Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.
Repository Index
47,133 repositories indexed
1–19 of 19 · Most stars
TranslatedA toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo.
244 pixel art effects, every one a small piece of code. Plus a Claude Code skill to make your own.
- agent-skills
- animation
- canvas
- claude-code-plugin
Motion films that never cut to the next slide: every beat grows out of the one before, one continuous camera, continuity measured by an oracle. Product launch films and feature demos, made with a coding agent.
- agent-skill
- animation
- canvas
- claude-skill
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
- agent-skills
- ai-agents
- ai-video
- claude-code
An infinite zoomable canvas for coding. Editor, terminal, and browser panels in a spatial workspace.
Build a system, load it until it breaks, and watch why. A system design simulator for learning distributed systems.
The open-source studio for making games with AI. Your own one-person game studio. Everything you need to make games with AI, in one app. Game canvas. Bring your own key.
- ai-coding
- ai-coding-agent
- ai-game-design
- ai-game-dev
Procedural animation in any style for Claude Code: short single-file canvas videos with story, look and storyboard check-ins. 7 built-in styles or one matched from your references, your own music (beat-mapped), real product screenshots, every format from one piece.
- animation
- canvas
- claude-code
- claude-code-plugin
Art and animation, written as code. Illustrations, loops, interactive web art, launch-videos and scored films in dozens of styles, identical on every render.
- agent-skills
- animation
- canvas
- claude-code
TranslatedUse Claude Opus 5.5 to write code and make videos: first it gives three options with previews, and after you confirm, it renders the final video frame by frame | Canvas / WebGL / Three.js / Remotion / HyperFrames | Claude Code Skill
A pure-code beat-synced showcase-video Agent Skill: HTML/Canvas/SVG/Three.js frame-by-frame + Python numpy/scipy score + FFmpeg. No generative models.
A Claude skill for directing, building and verifying code-rendered videos (HTML/Canvas → MP4): principles, gated workflow, QA scripts and evals.
TranslatedDeterministic HTML-to-MP4 renderer: seek to t, screenshot, encode. No framework, no build step, no GPU. Make videos frame by frame with code: HTML / Canvas animation → MP4 / GIF / transparent layer
- agent-skill
- animation
- canvas
- ffmpeg
TranslatedA DeepSeek Harness skill that turns Chinese copy, art-style prompts, and sound into coherent code animations (Remotion / Canvas / HTML). Includes search of a 341-style art library, semantic storyboarding, shot transitions, character performance, four music and sound-effect plans, and review and revision.
- animation
- chinese
- code-animation
- deepseek-harness
Codex plugin for OpenPencil — an interactive Rust/WASM canvas for AI-assisted UI design. Create editable .op files from prompts, refine selected elements, generate image assets, and install with one prompt on macOS, Windows, and Linux.
A local-first infinite canvas for UI design — one your agent can edit. Desktop app, MCP-native.
Read-only MCP server that connects Claude, ChatGPT and other AI assistants to Canvas LMS.
TranslatedWant to eat McDonald's while managing your body shape? This expert helps you put together a McDonald's (麦麦) meal combo based on your daily calorie expenditure. Based on SP matrix theory, it connects nutrition-based selection with the ordering loop through McDonald's official MCP Server (35 official tools · 14 REST endpoints · zero third-party frontend dependencies).