Video & Animation

拷打式复盘 Agent Skill：把视频/音视频稿、PDF、文章、字幕、笔记或主题变成研究先行的互动复盘单，支持错题、周考和开放题 Agent rubric 复核。

Codex skill for building simple MP4 videos from scripts, images, and timelines.

A Codex skill for turning plot summaries into cinematic AI video prompts. It diagnoses story, emotion, structure, shot design, micro-expressions, sound, reference image prompts, and continuation logic, then outputs copy-ready prompts for short-form AI video generation.

Build AI-driven 3D avatar animation from natural language commands for real-time WebGL interaction and training flows

One source → every channel. Agent-native content repurposing: turn a video/article into an X article, a week of posts, an SEO blog post, and a video script.

Regenerate and publish reference docs for the official Unreal Engine ModelContextProtocol MCP server by probing a live editor — one skill per Epic release.

A multi-agent decision council Skill for fuzzy decisions, with six-role deliberation, traceability, safety gates, and evaluation assets.

Claude Code skill for generating animated hero GIFs for GitHub repos

An open Agent Skill that turns one poster into a 15-second vertical promotional video workflow and Seedance-style prompt.

Data Journalist Agent: Transforming Data into Verifiable Multimodal Story

Claude/Codex skill pack built downstream of yt-dlp for transcripts, WhisperX fallback, and frame-based video watching.

用 Google Gemini API 的 TTS 模型把腳本配音成音檔，並同時輸出時間軸對齊的 SRT 字幕的 OpenClaw / Claude skill — Gemini text-to-speech with time-aligned SRT subtitles.

Agent Skill-compatible LLM harness for Codex and Claude Code creators: validated ComfyUI AI image workflows for illustration, comics, animation, evals, provenance.

中文优先的语义动漫推荐 Codex Skill 和实验性 TypeScript CLI，优先参考 Bangumi/AniList 等高质量数据源。

Portable, agent-driven course on AI systems engineering. Foundations-first or builder-first (10 hands-on loops, ~70-120h on Gemini's free tier). Runs in Claude Code, Codex CLI, Copilot CLI, Cursor, Aider — Windows/macOS/Linux.

Claude skills and projects

A validated, Baseline-aware modern CSS skill for AI coding agents (Claude Code, Codex, Cursor, Pi, OpenCode, Kiro).

Generate HeyGen presenter videos via the v3 Video Agent pipeline — handles Frame Check (aspect ratio correction), prompt engineering, avatar resolution, and voice selection. Required for any HeyGen video generation. Replaces deprecated endpoints with v3. Use when: (1) generating any HeyGen video (via API or otherwise), (2) sending a personalized video message (outreach, update, announcement, pitch, knowledge), (3) creating a HeyGen presenter-led explainer, tutorial, or product demo with a human face, (4) "make a video of me saying...", "send a video to my leads", "record an update for my team", "create a video pitch", "make a loom-style message", "I want to appear in this video", "generate a HeyGen video", "make a talking head video". Accepts avatar_id from heygen-avatar for identity-first HeyGen videos, or uses a stock presenter. Returns video share URL + HeyGen session URL for iteration. Chain signal: when the user wants to create/design an avatar AND make a video in the same request, run heygen-avatar firs

After Effects animation rendering for web and React applications. Use this skill when implementing Lottie animations, JSON vector animations, interactive animated icons, micro-interactions, or loading animations. Triggers on tasks involving Lottie, lottie-web, lottie-react, dotLottie, After Effects JSON export, bodymovin, animated SVG alternatives, or designer-created animations. Complements GSAP ScrollTrigger and Framer Motion for scroll-driven and interactive animations.

Remotion renderer for json-render that turns JSON timeline specs into videos. Use when working with @json-render/remotion, building video compositions from JSON, creating video catalogs, or rendering AI-generated video timelines.

Use when the user asks to generate, edit, extend, poll, list, download, or delete Sora videos, create reusable non-human Sora character references, or run local multi-video queues via the bundled CLI (`scripts/sora.py`); includes requests like: (i) generate AI video, (ii) edit this Sora clip, (iii) extend this video, (iv) create a character reference, (v) download video/thumbnail/spritesheet, and (vi) Sora batch planning; requires `OPENAI_API_KEY` and Sora API access.

Blender to web export workflows for 3D models and animations. Use this skill when exporting Blender models to glTF for web, optimizing 3D assets for Three.js or Babylon.js, batch processing models with Python scripts, automating Blender workflows, or creating web-ready 3D pipelines. Triggers on tasks involving Blender glTF export, bpy scripting, 3D asset optimization, model compression, texture baking, or Blender automation. Exports models for threejs-webgl, react-three-fiber, and babylonjs-engine skills.

Modern web design trends, principles, and implementation patterns for 2024-2025. Use this skill when designing websites, creating interactive experiences, implementing design systems, ensuring accessibility, or building performance-first interfaces. Triggers on tasks involving modern design trends, micro-interactions, scrollytelling, bold minimalism, cursor UX, glassmorphism, accessibility compliance, performance optimization, or design system architecture. References animation skills (GSAP, Framer Motion, React Spring), 3D skills (Three.js, R3F, Babylon.js), and component libraries for implementation guidance.

Create explainer videos with narration and AI-generated visuals. Triggers on: "解说视频", "explainer video", "explain this as a video", "tutorial video", "introduce X (video)", "解释一下XX（视频形式）".