New skills

Identify reusable patterns, components, and design tokens, then extract and consolidate them into the design system for systematic reuse.

Strengthen interfaces against edge cases, errors, internationalization issues, and real-world usage scenarios that break idealized designs.

Analyze and redesign the feature to perfectly match our design system standards, aesthetics, and established patterns.

Create or improve onboarding experiences that help users understand, adopt, and succeed with the product quickly.

Identify and fix performance issues to create faster, smoother user experiences.

First : Use the frontend-design skill for design principles and anti-patterns.

Reduce visual intensity in designs that are too bold, aggressive, or overstimulating, creating a more refined and approachable aesthetic without losing effectiveness.

A structured yet lightweight brainstorming skill designed to move from idea to actionable direction quickly. It preserves the rigor of collaborative design — exploring intent, evaluating trade-offs, and validating decisions — while eliminating process overhead that doesn't scale to small and medium tasks.

Gather design context for this project, then persist it for all future sessions.

Use when: User asks to generate a video, create a video from text, animate an image, make a short clip, or produce AI video.

Mode slash commands are mapped as follows.

Unity · Unreal Engine · Godot · Custom/Other

All workflows are available immediately — no sequential phases required.

Deploy any project to Vercel. Always deploy as preview (not production) unless the user explicitly asks for production.

PREREQUISITE: Read ../gws-shared/SKILL.md for auth, global flags, and security rules. If missing, run gws generate-skills to create it.

PREREQUISITE: Read ../gws-shared/SKILL.md for auth, global flags, and security rules. If missing, run gws generate-skills to create it.

Tracks LLM API costs, tokens, and latency using Tokuin CLI , and auto-generates a data-driven admin dashboard with PM insights.

Run 150+ AI apps in the cloud with a simple CLI. No GPU required.

Generate images with 50+ AI models via inference.sh CLI.

Generate videos with 40+ AI models via inference.sh CLI.

The data cleaning pipeline consists of the following 11 steps, each executed independently without deleting the original data:

Automate any Electron desktop app using agent-browser. Electron apps are built on Chromium and expose a Chrome DevTools Protocol (CDP) port that agent-browser can connect to, enabling the same snapshot-interact workflow used for web pages.

PREREQUISITE: Read ../gws-shared/SKILL.md for auth, global flags, and security rules. If missing, run gws generate-skills to create it.

PREREQUISITE: Read ../gws-shared/SKILL.md for auth, global flags, and security rules. If missing, run gws generate-skills to create it.