LobsterAI is an open-source desktop AI agent that operates files, commands, browsers, documents, spreadsheets, slides, messaging channels, and scheduled jobs in a user's working environment. It supports office work, research, and custom multi-agent workflows, while catalogue add-ons extend the agent with additional skills and workflows.
Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/netease-youdao/lobsterai/seedream)<a href="https://agentmods.dev/skills/netease-youdao/lobsterai/seedream"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/seedream/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/netease-youdao/lobsterai/seedream"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/seedream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.04094 |
| Opus 5 | $0.00028 | $0.02047 |
| Sonnet 5 | $0.00011 | $0.00819 |
| Haiku 4.5 | $0.00006 | $0.00409 |
Grade A, and why
seedream scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- seedream — 91% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seedream 图片生成
使用火山引擎 Seedream 模型生成高质量 AI 图片，支持文本生成图片（T2I）、图片编辑（I2I）、多图融合、组图生成、联网搜索等多种创作模式。
✨ Node.js 版本：此脚本使用 Node.js 实现，无需 Python 环境。通过入口脚本自动检测 Node.js 运行时（优先使用系统 node，回退到 LobsterAI 内置运行时），Windows 和 Mac 用户都可以开箱即用。
配置
- Base URL:
https://ark.cn-beijing.volces.com/api/v3 - API Key: 从环境变量
ARK_API_KEY读取 - 认证方式:
Authorization: Bearer {API_KEY} - SDK: 兼容火山方舟 Python SDK
快速开始
第一步：设置 API Key
# macOS / Linux - 当前终端临时生效（立即使用）
export ARK_API_KEY="你的API密钥"
# Windows PowerShell - 当前会话临时生效
$env:ARK_API_KEY="你的API密钥"
# 验证设置成功（macOS/Linux）
echo $ARK_API_KEY
# 验证设置成功（Windows）
echo $env:ARK_API_KEY
第二步：生成你的第一张图片
bash "$SKILLS_ROOT/seedream/scripts/generate-image.sh" \
--prompt "一只可爱的橘色小猫"
如何配置 API Key
方式一：通过环境变量配置（推荐）
在终端中设置环境变量：
# macOS/Linux
export ARK_API_KEY="你的API密钥"
# 或者添加到 ~/.zshrc 或 ~/.bashrc 以永久生效
echo 'export ARK_API_KEY="你的API密钥"' >> ~/.zshrc
source ~/.zshrc
# Windows PowerShell
$env:ARK_API_KEY="你的API密钥"
# 或者设置系统环境变量以永久生效
[System.Environment]::SetEnvironmentVariable('ARK_API_KEY', '你的API密钥', 'User')
方式二：通过 LobsterAI 启动时注入
LobsterAI 会自动读取系统环境变量，确保在启动 LobsterAI 前已设置 ARK_API_KEY。
如何获取 API Key：
- 访问火山方舟控制台：https://console.volcengine.com/ark/region:ark+cn-beijing/apikey
- 创建新的 API Key
- 复制密钥并设置为环境变量
前置检查
无需安装任何依赖！ 该脚本已兼容 Node.js 内置模块。
LobsterAI 已包含 Node.js 运行时，所有必要的依赖已被自动打包。Windows 和 Mac 用户无需额外配置。
工作流程
Seedream 图片生成采用同步模式，流程简单高效：
- 提交请求 - 调用 API 提交图片生成请求
- 等待生成 - API 直接处理并生成图片（通常 30-60 秒）
- 下载图片 - 从返回的 URL 下载生成的图片文件
相比异步模式，同步模式更简单直接，无需轮询任务状态。
配额和限制
免费额度
所有 Seedream 模型提供免费额度，具体请参见火山方舟控制台。
限流限制
- IPM（每分钟图片数）: 500 张/分钟（Seedream 4.5, 4.0）
- 不同模型的限流不同，请参见官方文档
图片保存时间
⚠️ 重要提醒：
- 任务数据（包括图片URL）仅保留 24 小时
- 超时后会被自动清除
- 务必及时下载保存生成的图片
使用示例
路径说明：下面的示例使用 $SKILLS_ROOT 环境变量来引用脚本路径。LobsterAI 会自动设置这个变量，指向实际的 SKILLs 目录位置，因此无需手动修改路径。
1. 文本生成图片（T2I）
根据文字描述生成图片，适合创意激发和概念设计。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 449 lines · 56 tokens per session scan A 7c6d9c2caaaa
seedream is a skill published in the GitHub repository netease-youdao/LobsterAI (6,007 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 4,094 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hive.image-generation
Required before calling imagegenerate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2…
qwen-image
Generate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text descriptions.
screenshot-sender
Capture screenshots on macOS and optionally send them to Feishu chats. Use when the user asks to take a screenshot, capture the screen, send a screenshot, or needs visual evidence of something on screen. Supports full screen, window, and region capture modes.
video-subtitles
Generate SRT subtitles from video/audio with translation support. Transcribes Chinese (FunASR/Whisper), English (Whisper), Hebrew (ivrit.ai), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or hardcoded subtitles.
chart-image
A chart-making tool that turns data into PNG images. It supports line, bar, pie, scatter, area, heatmap, box, and radar charts in three visual styles.
voice
A voice tool that converts text to spoken audio and audio recordings to text. It uses edge-tts for speech output and either the Whisper API or local whisper.cpp for transcription.