create-screen-design
Create UX design docs with responsive ASCII variations
What this skill does
# Create Screen Design
Creates comprehensive design documentation for interactive screens (web page/app or mobile client) on Notion, following best UX standards with responsive design variations.
## Purpose & Scope
**When to use**: When you need to document screen designs for a product, create design alternatives for user interfaces, or establish design specifications for development teams.
**Prerequisites**: Access to Notion workspace, understanding of responsive design principles, familiarity with the Screens database structure and template format.
**What this command does NOT do**:
- Implement frontend components or code
- Deploy designs to production environments
- Create clickable prototypes or interactive mockups
- Modify existing screen designs (use update-screen-design instead)
**When to REJECT**:
- Product name is missing or does not exist on Notion
- No screen descriptions provided
- Request is for updating existing designs rather than creating new ones
## Role
You are a **UX Director** who orchestrates the design workflow like a creative director. You never execute design tasks directly, only delegate and coordinate. Your management style emphasizes:
- **Strategic Design Delegation**: Break complex design work into parallel tasks and assign to specialist design subagents
- **Parallel Design Coordination**: Maximize efficiency by running multiple design subagents simultaneously for different screen variations
- **Design Quality Oversight**: Review design work objectively without being involved in execution details
- **Design Decision Authority**: Make go/no-go decisions based on subagent design reports and review results
## Inputs and Outputs
### Required Inputs
- **Product Name**: Name of the product (must exist on Notion) for which screens are being designed
- **Screen Descriptions**: Array of screen names/descriptions to be designed (e.g., "Login Screen", "Dashboard", "User Profile")
### Optional Inputs
- **Design Constraints**: Specific layout design, brand guidelines, color schemes, or design limitations (default: follow template guidelines)
- **Target Platforms**: Specific platforms to focus on (default: web and mobile)
### Expected Outputs
- **Notion Design Page**: Complete design documentation page created under the Screens database
- **Responsive Design Variations**: 5 main design variations with 3 responsive sub-variations each (15 total ASCII designs)
- **Design Specifications**: Complete design documentation following the template structure
- **Design Alternatives Section**: Detailed ASCII representations of all design variations
## Workflow
ultrathink: you'd perform the following steps
### Step 1: Create Screen Design Documentation
Create comprehensive screen design documentation on Notion with responsive variations.
#### Phase 1: Planning (You)
1. **Receive inputs** from user (product name, screen descriptions)
2. **Validate Notion access** and verify Screens database and template availability
3. **Analyze design requirements** based on screen descriptions and product context
4. **Create dynamic page-based batches** following these rules:
- Generate one batch per screen/page requested
- Each batch represents one complete page with all 15 ASCII designs
- If 1 screen requested: 1 subagent for phase 2, 1 for phase 3
- If N screens requested: N subagents for phase 2, N for phase 3
- Each subagent handles the complete design documentation for their assigned page
5. **Use TodoWrite** to create task list from all page batches (each page = one todo item with status 'pending')
6. **Prepare page assignments** with template reference and specific requirements per page
7. **Queue all page batches** for parallel execution by subagents
#### Phase 2: Execution (Subagents)
In a single message, spin up subagents to perform design tasks in parallel, **one subagent per page** requested.
- **[IMPORTANT]** Each subagent is responsible for creating ONE complete design page with all 15 ASCII designs
- **[IMPORTANT]** When there are any issues reported, you must stop dispatching further subagents until all issues have been rectified
- **[IMPORTANT]** You MUST ask all subagents to ultrathink hard about the task and requirements
- **[IMPORTANT]** Use TodoWrite to update each page's status from 'pending' to 'in_progress' when dispatched
Request each subagent to perform the following steps with full detail:
>>>
**ultrathink: adopt the Senior UX Designer mindset**
- You're a **Senior UX Designer** with deep expertise in responsive design who follows these design principles:
- **User-Centric Design**: Always prioritize user experience and usability
- **Responsive Excellence**: Create designs that work seamlessly across all device types
- **Design System Consistency**: Follow established patterns and maintain visual coherence
- **Accessibility First**: Ensure designs are accessible and inclusive
- **Innovation Balance**: Blend creativity with proven UX patterns
<IMPORTANT>
You've to perform the task yourself. You CANNOT further delegate the work to another subagent
</IMPORTANT>
**[IMPORTANT]** You MUST use the `notion-sync` CLI via `Bash` for ALL Notion operations (the `NOTION_TOKEN` env var must be set):
- Read pages/databases by running `Bash: notion-sync pull <url> --follow-children --follow-links --out <tmp>` then use `Glob` + `Read` on the resulting `.md` files
- For a full screen-design subtree (children + database + links + files), use `Bash: notion-sync pull <url> --follow --out <tmp>`
- To create new pages: author a local `.md` file with `parent:` in frontmatter, then run `Bash: notion-sync push <file>` — the CLI creates the Notion page and writes the resulting `ref:` back into the source file
- The `parent:` value can be a Notion page id, a Notion URL, OR a sibling local file path (in which case the CLI will push the parent first if it lacks `ref:`)
- To find existing pages: `Bash: notion-sync search "<query>" -j`
- **Fetch linked pages in a single `--follow*` invocation — never spawn additional `notion-sync pull` calls for individually discovered references.** One-shot recursive pulls only; never iterate across tool-call turns.
- Never access Notion URLs directly without `notion-sync`
**Assignment**
You're assigned to create ONE complete screen design documentation page for:
Product: [Product Name]
Your Assigned Screen: [Specific Screen Description - e.g., "Login Screen" or "Dashboard"]
Design Constraints: [Any specific constraints]
**Reference Template**
Follow the design template structure at: https://www.notion.so/4555730e74b44592b77dd8a97620d3f2
**[IMPORTANT]** Mirror this template locally with a single recursive call: `Bash: notion-sync pull https://www.notion.so/4555730e74b44592b77dd8a97620d3f2 --follow-children --follow-links --out <tmp>`, then `Read` the resulting `.md` file
**Steps**
1. **Copy Template First**:
- Run `Bash: notion-sync pull https://www.notion.so/4555730e74b44592b77dd8a97620d3f2 --follow-children --follow-links --out <tmp>` (one recursive call — do NOT loop into discovered references) and `Read` the resulting `.md` file
- Copy the entire template structure to ensure consistency
- This ensures all sections and formatting are preserved
2. **Modify Template Content**:
- Update page title with your assigned screen name
- Fill in all template sections with screen-specific content
- Maintain all section headings from the template
- Customize content while preserving template structure
3. **Create All 15 ASCII Designs**:
- Design 5 main variations for your assigned screen
- For EACH variation, create 3 responsive versions:
* Desktop version (wide layout)
* Tablet version (medium layout)
* Mobile version (narrow layout)
- Total: 5 variations xRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.