pencil-to-code▌
phrazzld/claude-config · updated Apr 8, 2026
MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.
Export Pencil .pen designs to production React/Tailwind code.
Pencil to Code
Export Pencil .pen designs to production React/Tailwind code.
Interface
Input:
- Frame ID to export (or entire document)
- Target framework: React (default), Vue, HTML
- Optional: Component name, output path
Output:
- React component(s) with Tailwind classes
- Tailwind theme configuration (from .pen variables)
- Optional: Screenshot comparison for validation
Workflow
1. Read Design Structure
// Get full frame tree
mcp__pencil__batch_get({
filePath: "<path>.pen",
nodeIds: ["frameId"],
readDepth: 10,
resolveInstances: true,
resolveVariables: true
})
// Get design variables/theme
mcp__pencil__get_variables({ filePath: "<path>.pen" })
2. Extract Design Tokens
Transform .pen variables → Tailwind theme:
/* From .pen variables */
@theme {
--color-primary: [from variables.colors.primary];
--color-background: [from variables.colors.background];
--font-sans: [from variables.fonts.body];
/* ... */
}
Reference: references/token-extraction.md
3. Map Nodes to Components
| .pen Node Type | React Output |
|---|---|
frame with layout |
<div className="flex ..."> |
frame with children |
Component with children |
text |
<p>, <h1-6>, or <span> |
ref (instance) |
Reusable component |
rectangle |
<div> with fill |
ellipse |
<div className="rounded-full"> |
image |
<img> or fill: url() |
Reference: references/node-mapping.md
4. Generate Code
Component structure:
// components/[ComponentName].tsx
import { cn } from "@/lib/utils"
interface [ComponentName]Props {
className?: string
// Extracted props from design
}
export function [ComponentName]({ className, ...props }: [ComponentName]Props) {
return (
<div className={cn("[tailwind classes]", className)}>
{/* Nested structure */}
</div>
)
}
Tailwind mapping:
.pen property → Tailwind class
--------------------------------
fill: #000 → bg-black
layout: horizontal → flex flex-row
gap: 16 → gap-4
padding: [16,24,16,24] → py-4 px-6
fontSize: 24 → text-2xl
fontWeight: 700 → font-bold
cornerRadius: [8,8,8,8] → rounded-lg
5. Validate (Optional)
// Screenshot the .pen frame
mcp__pencil__get_screenshot({ nodeId: "frameId" })
// Compare visually with rendered React
// (Manual step or browser automation)
6. Output
## Generated Components
### [ComponentName]
- File: `components/[ComponentName].tsx`
- Props: [list extracted props]
### Theme Configuration
- File: `app/globals.css` (additions)
## Verification
Screenshot comparison: [attached]
Translation Rules
Layout System
.pen Tailwind
--------------------------------------
layout: "vertical" → flex flex-col
layout: "horizontal" → flex flex-row
layout: "grid" → grid
alignItems: "center" → items-center
justifyContent: "center" → justify-center
gap: 8 → gap-2
gap: 16 → gap-4
gap: 24 → gap-6
width: "fill_container" → w-full
height: "fill_container" → h-full
Spacing (8-point grid)
.pen padding Tailwind
----------------------------------------
[8,8,8,8] → p-2
[16,16,16,16] → p-4
[16,24,16,24] → py-4 px-6
[24,32,24,32] → py-6 px-8
Typography
.pen Tailwind
----------------------------------------
fontSize: 12 → text-xs
fontSize: 14 → text-sm
fontSize: 16 → text-base
fontSize: 20 → text-xl
fontSize: 24 → text-2xl
fontSize: 32 → text-3xl
fontSize: 48 → text-5xl
fontWeight: 400 → font-normal
fontWeight: 500 → font-medium
fontWeight: 600 → font-semibold
fontWeight: 700 → font-bold
Colors
.pen Tailwind
----------------------------------------
fill: "#FFFFFF" → bg-white
fill: "#000000" → bg-black
fill: variable → bg-[var(--color-name)]
textColor: "#6B7280" → text-gray-500
stroke: "#E5E5E5" → border-gray-200
Border Radius
.pen cornerRadius Tailwind
----------------------------------------
[0,0,0,0] → rounded-none
[4,4,4,4] → rounded
[8,8,8,8] → rounded-lg
[16,16,16,16] → rounded-2xl
[9999,9999,9999,9999] → rounded-full
Constraints
- Single concern: Export → code. No design modifications.
- Tailwind 4 @theme: CSS-first token system
- React + TypeScript: Default output target
- Semantic HTML: Choose appropriate elements
- Accessibility: Include aria attributes where detectable
References
references/node-mapping.md— Complete node → component mappingreferences/token-extraction.md— Variable → theme extractiondesign-tokens/— Token system conventions
Integration
Called by:
design-explorationorchestrator (after direction selection)- Direct user invocation
Composes:
design-tokens(for theme structure)
How to use pencil-to-code on Cursor
AI-first code editor with Composer
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
- ›Cursor installed and configured on your development machine
- ›Node.js version 16.0+ with npm package manager (verify with
node --version) - ›Active project directory or workspace where you want to add pencil-to-code
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
The skills CLI fetches pencil-to-code from GitHub repository phrazzld/claude-config and configures it for Cursor.
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
Verify installation
Confirm successful installation by checking the skill directory location:
Reload or restart Cursor to activate pencil-to-code. Access the skill through slash commands (e.g., /pencil-to-code) or your agent's skill management interface.
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
List & Monetize Your Skill
Submit your Claude Code skill and start earning
Use Cases▌
User Story & Requirements Generation
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Competitive Analysis
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Roadmap Prioritization
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
Make data-driven prioritization decisions faster
Stakeholder Communication
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Implementation Guide▌
Prerequisites
- ›Claude Desktop or compatible AI client
- ›Access to product documentation and roadmap tools (Jira, Notion, etc.)
- ›Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
- ›Stakeholder contact information and communication channels
Time Estimate
30-60 minutes to see productivity improvements
Installation Steps
- 1.Install product management skill
- 2.Start with user story generation for known feature
- 3.Progress to competitive analysis: research 2-3 competitors
- 4.Use for roadmap prioritization: apply RICE/ICE scoring
- 5.Draft stakeholder communications and refine based on feedback
- 6.Build template library for recurring PM tasks
- 7.Share effective prompts with product team
Common Pitfalls
- ⚠Not validating competitive research—verify facts before sharing
- ⚠Accepting user stories without involving engineering team
- ⚠Over-relying on frameworks without qualitative judgment
- ⚠Not customizing outputs to company culture and communication style
- ⚠Skipping stakeholder validation of generated requirements
Best Practices▌
✓ Do
- +Validate research and competitive analysis with real data
- +Collaborate with engineering when generating technical requirements
- +Customize frameworks and templates to your company context
- +Use skill for first drafts, refine with stakeholder input
- +Document successful prompt patterns for PM tasks
- +Combine AI efficiency with human judgment and intuition
✗ Don't
- −Don't publish competitive analysis without fact-checking
- −Don't finalize user stories without engineering review
- −Don't make prioritization decisions solely on AI scoring
- −Don't skip customer validation of generated requirements
- −Don't ignore company-specific context and culture
💡 Pro Tips
- ★Provide context: company goals, constraints, customer feedback
- ★Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
- ★Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
- ★Use skill for 70% generation + 30% customization to company needs
When to Use This▌
✓ Use When
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid When
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
Learning Path▌
- 1Basic: user stories, feature specs, status updates
- 2Intermediate: competitive analysis, prioritization frameworks, PRDs
- 3Advanced: product strategy, go-to-market planning, OKR setting
- 4Expert: product vision, market positioning, business model innovation
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.6★★★★★38 reviews- ★★★★★Ira Mehta· Dec 28, 2024
pencil-to-code has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Ganesh Mohane· Dec 20, 2024
We added pencil-to-code from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Lucas Brown· Dec 20, 2024
pencil-to-code fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Mia Abbas· Dec 16, 2024
Useful defaults in pencil-to-code — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Sakshi Patil· Nov 11, 2024
Useful defaults in pencil-to-code — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Soo Nasser· Nov 7, 2024
We added pencil-to-code from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Zaid Rahman· Oct 26, 2024
pencil-to-code reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Chaitanya Patil· Oct 2, 2024
Registry listing for pencil-to-code matched our evaluation — installs cleanly and behaves as described in the markdown.
- ★★★★★Lucas Desai· Sep 21, 2024
Solid pick for teams standardizing on skills: pencil-to-code is focused, and the summary matches what you get after install.
- ★★★★★Arya Diallo· Sep 1, 2024
I recommend pencil-to-code for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
showing 1-10 of 38