Graph

Terminal-first AI video editing skill driven entirely by plain English prompts. Specializes in automated b-roll integration, voice grading, motion graphics, and Whisper burnt-in captions via HyperFrames, Remotion, and FFmpeg.

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Next-generation visual node canvas for chaining multimodal AI prompts, image generation pipelines, and code execution blocks.

[SIGGRAPH Asia 2026] UniMate: One Unified Model to Animate Diverse Skeletons

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.

Open-source AI-native canvas and agent workspace unifying multi-threaded chat, knowledge retrieval, and document co-creation.

Iterative, graph-based autonomous research agent with reflection, web search verification, and structured report compilation.

Model Context Protocol server for Obsidian vaults, enabling AI assistants to safely search, read, and append local Markdown notes without corrupting frontmatter.

Autonomous coding workflow that generates implementations, runs unit test executions, and self-corrects runtime stack traces.

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds across 162 languages.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

The most powerful and modular diffusion model GUI, API, and backend with a graph/nodes interface. The fastest local inference engine for Stable Diffusion, Flux, and SDXL.

The design language that makes your AI harness better at design. Enforces visual hierarchy, accessible typography, and polished layouts.

The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.

Robust graph-based agent orchestration pattern featuring human-in-the-loop review checkpoints, state persistence, and cyclical reflection loops.

Milvus & Zilliz-powered Claude Desktop and Cursor MCP server for long-term agent memory, doc retrieval, and code knowledge graph querying.