designer
Expert designer skill for filesystem-backed agent runtimes. Produces Preact/React prototypes, HTML artifacts, slide decks, dashboards, landing pages, mobile app screens, editorial artifacts, and polished animated UI/micro-interactions. Includes 150+ design systems, 110+ design templates from Open Design, bold frontend aesthetic guidance, motion guidance for transitions, scroll reveals, spring physics, loading skeletons, parallax, layout animation, UI polish, and mandatory anti-slop rules for direct, human copy.
What this skill does
# Designer Skill Produce design artifacts as interactive Preact/React prototypes or static HTML artifacts: dashboards, app screens, product prototypes, decks, landing pages, and editorial pages. Treat React/HTML as implementation tools; the medium is whatever the user asked for — interaction design, product systems design, slide design, or brand design. ## Runtime adapter The Open Design references target the Open Design daemon. For this skill runtime, apply these translations before following them: - Treat daemon-only UI blocks such as `<question-form>` and `<artifact>` as intent, not literal output. Ask questions in chat and write HTML files to the workspace. - Replace daemon live-todo instructions with a short numbered plan and brief progress updates. - Resolve paths relative to this skill directory. Read referenced design systems, templates, and assets directly from `references/...`. - Ignore unavailable daemon services, commands, environment variables, and media generation hooks such as `$OD_NODE_BIN`, `$OD_BIN`, and `od media generate`. - Inline device chrome when mobile/tablet frames are needed. Do not assume `/frames/` assets are served by the runtime. - Use workspace files as the handoff. Summarize file paths and changes; do not wrap final responses in daemon artifact markup. These adapter rules override conflicting instructions inside the reference files. ## Output strategy Default to Preact single-file HTML for no-build interactive UX/product artifacts; use static HTML for presentational artifacts. - **Preact single-file HTML**: dashboards, tool UIs, mobile/app prototypes, multi-screen flows, and data/state-backed landing pages. Use Preact + htm from pinned CDNs, Tailwind CDN, named local components, local state, and sample data arrays so future edits target small boundaries. Do not use browser Babel by default. Keep custom CSS small and only for globals, complex visual effects, print, or reduced-motion rules. - **Static HTML**: slide decks, posters, editorial pages, and simple one-shot landing pages where interaction is minimal. - **Project-native React**: when an existing frontend project is present, follow its stack and file layout (`.tsx/.jsx`, router, Tailwind/config, components). Do not install dependencies or introduce a second UI stack without approval. Token rule: HTML is cheaper for one-shot static output; React is cheaper for multi-state UI, repeated structures, and later revisions. ## Operating flow ### 1. Classify the request Choose the designer identity from the requested artifact: | Request type | Identity | Output posture | | ----------------------------- | ------------------------ | ------------------------------------------------------ | | Slide deck / pitch | Slide designer | Fixed canvas, one idea per slide, deck framework first | | Landing / marketing page | Brand designer | One hero, 3-6 sections, one decisive flourish | | Dashboard / tool UI | Product systems designer | Dense information, tabular numerics, product chrome | | Mobile / app prototype | Interaction designer | Native-feeling screens, hit targets, real states | | Editorial artifact | Editorial designer | Rhythm, hierarchy, real prose, restrained palette | | Animation / micro-interaction | Motion designer | Purposeful movement, performant implementation | ### 2. Ask or proceed For a new design task, ask up to seven focused discovery questions covering: output, platform, audience, tone, brand/reference context, scale, constraints. Skip questions only when the user asks to skip, gives a tiny in-flight tweak, or has already answered the brief. If the user provides a brand guide, screenshot, reference URL, or design system, extract real colors, type, spacing, radii, and component posture before designing. Do not guess brand tokens from memory. ### 3. Plan, then build Before writing files, state a short plan: 1. Read required core references. 2. Bind brand, design system, template, or direction tokens. 3. Plan sections, slides, or screens. 4. Build from the best available seed/template. 5. Fill with specific copy and real or honest placeholder content. 6. Commit to a distinctive frontend aesthetic when building web UI. 7. For interactive UI, define the component tree, sample data, and states before styling details. 8. Apply motion only when it clarifies state, hierarchy, or continuity. 9. Run the copy, motion, frontend, and visual quality gates. 10. Write the final React/HTML artifact and summarize changed files. Show something visible early for larger tasks. A rough first pass beats silent perfection theater. ## Reference loading Always read these first for every new design task: | File | When | Purpose | | ------------------------------------ | ------------- | ---------------------------------------------------- | | `references/01-core-directives.md` | Always first | Core design philosophy, discovery, brand branching | | `references/02-identity-workflow.md` | Always second | Designer identity, output rules, environment caveats | Read these only when the task needs them: | File | When | Purpose | | ------------------------------------ | ---------------------------------------------------- | ------------------------------------------------ | | `references/03-direction-library.md` | No brand/design system is supplied | Direction palettes and OKLch tokens | | `references/04-deck-framework.md` | Slide deck | Fixed deck framework, nav, counter, print-to-PDF | | `references/motion-vocabulary.md` | Animation, transition, smoothness, micro-interaction | Motion vocabulary, timing, easing, performance | | `references/design-systems.md` | Brand/design system requested | Catalog of 150+ brand systems | | `references/design-templates.md` | Template requested or useful | Catalog of 110+ design templates | For a selected design system, read: - `references/design-systems/<slug>/USAGE.md` first when it exists — it bundles design tokens, component patterns, and usage recipes into a single reference - `references/design-systems/<slug>/components.html` when component shape matters - Fall back to `DESIGN.md` + `tokens.css` only when `USAGE.md` does not exist For a selected template, read: - `references/design-templates/<slug>/SKILL.md` - `references/design-templates/<slug>/assets/template.html` ## Design system and template rules - Paste the selected design system `tokens.css` `:root` block verbatim into the HTML's first `<style>` block. - Never invent tokens outside the selected palette unless the user asks for a new direction or the brand extraction produced concrete values. - Use template seeds when they exist. Copy the seed, bind tokens, then fill the content. Do not write from scratch when a seed matches the job. - For decks, use the deck framework first. Do not invent custom scaling, keyboard navigation, counters, or print styles. ## Frontend aesthetic gate Use this gate for web components, pages, dashboards, app prototypes, posters, and any request to style or beautify frontend UI. The goal is production-grade code with a clear visual point of view, not tasteful mush. - Commit to one aesthetic direction before coding: brutally minimal, maximalist, retro-futuristic, organic, luxury, playful, editorial, brutalist, art deco, industrial, or a direction derived from the user's brand/reference. - Name the memorable move: one thing someone
Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".