Fluxwing Component Creator
Create uxscii components with ASCII art and structured metadata when user wants to create, build, or design UI components. Use when working with .uxm files, when user mentions .uxm components, or when creating buttons, inputs, cards, forms, modals, or navigation.
What this skill does
# Fluxwing Component Creator
You are helping the user create uxscii component(s) using the **uxscii standard** by orchestrating the designer agent.
## Data Location Rules
**READ from (bundled templates - reference only):**
- `{SKILL_ROOT}/templates/` - 11 component templates
- `{SKILL_ROOT}/docs/` - Documentation
**INVENTORY sources:**
- `./fluxwing/components/` - User components
- `./fluxwing/library/` - Customized templates
- `{SKILL_ROOT}/templates/` - Bundled templates (READ-ONLY)
**WRITE to (project workspace - via designer agent):**
- `./fluxwing/components/` - Your created components
**NEVER write to skill directory - it's read-only!**
**LOAD for copy-on-update logic:**
- `{SKILL_ROOT}/../shared/docs/copy-versioning.md` - Versioning pattern for existing components
## Your Task
Help the user create uxscii component(s) by gathering requirements and spawning designer agent(s).
**Supports both single and multi-component creation:**
- Single: "Create a submit button"
- Multiple: "Create submit-button, cancel-button, and email-input" (agents run in parallel)
## Speed Modes
Fluxwing supports two creation modes optimized for different use cases:
### Fast Mode (Scaffolding)
**When:** Scaffolder creates multiple components in parallel
**Speed:** ~10 seconds per component
**Output:** `.uxm` only (fidelity: sketch)
**Method:** Template-based variable substitution
Fast mode skips:
- Documentation loading
- ASCII art generation
- Detailed metadata
### Detailed Mode (Standalone)
**When:** User explicitly creates single component
**Speed:** ~60-90 seconds per component
**Output:** `.uxm` + `.md` (fidelity: detailed)
**Method:** Full docs, careful ASCII generation
Detailed mode includes:
- Complete documentation reference
- Hand-crafted ASCII art
- Rich metadata with examples
**Default:** Fast mode when called by scaffolder, detailed mode otherwise
## Workflow
### Step 1: Determine Creation Mode & Parse Request
**First, determine creation mode:**
Check context to decide fast vs detailed mode:
**Use Fast Mode if:**
- Called by scaffolder skill (check for "screen context" in request)
- User explicitly requests "fast" or "quick" component
- Creating multiple components (6+ components)
**Use Detailed Mode if:**
- User creating single component interactively
- User requests "detailed" or "production" quality
- No screen context provided
**Default:** Detailed mode (safer, better quality)
**Then, detect if user wants single or multiple components:**
1. **Single component request**:
- "Create a submit button"
- "I need a card component"
- Proceed with single-component workflow (Steps 2-4)
2. **Multiple component request**:
- "Create submit-button, cancel-button, and email-input"
- "I need a button, input, and card"
- "Create these components: [list]"
- Proceed with multi-component workflow (see Step 3b)
**For each component, gather:**
- **Component name** (will be converted to kebab-case, e.g., "Submit Button" → "submit-button")
- **Component type**: button, input, card, navigation, form, list, modal, table, badge, alert, container, text, image, divider, or custom
- **Key properties**: What should be configurable? (text, colors, sizes, etc.)
- **Visual style preferences**: rounded, sharp, minimal, detailed, etc.
**If details are missing**: Make reasonable assumptions based on component type and common patterns. Don't over-ask.
**Note**: Components are created with default state only for fast MVP prototyping. Users can expand components later to add interactive states (hover, focus, disabled, etc.).
### Step 2: Check for Similar Templates
Browse available templates to offer starting points:
```typescript
// Check bundled templates
const bundledTemplates = glob('{SKILL_ROOT}/templates/*.uxm');
// Check user library
const libraryTemplates = glob('./fluxwing/library/*.uxm');
// Suggest similar templates if found
if (similarTemplates.length > 0) {
console.log(`Similar templates found: ${similarTemplates.join(', ')}`);
console.log('Would you like to base this on an existing template or create from scratch?');
}
```
### Step 3: Pre-Creation Validation (Check for Existing Component)
**IMPORTANT**: Before creating any component, check if it already exists to prevent data loss.
**For each component you plan to create:**
1. **Convert to kebab-case ID**:
```
"Submit Button" → "submit-button"
"User Profile Card" → "user-profile-card"
```
2. **Check if component exists**:
```bash
# Check for existing component
test -f ./fluxwing/components/{component-id}.uxm
```
3. **If component EXISTS**:
**Inform user and offer choices**:
```
Component '{component-id}' already exists (version {current-version}).
Options:
(a) Create new version (copy-on-update: {component-id}-v{N+1})
(b) Create with different name
(c) Cancel operation
What would you like to do?
```
**Handle user response**:
- **Choice (a) - Create new version**:
1. Load copy-versioning logic from `{SKILL_ROOT}/../shared/docs/copy-versioning.md`
2. Read existing `{component-id}.uxm`
3. Find highest version (check for `{component-id}-v2`, `-v3`, etc.)
4. Calculate next version: `v{N+1}`
5. Pass to designer agent with versioning parameters:
- `baseComponentId`: Original ID (e.g., "submit-button")
- `newComponentId`: Versioned ID (e.g., "submit-button-v2")
- `baseOnExisting`: true
- `sourceVersion`: Highest existing version
6. Designer creates `{component-id}-v{N+1}.uxm` and `.md`
7. Metadata: Increment minor version (1.0.0 → 1.1.0), update modified, preserve created
- **Choice (b) - Different name**:
1. Ask: "What would you like to name this component?"
2. Wait for user response
3. Use new name for component ID
4. Proceed with normal creation
- **Choice (c) - Cancel**:
1. Do not create any files
2. Inform user: "Operation cancelled. No files were created."
3. Exit workflow
4. **If component DOES NOT exist**:
- Proceed with normal creation workflow (no versioning needed)
- Component will be created as `{component-id}.uxm` (no version suffix)
- Initial version: 1.0.0
**For multiple components**: Check existence for EACH component individually. Some may need versioning, others may not.
## Agent Prompts
### Fast Mode Agent (For Scaffolder)
Use this when creating multiple components quickly:
```typescript
Task({
subagent_type: "general-purpose",
// Note: model parameter not yet supported by Task tool
description: "Create ${componentName} (fast)",
prompt: `Create sketch-fidelity uxscii component from template.
Component: ${componentName}
Type: ${componentType}
Screen context: ${screenContext}
${baseOnExisting ? `
VERSIONING MODE:
- Base on existing: ${baseComponentId}
- New component ID: ${newComponentId}
- Source version: ${sourceVersion}
- Copy-on-update: Increment minor version, preserve created timestamp
` : ''}
FAST MODE - Speed is critical! <10 seconds target.
Your task:
1. ${baseOnExisting ? `Load existing: ./fluxwing/components/${sourceVersion}.uxm` : `Load minimal template: {SKILL_ROOT}/templates/minimal/${componentType}.uxm.template`}
2. ${baseOnExisting ? `Read current version number and metadata.created timestamp` : `If template not found, FAIL with error: "No template found for type: ${componentType}"`}
3. Replace template variables (component type specific):
**Common variables (all types):**
- {{id}} = "${componentId}"
- {{name}} = "${componentName}"
- {{description}} = "${description || 'Component for ' + screenContext}"
- {{timestamp}} = "${new Date().toISOString()}"
**Component-specific variables:**
| Type | Variables |
|------------|-------------------------------------------|
| button | {{label}}, {{variant}} |
| input | {{placeholder}}, {{type}}, {{value}} Related 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.