designcraveyard

Decompose a design requirement into flows, pages, templates, patterns, components, atoms, and data fields using Brad Frost atomic design. Use when starting a new design project, analyzing an app for redesign, or breaking down a feature brief. Triggers on…

Define visual directions (stylescapes), generate fully styled standalone pages, source assets, and produce presentation artifacts for client review. Triggers on 'style this', 'create visual direction', 'build stylescape', 'define the look and feel'.

Compose real design system components into full responsive page layouts with real data points. Uses ds- components from the HTML Template design system. Triggers on 'wireframe this page', 'create layout', 'build screen', 'design the page structure'.

First-time setup for the Design Workflow plugin. Checks and configures API keys (OpenAI, Google Cloud/Vertex AI, Unsplash), verifies the HTML Template design system path, and installs the web-to-figma Chrome extension. Run this once before using /design.…

Generate and manipulate visual assets — icons, illustrations, images. Supports OpenAI (gpt-image-1, gpt-image-1-mini, dall-e-3), Google Vertex AI Imagen (Imagen 3/4), and Google Vertex AI Gemini (gemini-2.5-flash-image, gemini-3-pro-image-preview). Operations…

Start or continue a design project. Manages the full workflow from brief to visual direction — analyzes requirements, gathers inspiration, creates wireframes, and applies styling. Entry point for the design pipeline. Triggers on "start design project", "new…

Gather, organize, and tag design references from real apps, web search, and designer-provided screenshots. Connects references to the atomic decomposition from Analyze. Triggers on 'find inspiration', 'gather references', 'build mood board', 'check this app'.

First-time setup for edu-vid-gen plugin. Installs prerequisites (ffmpeg, imagemagick, python packages, gcloud), configures API keys and Google Cloud Vertex AI, sets output directory, and verifies everything works. Run this once on a new machine before using…

Generate multiple educational videos from a single batch manifest (batch.json). Phase-batched execution with 4 review gates, cost tracking, and resume support. Uses all existing edu-vid-gen scripts — no new generation tools.

Regenerate or reuse a character from a previous edu-video project. Pass a character's reference sheet and recreation prompt to produce the character in a new pose, scene, or expression. Use when the user says "recreate character", "use Droppy in a new scene",…

Generate an educational explainer video for a given topic and school class. Audio-first pipeline with VO-driven clip planning, Gemini-powered validation after every clip, MoviePy compositor for transitions, ambient audio layers (--audio-layers), and…

Extend an image in any direction to create space for text overlays. Adds a flat color, gradient, or blurred extension suitable for legible text placement. Use when the user says "extend image for text", "add text space", "make room for title", "extend…

Generate character-consistent videos using Veo's video extension chain. Instead of generating separate clips and stitching, this creates one continuous video by extending each clip from the previous one's last frame. Solves character drift (especially for…

VO-synced video compositor — takes existing clips + timeline.json, calculates gaps/overflow, lets user choose transitions (crossfade, slow zoom, Veo TC), and produces a perfectly synced final video with full-vo.mp3 as master clock.