Command Claude Code
Open a first-contribution PR (or bug issue) on nexu-io/open-design — works for non-coders too.
81 tagged ai design, measured the same way as everything else here.
Browse within: design-system 49accessibility 48claude-commands 48anti-slop 14awwwards 14agentic-workflow 8ai-assistant 8ai-security 8ai-toolkit 8coding-agent 8workflow 8
Command Claude Code
Open a first-contribution PR (or bug issue) on nexu-io/open-design — works for non-coders too.
Command Claude Code
Archive a completed change in the experimental workflow.
Command Claude Code
Enter explore mode - think through ideas, investigate problems, clarify requirements.
Command Cursor
Enter explore mode - think through ideas, investigate problems, clarify requirements.
superdesigndev/superdesign-skill
Command Claude Code
Analyze git changes and create a commit without Claude Code attribution.
yizhiyanhua-ai/fireworks-design
Command Claude Code
Generate a world-class frontend page via fireworks-design (explore → judge → synthesize → refine → polish).
agenisea/ai-design-engineering-cc-plugins
Command
Design and protect scalable backend systems with clean contracts, strong boundaries, and reliability.
agenisea/ai-design-engineering-cc-plugins
Command
Architect the intelligence layer — RAG pipelines, model selection, embeddings, and evaluation for agentic systems.
agenisea/ai-design-engineering-cc-plugins
Command
Create app blueprints and agent prompts from rough ideas. Generates specifications for v0, Lovable, Replit, or any AI builder.
Command
Plan UI assets for a Stark design before implementation, including references, icons, typography, generated product mocks, and optional image generation when the agent supports it.
Command
Use this command when the user asks Stark to go all out, raise design quality broadly, use libraries well, make a UI feel actually designed, or coordinate research, typography, motion, usability, implementation, and QA in one pass.
Command
Use this command when a web UI should be maintained, released, compared across runs, or used as public proof. It turns visual QA into a repeatable local/CI gate instead of a one-off screenshot check.
Command
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
Command
Use when code has drifted off the design system. Raw hex values and pixel numbers written where a token already exists, one-off components, library defaults left untouched. Finds every bypass and fixes it.
Command
Use when a design keeps getting reinvented every session. Interviews you until you share one understanding, then writes the vocabulary and the binding decisions into the repo so they survive the next context window.