Wan 视频生成
About
This skill uses the Wan 2.6 model to generate videos from images or reference videos, enabling tasks like animating pictures and maintaining subject consistency. It offers different model versions for quality or cost efficiency, supporting various resolutions and durations. Developers should invoke it when users request image-to-video, reference-based generation, or mention Wan 2.6.
Quick Install
Claude Code
Recommendednpx skills add openclaw/skills -a claude-code/plugin add https://github.com/openclaw/skillsgit clone https://github.com/openclaw/skills.git ~/.claude/skills/Wan 视频生成Copy and paste this command in Claude Code to install this skill
GitHub Repository
Related Skills
descript
OtherThe Descript skill enables text-based editing of audio and video content through Claude, including transcription and production workflows. It allows developers to manipulate multimedia files by editing their transcribed text directly. Use this skill when you need to automate or streamline audio/video editing tasks within your development pipeline.
clipchamp
OtherThis skill enables Claude to automate video editing using Microsoft Clipchamp, allowing developers to programmatically create, edit, and export videos through templates and stock media. It's ideal for automating video content creation workflows or batch processing. Setup requires Clipchamp credentials configured via environment variables or manual browser authentication.
Sora 2 视频生成
OtherThis skill enables video generation using OpenAI's Sora 2 model through the fal.ai platform. It supports text-to-video, image-to-video, and video remixing at various quality levels (720p/1080p). Developers should use it when users request video creation from prompts, images, or mention Sora/OpenAI video generation.
Seedance 视频生成
OtherThis skill uses Bytedance's Seedance models to generate videos from text, images, or reference images, including support for audio generation and lip-syncing. It's ideal for developers needing to create videos, maintain character consistency, or leverage image-to-video generation. Key capabilities include text-to-video with audio, first-frame image-to-video, and reference-guided video generation for stronger subject consistency.
