Grasshopper modeling can require many repeated component, connection, and parameter steps. This skill turns structured design notes into executable workflow files and local MCP actions.

Generative art requests often need structure, reproducibility, and usable controls. This skill guides Claude, Codex, and Claude Code to create original p5.js artwork with seeded variation.

Removing or replacing a video region across frames can cause visual drift and broken motion. This skill selects a suitable RunComfy route and provides focused prompts for consistent edits.

Changing image lighting usually requires a new shoot or manual editing. This skill helps Claude, Codex, or Claude Code route still-image relighting requests through RunComfy models.

Choosing a lip-sync model and request format can be difficult across different input types. This skill selects a suitable RunComfy route and prepares the CLI invocation.

Cropped images often need a wider canvas for banners, social posts, or product layouts. This skill guides Claude, Codex, and Claude Code to outpaint images with RunComfy models while preserving the original subject.

Precise image edits need clear model routing and focused prompts. This skill helps Claude, Codex, and Claude Code call Flux 1 Kontext Pro through RunComfy with practical prompt patterns.

Creative teams need fast image drafts without losing control over prompt structure and model settings. This skill guides Claude, Codex, and Claude Code to use RunComfy Flux 2 Klein variants for rapid concepts and polished outputs.

UI and UX work often loses consistency across screens, states, and decisions. This skill gives Claude, Codex, and Claude Code a concise checklist for design reviews and documentation.

Storytelling products need profile cards that show identity, context, and AI assistance without disrespecting contributors. This skill gives Claude, Codex, and Claude Code structured design guidance for Empathy Ledger card components.

Teams can lose consistency when dark themes and component rules are undocumented. This skill provides practical visual rules for a modern Physical AI Hub interface.

Frontend teams need consistent UI components and page sections. This skill guides Claude, Codex, and Claude Code to use Shadcn MCP and 21st.dev MCP.

Teams lose time translating theme choices into repeatable shadcn commands. This skill uses tweakcn references to select a theme and guide installation.

Creating polished logo assets often requires multiple design and cleanup steps. This skill generates a logo with Replicate, removes the background, and saves a transparent PNG.

Creating consistent website imagery can slow down component work. This skill generates, optimizes, and saves WebP assets with Replicate and Sharp.

Teams need consistent visual assets for product pages, docs, and marketing screens. This skill guides DALL-E generation and stores files in project asset folders.

Influencer traffic often leaves when landing pages fail to match creator messaging or simplify the offer. This skill audits message continuity and builds a prioritized conversion and testing plan.

Email HTML can fail across clients, dark mode, and image-off settings. This skill creates table-based builds and documents rendering, accessibility, and plain-text checks.

Educational image prompts often produce generic diagrams that miss the lesson goal. This skill turns lesson context into focused creative briefs for learner-appropriate visuals.

Teams need consistent UX feedback before changing interface components. This skill applies a three-part framework for position, visual weight, and spacing.