Communitygithub.com

ChatCut-Inc/digital-human

Create and manage script- or audio-driven AI avatar videos from an official or saved presenter, an imported portrait, or a representative still prepared from video. Use for digital human, digital twin, virtual persona, talking photo, portrait lip-sync, script editing without reshoot, AI avatar, avatar video, talking avatar, photo avatar, video avatar, AI presenter, virtual presenter, virtual spokesperson, or a person's digital twin, including choosing or creating the avatar and deciding its voice, script, aspect ratio, and output.

What is digital-human?

This skill enables developers and content creators to produce professional AI avatar videos directly from scripts or audio inputs. It supports multiple avatar sources: official or previously saved presenters, imported portraits, or representative stills extracted from video. Users can customize the avatar's voice, script, aspect ratio, and output format. The skill is platform-agnostic and designed for integration into workflows involving digital humans, digital twins, virtual personas, talking photos, or AI presenters. It streamlines content creation by allowing script edits without needing to reshoot, making it ideal for marketing, education, customer service, and personalized video messaging. The underlying technology leverages advanced AI to animate still images or recorded presenters with natural lip-sync and expressive movements, ensuring high-quality and engaging video outputs.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/ChatCut-Inc/agent-plugin/tree/main/claude/skills/digital-human
View original→Browse all skills

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentation

What does digital-human do?

Create and manage script- or audio-driven AI avatar videos from an official or saved presenter, an imported portrait, or a representative still prepared from video. Use for digital human, digital twin, virtual persona, talking photo, portrait lip-sync, script editing without reshoot, AI avatar, avatar video, talking avatar, photo avatar, video avatar, AI presenter, virtual presenter, virtual spokesperson, or a person's digital twin, including choosing or creating the avatar and deciding its voice, script, aspect ratio, and output.

Individual skills in this repo

This repo contains 4 individual skills — each has its own dedicated page.

ChatCut-Inc/agent-plugin

Use when Codex uses the ChatCut plugin (chatcut MCP server) to add, create, hand-author, patch, or place Motion Graphic JSX assets. Covers reference browsing, direct inline JSX authoring, editable properties, asset binding, timeline placement, and composed verification.

ChatCut-Inc/agent-plugin

AI video generation via Seedance, Kling, Gemini Omni, MiniMax H3, and MiniMax H3 Max. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation — or wants to modify / edit / extend an existing generated clip.

ChatCut-Inc/agent-plugin

Use when the user asks for transcription, captions, subtitles, bilingual subtitles, filler-word removal, or pause cleanup in ChatCut.

ChatCut-Inc/video-translation

Translate, dub, and localize speech in an existing video with optional lip sync and translated captions.

Related Skills

steipete/video-frames

Extract frames or short clips from videos using ffmpeg.

community

steipete/summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

community

openclaw/openclaw

Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

community

obra/superpowers

Obra superpowers agent skills.

community

affaan-m/ECC

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...

community

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

community