cn-video-gen国产AI视频生成技能。支持通义万相(Wan2.6文生视频/图生视频)和可灵(Kling V2)。适合创意视频制作、图生视频、动态内容生成等场景。当用户要求生成视频、将图片生成动态视频、或基于描述生成视频片段时触发。
Install via ClawdBot CLI:
clawdbot install dadaniya99/cn-video-genGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Hardcoded API key or token pattern found in skill definition
sk-Um9dYCP0y...Calls external URL not in known-safe list
https://dashscope.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthAudited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
This skill enables users to generate dynamic video content from text prompts or images, ideal for creating promotional videos, social media clips, or artistic projects. It supports platforms like Tongyi Wanxiang and Kling V2, offering flexibility in resolution and duration for cost-effective prototyping and final output.
Users can upload static images to generate animated videos, enhancing visual storytelling for presentations, educational content, or product showcases. The process requires uploading images to a public URL first, with tips for optimizing image quality and motion cues to improve results.
Designed for advanced users like storyboard artists, this scenario allows creating videos with multiple camera shots (e.g., push-ins, tracking shots) using specialized parameters. It leverages prompt engineering for detailed motion descriptions to produce cinematic sequences for film or gaming content.
Users can test video concepts with shorter durations (e.g., 5 seconds) and lower resolutions (720P) to validate prompts before investing in higher-quality outputs. Failed tasks are not charged, encouraging experimentation in iterative design processes for startups or small businesses.
Monetize by offering access to the video generation APIs (Tongyi Wanxiang and Kling V2) through subscription plans or pay-per-use pricing. Revenue can be generated based on video duration and resolution, with tiered pricing for different user segments like freelancers or enterprises.
Integrate this skill into creative agencies to provide video production services, charging clients per project or on a retainer basis. Upsell options include multi-shot narratives and high-resolution outputs, leveraging the skill's support for detailed prompt engineering and cost control.
License the skill to third-party platforms (e.g., social media tools, e-learning systems) for embedding video generation capabilities. Revenue comes from licensing fees or revenue-sharing agreements, targeting industries like marketing and education that require dynamic content creation.
💬 Integration Tip
Ensure API keys (e.g., DASHSCOPE_API_KEY) are securely configured and use the provided scripts for image upload and video generation to streamline workflow.
Scored Apr 18, 2026
Extract frames or short clips from videos using ffmpeg.
Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.
Generate SRT subtitles from video/audio with translation support. Transcribes Hebrew (ivrit.ai) and English (whisper), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or hardcoded subtitles for WhatsApp/social media.
AI视频脚本生成器。根据用户输入的主题/关键词,生成完整的视频脚本,包含分镜描述、画面提示词、配音文案。适用于短视频创作者、AI视频制作者、内容营销人员。触发词:视频脚本、分镜、AI视频、短视频文案、视频策划。
Generate document, outline, and image-text AI notes by providing a video URL, using Baidu's video analysis and note extraction APIs.
Process video and audio using FFmpeg CLI for transcoding, cutting, merging, audio extraction, thumbnails, GIFs, speed, filters, subtitles, and watermarks.