Claude Skills by tensorslab

> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking. **Goal:** Create a new `ali-video` skill that mirrors the tl-video skill's front-end UX (prompt enhancement, progress tracking, heartbeat messages, local downloads) but replaces the backend with Aliyun Bailian DashScope API using HappyHorse models. **Architecture:** Follow ...

Generate videos using Aliyun Bailian's HappyHorse AI video generation models via DashScope API. Supports text-to-video (T2V), image-to-video (I2V with first frame), and reference-to-video (R2V with multiple reference images). Supports batch generation with concurrent task execution. Requires DASHSCOPE_API_KEY. Video generation typically takes 1-5 minutes. MUST use this skill whenever generating videos with Aliyun/HappyHorse/DashScope, including batch video generation, animating images, or cre...

对图像进行编辑操作。支持四种功能：变宽高比（aspect）、擦除对象（erase）、去除背景（rmbg）、通用编辑（edit）。基于 tl-image 的 quickedit 模型实现快速图像编辑。当用户需要修改图片宽高比、移除图片中的对象、去除背景或进行自定义编辑时使用此技能。

Generate and edit images using TensorsLab's AI models. Supports text-to-image, image-to-image generation, plus advanced editing: avatar generation, watermark removal, object erasure, face replacement, and general image editing. Features automatic prompt enhancement, progress tracking, and local file saving. Requires browser-based authorization before first use.

Generate videos using TensorsLab's AI video generation models. Supports text-to-video and image-to-video generation with automatic prompt enhancement, progress tracking, and local file saving. Use for generating videos from text descriptions, animating static images, creating cinematic content, and various aspect ratios. Requires browser-based authorization before first use. Video generation takes several minutes.