ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 3/5

design-engineering

Orchestrate iterative design and frontend engineering work through research, planning, sub-agent execution, and validation loops. Use when a visual/UI task requires multiple iterations, when the first implementation needs refinement based on feedback, when choosing between competing technical approaches (Canvas vs SVG vs CSS), or when coordinating sub-agents on design-heavy work. Covers animation architecture decisions, progressive enhancement patterns, performance-aware rendering choices, and the research→plan→execute→validate workflow. Complements frontend-design (which handles aesthetics) by adding engineering discipline, iteration management, and technical decision-making.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/bloodandeath/keats-design-engineering
Or

What This Skill Does

The design-engineering skill acts as an orchestrator for complex, iterative frontend development tasks. Unlike standard coding skills that aim for a single-pass implementation, this skill implements a rigorous research-plan-execute-validate loop to ensure high-quality visual output. It bridges the gap between creative design intent and disciplined engineering, managing the lifecycle of a task through structured phases including technical research, architectural decision-making, sub-agent coordination, and iterative refinement. It is specifically designed to handle tasks where visual fidelity, performance, and progressive enhancement are critical, requiring more than a simple "code it" command.

Installation

To add this skill to your OpenClaw agent, execute the following command in your terminal or command-line interface: clawhub install openclaw/skills/skills/bloodandeath/keats-design-engineering

Use Cases

  • Complex UI Architectures: Developing data-heavy dashboards or interactive canvases where you need to decide between Canvas, SVG, or DOM-based rendering.
  • Animation-Heavy Features: Architecting performant web animations that must maintain 60fps across devices.
  • Design Systems Integration: Managing the evolution of a component library where individual visual tweaks require engineering validation to prevent regression.
  • Technical Refactoring: Updating legacy rendering logic (e.g., migrating from heavy JS animations to CSS-based transforms) while maintaining existing visual requirements.

Example Prompts

  1. "Design-engineering: We need a high-performance particle visualization for the landing page. Research three approaches: Three.js, raw HTML5 Canvas, and SVG-based motion. Compare them based on mobile performance and load time, then propose an architecture."
  2. "Refine the dashboard chart component. The current implementation is sluggish with 500+ data points. Research why it's lagging, present a plan to improve the rendering pipeline, and coordinate the necessary sub-agents to execute the performance fix."
  3. "Build an interactive onboarding flow. Start by researching design patterns for similar products, create a phase-based plan for the implementation, and manage the sub-agents to build the individual components. Remember to perform a validation check after each animation step."

Tips & Limitations

The design-engineering skill relies heavily on your willingness to approve plans. Do not skip the plan phase, as it is the most critical checkpoint for project success. Always define clear validation criteria in your prompt; without them, the agent may struggle to identify when a UI iteration is 'complete.' Keep in mind that this skill does not replace the frontend-design skill; use this one for the how and structure, and use that one for the look and feel. The skill is designed for iterative work—if you are looking for a quick, one-off script, this might be overkill.

Metadata

Stars4190
Views0
Updated2026-04-18
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-bloodandeath-keats-design-engineering": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#frontend#engineering#ui-development#iteration#architecture
Safety Score: 3/5

Flags: file-write, file-read, code-execution

Related Skills

agent-cost-monitor

Real-time token usage and cost tracking across all your OpenClaw agents — alerts, budgets, and optimization tips

bloodandeath 4190

web-monitor

Monitor web pages for content changes and get alerts. Track URLs, detect updates, view diffs. Use when asked to watch a website, track changes on a page, monitor for new posts/content, set up page change alerts, or check if a site has been updated. Supports CSS selectors for targeted monitoring.

bloodandeath 4190

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

bloodandeath 4190

code-reviewer

Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Default behavior is a single-model adversarial review that identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Supports an optional `--dual` mode for heavier cross-model iterative review when deeper scrutiny is worth the added cost and latency. Use when users ask to "critically review my code", "critically review" code or a PR, "critique my code", "find issues in my code", "find issues" in code, ask "what's wrong with this code", ask to "review this code", "critique my PR", say "double review this", or request a "cross-model review". Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required Changes, Suggestions, Noted) and specific, actionable recommendations.

bloodandeath 4190

code-reviewer

Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Default behavior is a single-model adversarial review that identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Supports an optional `--dual` mode for heavier cross-model iterative review when deeper scrutiny is worth the added cost and latency. Use when users ask to "critically review my code", "critically review" code or a PR, "critique my code", "find issues in my code", "find issues" in code, ask "what's wrong with this code", ask to "review this code", "critique my PR", say "double review this", or request a "cross-model review". Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required Changes, Suggestions, Noted) and specific, actionable recommendations.

bloodandeath 4190