render with a NEW screen id + fresh screenshot. So: verify text edits in\n  the Stitch UI, and if you need an accurate exported thumbnail of a text-only change, re-generate the\n  screen rather than trusting the screenshot URL.\n- Don't over-generate: cover the distinct screens + one representative \"template\" screen for repeated\n  patterns (e.g. one feature-guide covers the rest); note the repeats rather than rendering all.\n","# Design-mockup — Stitch mockups, on this project's brand\n\nMockup-first: for any new UI or feature, produce and get approval on **visual mockups** before\nimplementation. This skill is **project-agnostic** — it adapts to the repo you're in.\n\nRequires the Stitch MCP tools (`mcp__stitch__*`). Load them first with ToolSearch if deferred.\n\n## STEP 0 — Find THIS project's design source of truth (always first)\n\nNever invent a brand. Look, in priority order, for what the project already defines:\n- A written design spec — `docs\u002Fdesign.md`, `DESIGN.md`, a style guide, or brand guidelines.\n- **Design tokens** — a tokens file (`tokens.css`\u002F`tokens.ts`), CSS `:root` custom properties,\n  a Tailwind\u002Ftheme config, `components.json` (shadcn), `globals.css`. Extract the real hex values.\n- A **live design-system \u002F storybook page** — often the truest \"how to compose screens\" reference.\n- `CLAUDE.md` for any stated brand\u002FUX rules.\n\nCapture: primary\u002Fsecondary\u002Faccent brand colors (real hexes), neutrals, typeface(s), corner radius\nscale, light\u002Fdark support, and the reusable component vocabulary.\n\n**If NO design source exists:** offer to author a `design.md` from whatever tokens\u002Fassets do exist\n(sample brand colors straight from the logo asset if needed — don't eyeball). Get the user to\nconfirm the palette before generating. A wrong brand wastes every screen.\n\n## STEP 1 — Stitch design system (once per brand)\n\n- Reuse an existing project if appropriate, else `create_project`.\n- `create_design_system` with the project's real tokens mapped to Stitch params:\n  - `colorMode` LIGHT\u002FDARK to match the project (many are light-only).\n  - `headlineFont`\u002F`bodyFont`\u002F`labelFont` → the project's typeface (enum, e.g. `INTER`).\n  - `roundness` → closest to the project's radii (`ROUND_FOUR` for ~4–6px, `ROUND_EIGHT` for ~8px).\n  - `customColor` + `overridePrimaryColor` = brand primary; `overrideSecondaryColor` = secondary\u002Fink;\n    `overrideTertiaryColor` = accent; `overrideNeutralColor` = a representative neutral.\n  - `colorVariant: FIDELITY` to hold close to the seed colors.\n  - `designMd`: a COMPACT brand spec (palette + type + shape + a few usage rules + product tone).\n- Keep the returned `assets\u002F\u003Cid>` — pass it as `designSystem` to every generation for consistency.\n\n## STEP 2 — Generate screens\n\n- For each screen: `generate_screen_from_text` with `projectId`, the `designSystem` id, `deviceType`\n  (DESKTOP\u002FMOBILE\u002FTABLET), and a detailed prompt.\n- **Prompt recipe:** name the screen's job; specify layout top-to-bottom; give REAL copy (plain-English,\n  outcome-focused, never system jargon); call out brand usage explicitly (one primary action in the\n  primary color per screen, accent used sparingly, ink for headings); for in-context screens, describe\n  the app chrome (sidebar\u002Ftop bar) so it reads grounded; restate shape (small radii, no pills) and tone.\n- **Generate ONE screen first, verify the brand, THEN batch the rest** — cheaper to fix the design\n  system once than N times.\n\n## STEP 3 — Verify by LOOKING (non-negotiable)\n\nFor every generated screen, download the `screenshot.downloadUrl` and **Read the PNG to actually view\nit.** Confirm the brand colors, type, radii, and copy are right. TypeScript\u002Ftests can't catch a\nwrong-looking screen — your eyes are the gate. If a screen is off, fix via `edit_screens` (targeted\nchange) or `generate_variants` (explore alternatives), not a blind re-generate.\n\n## STEP 4 — Present for review\n\n- Build a single **review gallery** (a self-contained HTML Artifact with the screenshots embedded as\n  data URIs, annotated with each screen's role in the flow) so the user reviews everything in one place.\n- Also give the **Stitch project link** (`https:\u002F\u002Fstitch.withgoogle.com\u002Fprojects\u002F\u003CprojectId>`) as the\n  editable storyboard.\n- These are **mockups, not implementation.** Get the user's approval \u002F edits before any code is written.\n  On approval, hand off to implementation (or the project's ship\u002Fbuild flow). Never present a mockup as\n  a shipped feature.\n\n## Gotchas (learned in practice)\n\n- Call Stitch tools with **structured params**, never a raw-JSON string wrapper — it fails to parse.\n- A one-off **\"Request contains an invalid argument\"** is usually transient — **retry once** before\n  diagnosing; the second identical call typically succeeds.\n- `list_screens` can return empty even when screens exist — rely on each generation's returned screen\n  id\u002Fname, not on list_screens.\n- Each generation **echoes the full `designMd`** back in the response — keep that markdown tight to\n  avoid bloating context across many screens.\n- Screenshot URLs are large signed Google URLs — `curl -L` them; they may expire, so download promptly.\n- **`edit_screens` on text-only changes patches the live DOM but does NOT refresh the exported\n  screenshot\u002FhtmlCode** — the API keeps serving the pre-edit snapshot (same file id), so a downloaded\n  thumbnail lags even though the Stitch web app shows the change. Layout-level edits (e.g. removing a\n  sidebar) DO trigger a full re-render with a NEW screen id + fresh screenshot. So: verify text edits in\n  the Stitch UI, and if you need an accurate exported thumbnail of a text-only change, re-generate the\n  screen rather than trusting the screenshot URL.\n- Don't over-generate: cover the distinct screens + one representative \"template\" screen for repeated\n  patterns (e.g. one feature-guide covers the rest); note the repeats rather than rendering all.\n",{"name":5,"description":7},"main","f27dd0e6c87efa56cfdea304aa3e89e63c02711b","plugins\u002Fdevopsoscar\u002Fskills\u002Fdesign-mockup","https:\u002F\u002Fgithub.com\u002Fsharepointoscar\u002Fagent-workflow-skills","https:\u002F\u002Fgithub.com\u002Fsharepointoscar","Author | DevOps Practitioner | Docker | Terraform | Kubernetes | Jenkins X  | AWS | GCP | Azure and SP Veteran (since code-name Tahoe)","2026-11-11 12:44:52",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add sharepointoscar\u002Fagent-workflow-skills --skill design-mockup",{"tool":37,"command":38},"bunx","bunx skills add sharepointoscar\u002Fagent-workflow-skills --skill design-mockup",{"tool":40,"command":41},"pnpm","pnpm dlx skills add sharepointoscar\u002Fagent-workflow-skills --skill design-mockup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsharepointoscar\u002Fagent-workflow-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fdevopsoscar\u002Fskills\u002Fdesign-mockup\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M79FQNYDNR7TYQAM5061GVKR","web-performance-optimization","Optimize website and web application performance including loading speed, Core Web Vitals, bundle size, caching strategies, and runtime performance","https:\u002F\u002Fgithub.com\u002Fsharepointoscar\u002Fagent-workflow-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fskills-web-frontend\u002Fskills\u002Fweb-performance-optimization\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M79FQK396EEGX40QA7B9S404","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Fsharepointoscar\u002Fagent-workflow-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fskills-web-frontend\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79FQFK4GJCG8HVRG8JQF4QH","wcag-audit-patterns","Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.","https:\u002F\u002Fgithub.com\u002Fsharepointoscar\u002Fagent-workflow-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fskills-web-frontend\u002Fskills\u002Fwcag-audit-patterns\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M79FQ7WRQXC4D20Q2HTBMDG7","ui-ux-pro-max","UI\u002FUX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn\u002Fui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI\u002FUX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn\u002Fui MCP for component search and examples.","https:\u002F\u002Fgithub.com\u002Fsharepointoscar\u002Fagent-workflow-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fskills-web-frontend\u002Fskills\u002Fui-ux-pro-max\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M79FPZC11BPBWDCVK2TER0RC","stitch-ui-design","Expert guide for creating effective prompts for Google Stitch AI UI design tool. Use when user wants to design UI\u002FUX in Stitch, create app interfaces, generate mobile\u002Fweb designs, or needs help crafting Stitch prompts. Covers prompt structure, specificity techniques, iteration strategies, and design-to-code workflows for Stitch by Google.","https:\u002F\u002Fgithub.com\u002Fsharepointoscar\u002Fagent-workflow-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fskills-web-frontend\u002Fskills\u002Fstitch-ui-design\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79FPTMMM3C57JN25RTRX2HR","scroll-experience","Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences. Like NY Times interactives, Apple product pages, and award-winning web experiences. Makes websites feel like experiences, not just pages. Use when: scroll animation, parallax, scroll storytelling, interactive story, cinematic website.","https:\u002F\u002Fgithub.com\u002Fsharepointoscar\u002Fagent-workflow-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fskills-web-frontend\u002Fskills\u002Fscroll-experience\u002FSKILL.md",[],[]]