design-implementation
Streamlined UI development workflow with single-command feature implementation.Automates: dev server, browser, verification, error fixing, iteration loop.**Core Command:** "implement next feature" or "implement [feature description]"**What It Does:**1. Starts dev server (auto-detects port from package.json)2. Launches browser (visible by default, --headless available)3. Implements feature via frontend-design skill4. Verifies: console errors, TS errors, network failures, visual match5. Fixes iteratively (max 5 iterations)6. Reports completion or escalates with detailed report**Triggers:**- "implement next feature", "implement the hero section"- "verify this implementation", "check the UI"- "fix the errors", "iterate on this"- "start dev server", "manage server"
When & Why to Use This Skill
The design-implementation skill for Claude is a high-performance developer tool designed to automate the end-to-end frontend development lifecycle. By integrating dev server management, browser-based visual verification, and an iterative 'fix-it' loop, it allows developers to implement complex UI features from a single command. This skill bridges the gap between design and code by automatically detecting errors and refining the implementation until it meets visual and functional standards.
Use Cases
- Rapid UI Prototyping: Automatically build and deploy frontend components like hero sections, login forms, or navigation bars based on text descriptions or design specifications.
- Automated Visual Verification: Use the integrated Playwright runner to launch a browser and verify that the implemented UI matches the design without manual inspection.
- Iterative Debugging and Error Correction: Automatically detect and resolve TypeScript errors, console failures, and network issues through a self-correcting loop of up to five iterations.
- Dev Server Orchestration: Streamline local development by allowing the agent to auto-detect ports and manage the lifecycle of the development server (start/stop/restart) during the coding process.
- Headless Testing for CI: Execute the full implementation and verification workflow in headless mode to ensure code quality and visual consistency in automated environments.
| name | design-implementation |
|---|---|
| context | fork |
| description | | |
| Automates | dev server, browser, verification, error fixing, iteration loop. |
| **Core Command | ** "implement next feature" or "implement [feature description]" |
| **What It Does | ** |
| 4. Verifies | console errors, TS errors, network failures, visual match |
| **Triggers | ** |
Workflow Routing
| Intent | Workflow |
|---|---|
| "implement feature", "build the X" | workflows/implement-feature.md |
| "verify", "check", "screenshot" | workflows/verify-visual.md |
| "fix errors", "fix the issues" | workflows/fix-errors.md |
| "start server", "stop server" | workflows/manage-server.md |
| "test interactions", "click test" | workflows/test-interactions.md |
Quick Start
# Basic usage
"implement the login form based on the Figma design"
# With specific file
"implement the feature described in thoughts/features/hero-section.md"
# Headless mode (CI/testing)
"implement next feature --headless"
# Just verify current state
"verify the current implementation"
Configuration
Edit config.json in this skill directory:
{
"browser": {
"headless": false,
"viewport": { "width": 1280, "height": 720 }
},
"server": {
"port": "auto",
"startCommand": "auto",
"hmrDelay": 2000
},
"iteration": {
"maxIterations": 5,
"layoutTolerance": 0.95
},
"figma": {
"enabled": true
}
}
Tools
| Tool | Purpose |
|---|---|
tools/playwright-runner.ts |
Browser automation (screenshot, console, network) |
tools/server-manager.ts |
Dev server lifecycle (start, stop, detect port) |
State Tracking
state.json tracks current feature progress:
{
"currentFeature": "hero-section",
"iteration": 2,
"status": "fixing",
"errors": ["console: Failed to load image"],
"lastScreenshot": "history/hero-section/iteration-2.png"
}
Integration
| Skill/Agent | When Used |
|---|---|
frontend-design |
Initial implementation |
engineer agent |
Escalate complex bugs |
design-iterator agent |
Multiple visual refinements |
History
Each feature creates artifacts in history/{feature-id}/:
spec.md- Original feature specificationiteration-{n}.png- Screenshots per iterationfigma-reference.png- Design reference (if Figma link provided)errors.log- Captured errorsreport.md- Final completion report
Note: history/ is gitignored.