SkillFoxx

WorkRally skill

A Tencent skill giving an agent the WorkRally CLI: image, video and audio generation, projects, series, shots, assets and canvas.

  • 194 ★ on the repository
  • Last commit
Skill

Extended access

Why this level

  • The tool uses the platform API key and sends requests, files and prompts to the WorkRally cloud.
  • Generation spends account quota and deleting project objects moves them to a recycle bin.
All reasons and checks

tencent/workrallyAuthor:tencent

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/workrally

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The tool uses the platform API key and sends requests, files and prompts to the WorkRally cloud.
  • Generation spends account quota and deleting project objects moves them to a recycle bin.

This is third-party code. Review the repository files before installing.

What it does

WorkRally is a Chinese platform for making animated comics and short dramas with AI. The skill describes the `workrally` command-line tool for an agent, covering more than 30 platform capabilities: projects, series, shots, image and video generation, audio, an infinite canvas, an asset library and an enterprise knowledge base. Video has four modes: from text, from first and last frames, from a reference subject and video editing. A low-cost draft can later be upgraded to a finished clip. Agents sign in with an API key, people through the browser. `workrally shotlist` queues batch generation by shot, and `get-result --watch` follows progress.

Who it is for. Creators of animated series and short dramas who build projects on WorkRally and want an agent to run series, shots and generation from the terminal.

Good fit when

  • Batch image generation for all shots of a series from a list of prompts.
  • Low-cost video drafts are checked before a full render starts.
  • Voice-over files are uploaded, bound to shots and regenerated.
  • A project's enterprise knowledge base cards need searching and updating.
  • Shot order in a series changes with `shotlist sort`.

Not a fit when

  • You have no WorkRally account or API key; the tool does not work without them.
  • You need a standalone local video generator with no external platform.
  • Deleted objects must be restored from the tool itself; this is possible only in the web interface.

Example request

Create a series in the project, load the shot prompt list and queue image generation for all shots.

Limitations

The tool needs a WorkRally account and an API key from the platform's open API page. An agent signs in with `workrally auth login --token <key>`, while the interactive browser login is meant for a person. Generation runs in the platform cloud and spends its quota. The skill and docs are written in Chinese. Deleting projects, series and shots is soft: objects go to a recycle bin and are restored in the web interface. The skill is published by the Tencent organization, and the version in SKILL.md can differ from the npm package version.

How to disable. Delete the skill folder from the agent's skills directory and run `npm uninstall -g workrally`. Revoke the API key on the platform site and delete `~/.workrally/config.json`.

FAQ

How do I install the WorkRally CLI?

Run `npm install -g workrally`, then `workrally auth login --token <key>` and check `workrally auth status`. The key comes from the platform's open API page.

How does an agent sign in?

With an API key: the `--token` flag or the `WORKRALLY_API_KEY` variable. The environment variable takes priority over the config file, and browser login is for people only.

How do I see a generation result?

`generate-image`, `generate-video` and `generate-audio` only queue the task. `workrally shotlist get-result --story-id <id> --type image` with `--watch` reads the result.

Which video modes exist?

Four: from text, from first and last frames, from a reference subject and editing an existing video. The mode is set with `set-model`.

Where is configuration stored?

In `~/.workrally/config.json` or in the directory from the `WORKRALLY_CONFIG_DIR` variable.

Discussion

No questions or reviews yet.

Skills

A skill that turns narration text into a 20-second chunky-pixel explainer at 1920×1080 with voice-over and an editable project.

SkillExtended access84

A skill that turns a character image into an animated sticker pack and exports it for WeChat, Telegram, LINE and Discord.

SkillExtended access62

A skill that turns a script into a finished video with voice-over, subtitles, a cover and a publish text, frames drawn by code.

SkillBroad access85

A skill for Cursor, Claude Code and Codex: from a product name or URL it builds a 4K promo with music, voice-over and checks

SkillExtended access469

Skills and a CLI for video editing, motion graphics, 3D scenes and design, where the agent works in one local project.

SkillExtended access363

A skill that finds B-roll and literal sources for lines, shows them in a Storyboard and hands over clips after you approve

SkillBroad access242

README in short

The repository holds only the skill definition: `SKILL.md` and six reference files an agent loads as needed. They cover generation, canvas, asset upload, the knowledge base and batch shot work. Links to third-party skill stores are at the top of the file.

README badge

Original SKILL.md

---
name: workrally
slug: workrally
displayName: WorkRally
display_name: WorkRally
display_name_en: WorkRally
description: WorkRally CLI (workrally) — 面向 AI Agent 的 AIGC 漫剧视频创作全流程工具集。支持 AI 生图、AI 生视频（含样片 draft）、视频提示词优化、画布生音频/音乐、混元 3D 模型生成、AI 生音频、项目/剧集/场次/分镜的完整 CRUD、资产库、媒资管理、企业知识库检索与写入、无限画布、文件上传下载等。Use when user asks to generate images, generate videos, generate audio, generate music, generate 3d, optimize video prompts, manage projects, series, shots, search or write a knowledge base, upload files, download assets, manage materials, or interact with WorkRally platform via command line.
description_zh: 面向 AI Agent 的 AIGC 漫剧视频创作全流程工具集，支持 AI 生图/生视频/生音频、项目剧集场次管理、资产库、企业知识库与无限画布。
description_en: End-to-end AIGC comic-drama creation toolkit for AI Agents—image/video/audio generation, project/series/shot management, asset library, enterprise knowledge base, and infinite canvas.
tags: [AIGC, CLI, 漫剧, 生图, 生视频, 生音频, 项目, 剧集, 场次, 画布, 资产库, 知识库]
version: 2.12.0
license: MIT-0
author: WorkRally Team
homepage: https://workrally.qq.com
user-invocable: true
metadata: {"openclaw":{"emoji":"🎬","requires":{"bins":["workrally"],"env":["WORKRALLY_API_KEY","WORKRALLY_ENDPOINT","WORKRALLY_CONFIG_DIR","WORKRALLY_NO_UPDATE_CHECK"]},"primaryEnv":"WORKRALLY_API_KEY","credentials":{"storage":"~/.workrally/config.json","configDirEnv":"WORKRALLY_CONFIG_DIR","description":"workrally auth login 写入的登录态：API Key，或 OAuth access/refresh token，以及 endpoint。非持久化容器中可通过 WORKRALLY_CONFIG_DIR 环境变量指定配置目录"},"install":[{"id":"npm","kind":"node","package":"workrally","bins":["workrally"],"label":"Install WorkRally CLI (npm)"}],"category":"AIGC","tags":["workrally","aigc","cli","video-generation","image-generation","ai-tools","story","shot","series"]}}
---

# WorkRally CLI (workrally)

面向 AI Agent 的 AIGC 漫剧视频创作全流程命令行工具，封装 WorkRally 平台 30+ 核心能力，支持项目/剧集/场次的完整 CRUD、AI 生图/生视频、画布、资产库、媒资管理、文件上传等。

## 安装 & 配置

```bash
npm install -g workrally

# 配置登录。Agent / CI 只用 API Key，不要自己实现 OAuth，也不要请求 127.0.0.1 回调。
workrally auth login --token <YOUR_API_KEY>   # Agent / CI
export WORKRALLY_API_KEY=<YOUR_API_KEY>       # 环境变量优先于配置文件
workrally auth login                          # 仅人在本机终端使用，CLI 自己打开浏览器
# ↑ auth login 自动将 Token 写入配置文件：
#   若 WORKRALLY_CONFIG_DIR 已设置 → $WORKRALLY_CONFIG_DIR/config.json
#   否则 → ~/.workrally/config.json

workrally auth status                         # 验证登录状态
```

API Key 申请：[龙虾配置](https://workrally.qq.com/open-api)

Report a problem