メニュー
Generate videos using Tencent Cloud VOD AIGC models (Kling, Vidu, Hailuo, etc.). Updated with full API support.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.
Manages project knowledge using ByteRover context tree. Provides two operations: query (retrieve knowledge) and curate (store knowledge). Invoke when user requests information lookup, pattern discovery, or knowledge persistence. Developed by ByteRover Inc. (https://byterover.dev/)
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Perform web searches using DuckDuckGo. Use when web search is needed and no API key is available or Brave Search is not preferred.
Essential Docker commands and workflows for container management, image operations, and debugging.
| name | video-gen |
| description | Generate videos using Tencent Cloud VOD AIGC models (Kling, Vidu, Hailuo, etc.). Updated with full API support. |
This skill generates high-quality AI videos using Tencent Cloud VOD AIGC API. It supports Text-to-Video (T2V) and Image-to-Video (I2V) across multiple models.
node skills/video-gen/index.js "<Prompt>" [options]
| Flag | Description | Default |
|---|---|---|
--model <name> | Model name (Kling, Hailuo, Vidu, etc.) | Kling |
--model-version <ver> | Model version (e.g. 2.1, 2.5) | 2.5 |
--image <url> | Reference image URL for I2V | None |
--last-frame <url> | Last frame image URL (Kling 2.1, Vidu, GV) | None |
--resolution <res> | 720P, 1080P, 2K, 4K | 1080P |
--ratio <ratio> | 16:9, 9:16, 1:1 | 16:9 |
--enhance | Enable prompt enhancement | Disabled |
--chat-id <id> | Feishu chat ID for progress cards | None |
1. Basic Text-to-Video (Kling 2.5)
node skills/video-gen/index.js "A cyberpunk city in rain" --model Kling --model-version 2.5 --chat-id "oc_..."
2. Image-to-Video (Hailuo 2.3)
node skills/video-gen/index.js "Make the cat jump" --model Hailuo --model-version 2.3 --image "https://example.com/cat.jpg"
3. Start & End Frame (Kling 2.1)
node skills/video-gen/index.js "Morph from day to night" --model Kling --model-version 2.1 --image "https://.../day.jpg" --last-frame "https://.../night.jpg"
Requires .env variables:
VITE_VOD_SECRET_IDVITE_VOD_SECRET_KEYVITE_VOD_SUB_APP_ID