AI Agent Hub
Back to skills
WorkRally Video Generation icon

WorkRally Video Generation

Design & Media Updated 2026.08.30

Paste the following prompt into your AI chat to install this skill:

Please follow https://skillhub.cn/install/skillhub.md and install @tencent-adm/workrally-video.

About this skill

Problem

When an agent receives a request like “animate this image” or “generate a short clip,” plain chat is not enough. It must call a paid video-generation service while keeping payment, polling, and delivery states consistent.

How It Works

@tencent-adm/workrally-video targets text-to-video and single-image-to-video. The main steps are:
- Recognize whether the intent is to generate a new video, not images, copy, or queries.
- Check for weixinpay extension; if missing, stop with a paid-creation unavailable notice.
- Show the video-generation service and 6.88 CNY per generation before user confirmation.
- Compile the request into executable shot instructions: subject, action, camera motion, lighting/style, time segments, and consistency constraints.
- Call invoke to obtain a payment_code, hand it to WeChat Pay, then poll content with the same payment_id.
- Handle generating, delivered, refunded, failed, and expired statuses to avoid duplicate charges or generation.

Boundaries

The skill returns one 720p, 10-second video by default, and the prompt must stay under 500 characters. It accepts one optional reference image, but not multiple images, reference video, or reference audio. result_url is a WorkRally short link valid for 5 hours, so download it promptly. Image creation should use workrally-image, and successful output must be labeled as AI-generated.

Use Cases

  • A content editor turns one product poster into a 10-second motion preview from a single reference image.
  • A marketing writer generates a 720p short clip from a scene description for social media testing.
  • An agent developer adds paid video output by combining one image and a shot instruction into a generated clip.
  • A designer creates a 10-second logo motion draft by passing a reference image and concise motion constraints.

Best For

  • Content editors who need to turn static posters into short video previews
  • Marketing editors who need 10-second social clips from written scene descriptions
  • Developers building paid text-to-video flows inside AI agents
  • Designers who need logo motion drafts from a reference image and shot instructions