Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
frameproof
SkillsАгент смотрит видео без слепых зон и доказывает тайм-кодом, что видел. Офлайн, без API-ключей.
git clone https://github.com/edvardgrishin27/frameproof.git -
shaderera
SkillsThe programmable era of ads. Video made in code for experts and their AI agents: a film is render(t). Determinism checks, H.264/ProRes rendering, review and per-placement delivery, with an MCP server and agent skills.
git clone https://github.com/shaderera/shaderera.git -
reborn-forge
SkillsMeta-prompt generator for AI video: give it a niche and a reference YouTube URL and it returns a reusable 33-section master prompt (variation engine, stages, audio, lighting, scene JSON, anti-fail rules).
git clone https://github.com/waseemnasir2k26/reborn-forge.git -
Sonicmatch
MCP serversAnalyze video mood and pace, then recommend license-safe BGM with a mix spec.
https://github.com/js713-lab/sonic-match-mcp/releases/download/v0.2.0/sonicmatch-mcp-0.2.0.mcpb -
clipper-skill
SkillsClaude Code skill that turns podcasts, interviews and X broadcasts into post-ready short clips. Local MLX Whisper transcription, ffmpeg cuts on word boundaries, QA-checked, Google Drive + Doc hand-off. Open-source Opus Clip alternative.
git clone https://github.com/RealAdii/clipper-skill.git -
CyberVerse
Agents & frameworksSelf hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.
git clone https://github.com/Lynpoint/CyberVerse.git -
claude-motion-design
SkillsA Claude Code skill to make motion design videos in pure code: HTML + Playwright + ffmpeg. No After Effects, no Remotion license.
git clone https://github.com/howseen-ai/claude-motion-design.git -
claude-show-your-work
Agents & frameworksClaude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.
git clone https://github.com/iamumeransari/claude-show-your-work.git -
ai-megalist
PromptsCurated index of 200+ AI tools, one writeup per tool with hands-on takes. Covers coding, design, research, video, voice, agents, music, local LLMs. Compare alternatives, see real pricing, find the right tool for the job.
git clone https://github.com/IrtezaAsadRizvi/ai-megalist.git -
d3-lite
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-lite -
gufo
AI repositoriesThe open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and Windows.
git clone https://github.com/gufo-org/gufo.git -
beatra-skills
SkillsAgent Skills for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: AI image generation, text to speech, talking head video, AI music, and video generation skills that render on Beatra. 图片生成 · 配音 · 数字人 · AI 作曲
git clone https://github.com/beatra-ai/beatra-skills.git -
img-prompt
PromptsClick tags in your language, get the English prompt Midjourney, FLUX, GPT-Image & Veo actually expect — 한국어 العربية Русский हिन्दी ไทย | 英文提示词不用自己写:点中文标签,自动拼好模型认的那一套
git clone https://github.com/rockbenben/img-prompt.git -
legible-film
SkillsVideo editing for coding agents: cut interviews, podcasts and tutorials from their transcripts, make launch films, caption and mix, and check the delivered file before it ships.
git clone https://github.com/JamesDimachkie/legible-film.git -
LobsterAI
AI repositoriesOpen-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your phone via WeChat, Feishu, DingTalk & Telegram.
git clone https://github.com/netease-youdao/LobsterAI.git -
ultrademo
SkillsMoved to github.com/ultrademo-hq/ultrademo. This is the original Ultrademo skill; it still works but is no longer updated.
git clone https://github.com/new-xp/ultrademo.git -
yamlreel
SkillsWrite a short YAML file, get a finished video: animated diagrams, typed code, original music and an optional voiceover in your own voice. Vertical + landscape cuts, thumbnail and post copy, all rendered locally.
git clone https://github.com/nsijwali/yamlreel.git -
WeVisCut
Modelsany to any model by tencent · transformers
tencent/WeVisCut -
visual-skills
PromptsAI film director skills for agents: cinematic dramaturgy (Murch, blocking, montage) + exact prompt syntax for Seedance 2.5, Kling 3.0 Turbo/Omni, Veo 3.1, Nano Banana 2, GPT Image 2.5.
git clone https://github.com/smixs/visual-skills.git -
ImgEdify: AI Image Editor, AI Image Generator, AI Video Generator, AI Video Editor & AI Video Maker
MCP serversGenerate and edit images, create videos, quote credit costs, and retrieve private results.
-
skills
SkillsSkills I use with coding agents for interface, motion, sound and launch film work.
git clone https://github.com/HKTITAN/skills.git -
motionvideo.xyz
SkillsA directory of AI-powered motion videos, prompts, and skills that teach coding agents motion design/graphics
git clone https://github.com/motionvideohq/motionvideo.xyz.git -
kinetic-typography-skills
SkillsKinetic typography skills for AI coding agents — turn text into beat-synced, animated type for social, titles, and lyric videos.
git clone https://github.com/iart-ai/kinetic-typography-skills.git -
map-animation-skills
SkillsAnimated map skills for AI coding agents — draw routes, zoom-to-location, and data-driven map animations rendered to video.
git clone https://github.com/iart-ai/map-animation-skills.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.