skills.rest
wecode-ai
wecode-aiOFFICIAL
Explore all skills by this author →
GitHub

wegent-video-generation

Generates videos from text prompts with image, video, and audio reference materials via an MCP tool.

772|135|Updated Jan 10, 2026
Search Tags:#mcp#creative#video generation#text-to-video#reference materials#async polling
One-click install
npx skills add https://github.com/wecode-ai/Wegent --skill wegent-video-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wegent-video-generation
Source: https://github.com/wecode-ai/Wegent/tree/main/backend/init_data/skills/wegent-video-generation
Command: npx skills add https://github.com/wecode-ai/Wegent --skill wegent-video-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating video content from written ideas normally requires dedicated editing software and manual production work. This Skill lets users request AI-generated videos directly in chat, supplying text prompts plus optional reference materials, while the system handles asynchronous rendering in the background.

Core Features & Use Cases

  • Prompt-Based Video Generation: Calls the generate_video tool with a complete scene, motion, camera, and style description to produce a video.
  • Reference Material Support: Accepts user-provided image, video, and audio attachments (by attachment ID or HTTP URL) as inputs for the selected video model.
  • Asynchronous Polling Workflow: A polling response means the request was accepted and the video block is created and updated automatically, with no repeated tool calls needed.
  • Use Case: A user attaches a product photo and asks for a 10-second promotional clip with a slow camera pan; the Skill submits the request and the finished video appears in the conversation once rendering completes.

Quick Start

Ask the assistant to generate a video describing your desired scene, motion, camera angle, and style, optionally attaching reference images or clips.

Frequently Asked Questions about wegent-video-generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a video from a text prompt?▼

Describe the complete scene, motion, camera movement, and style in your request, and the generate_video tool is called with that prompt. The system accepts the request and creates the video block asynchronously.

Can I use reference images or audio for video generation?▼

Yes, the selected video model supports text, image, video, and audio reference materials. Pass them as attachment IDs or HTTP URLs, and only include materials the user has provided or selected.

What does a polling response mean after requesting a video?▼

A polling response means the video request was accepted and is being processed asynchronously. The system creates and updates the video block on its own, so you should not call the tool again or create a duplicate card.

Why did my video generation request return an error?▼

An error response indicates invalid parameters, such as unsupported reference materials or malformed inputs. Explain the error once, correct the invalid parameters, and only then retry the request.

Can I pass local sandbox file paths as video references?▼

No, sandbox paths are not accepted as reference materials. You must provide attachment IDs or HTTP URLs for any image, video, or audio inputs.

Related Skills

Explore More Design & Creative Skills→
CDO-07-NewCDO-07-New

fal-ai-media

Generate images, videos, and audio via fal.ai from text prompts.

Official
Intermediate
adiytharpansaadiytharpansa

social-media-poster

Automate social media publishing and scheduling across multiple platforms via APIs.

Community
Intermediate
tharunramagiritharunramagiri

tarunai-connect-videocaptioner

Transcribe video speech and generate translated subtitles for media files.

Community
Advanced
palmier-iopalmier-io
41

ugc-editing

Edit UGC footage into tight 9:16 vertical posts with captions.

Official
Advanced