Video & Animation

A local-first, privacy-aware coding agent for the terminal.

Turn talks, books and interviews into a method your agent can actually follow. Finds the decisions and the criteria behind them instead of restating the content. RU and EN.

公众号排版发布 Skill：四路语义配图、2.35:1 封面、可复制 HTML 与草稿箱发布

Turn a YouTube video or a web article into didactic study notes, rendered as a self-contained HTML page. Agent skill for Claude Code, Codex, Cursor, OpenCode and Gemini.

100+ curated Seedance 2.5 prompts with real video previews, plus an installable Agent Skill that optimizes prompts, creates storyboards, and generates videos via Seedance models.

Create high-fidelity Codex companions from 2+ photos with local open-weight neural editing and no OpenAI API key.

Open-source AI CLI and local MCP server connecting 25 clients—Claude Code, Cursor, Codex, ChatGPT, Hermes, and OpenClaw—to 2,000+ models/APIs, with OAuth and rollback.

Codex Skill for creating Chinese long-form articles and directly readable video speaking pieces, with course-series and plain-language new-technology modes.

Codex Skill for diagnosing and improving Chinese content, including topics, titles, long-form drafts, short-video scripts, resonance, and AI-expression signals.

把任意学科或技能主题制作成真正能教会人的视频的 Codex Skill

Codex Skill pipeline for analyzing Final Cut Pro rough cuts and preparing animation workflows

Upload an image and generate an adaptive WebGL particle animation page with a reusable Codex Skill.

codex skill for social media interview video rough cut workflow

Production-ready Codex Skills for generating 2D game maps, sprites, and video-to-sprite animations, with deterministic validation and Unity integration.

Codex skill for localized product demo videos with recording, narration, music, captions, and media verification

Find short videos that already work in your category, prove their traffic, borrow their structure — never their claims — and compile it into prompts an AI video model renders. yt-dlp only, no browser.

LINE 貼圖生成大師 Skill：台灣繁體中文日常用語、職場梗檢查、4x3 網格提示詞與 line-sticker-factory 整合。

Curated animation reference websites and a Codex skill for turning visual ideas into implementation-ready motion specs.

Agent-native deterministic hand-drawn animation video engine powered by SVG, Remotion, FFmpeg, and free Edge TTS.

85 个电商 AI Agent Skills — 商品图 / 带货视频 / 爆款复刻 / POD 印花 / 跨境选品。Agent skills for e-commerce content generation by LinkPix (青虎AI)

Agent Skill: turn data into the right chart — interactive, validated colours, conclusion-style titles. One JSON spec, zero dependencies.

给 AI Agent 的前端设计管线：先写 DESIGN.md 与 MOTION.md，经 job 分发、OpenSpec 与证据门禁再写代码。

Claude Code / Cursor / Codex skill. Redesigns any file from its own content — webpage, PDF, slides, infographic. Offline HTML. No CDN.

MiniMax H3 多模态 LoRA 训练、审计与交付技能：Ref2VA、联合音视频、低显存后端与十步证据链。