seedream-img-gen

This skill should be used when the user wants to generate images using Seedream, the image generation model from ByteDance on Volcengine platform. Triggers i...

Security Scan

The skill appears to implement Seedream image generation correctly, but its metadata and instructions are inconsistent about required credentials and paths — the package asks the user to set an ARK API key (and the script reads it) even though the registry metadata declares no required environment variables.

Purpose & Capability

The skill's name, description, SKILL.md and code all describe generating images via Volcengine/Seedream, which matches the requested capabilities. However, the registry metadata declares no required environment variables or primary credential, while both SKILL.md and scripts/generate_image.py clearly require an ARK_API_KEY (or VOLCENGINE_API_KEY). This mismatch between declared requirements and actual runtime needs is an incoherence.

Instruction Scope

SKILL.md stays within the image-generation domain: it instructs setting ARK_API_KEY, installing the Volcengine SDK or OpenAI compatibility package, and running the bundled script or using inline code. It references a user-local path (~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py) that does not exactly match the package slug/name in metadata (seedream-img-gen) — a path/name mismatch that can confuse installation and runtime. Instructions do not ask for unrelated files or other credentials and do not appear to exfiltrate data.

Install Mechanism

This is an instruction-only skill with bundled script; there is no install spec that downloads or extracts remote archives. SKILL.md recommends installing Python packages via pip (volcengine SDK or openai), which is reasonable for a Python script. No high-risk download URLs or extraction steps are present.

Credentials

The runtime code and documentation require an API key in ARK_API_KEY (or VOLCENGINE_API_KEY) to call the Volcengine endpoint, but the package metadata declares no required env vars or primary credential. That omission is problematic because users may not realize they must provide a credential, and the metadata does not warn about sensitive data use. Aside from the API key, no other secrets are requested.

Persistence & Privilege

The skill does not request persistent or elevated platform privileges (always is false). It does not modify other skills or system-wide settings. Autonomous invocation is allowed by default but is not combined with other high-risk factors here.

What to consider before installing

This skill otherwise looks like a straightforward Volcengine/Seedream image generator, but there are a few things to check before installing or running it: - The script requires an API key: SKILL.md and scripts/generate_image.py expect ARK_API_KEY (or VOLCENGINE_API_KEY) in the environment. The registry metadata incorrectly declares no required env vars — treat that as an omission and only provide an API key you trust the skill should use (i.e., purpose-limited or revocable key). - Verify the path/name: examples reference ~/.workbuddy/skills/seedream-image-gen while the registry slug is seedream-img-gen. Confirm you are running the bundled scripts from the repository you installed to avoid running an unexpected copy. - Review the bundled script yourself (scripts/generate_image.py) before running. It makes network calls only to Volcengine endpoints and downloads returned image URLs. Ensure you are comfortable with the SDKs it recommends (volcengine-sdk or openai-compatible client) and install those in an isolated environment (virtualenv). - Be cautious with the --output path you pass to avoid writing files to sensitive locations. The script will download any URL returned by the API — if you have concerns, run it in a sandbox or inspect API responses before auto-downloading. - If you need higher assurance, ask the publisher for corrected metadata that declares ARK_API_KEY as a required env var and clarifies the exact install path, or request an origin/source (homepage/author) so you can verify provenance. Confidence is medium because the code and docs are consistent with the described purpose, but the metadata omissions and path/name mismatches are unexplained and merit user attention before trusting credentials or running the skill.

Seedream 图片生成 Skill

概述

本 Skill 帮助通过火山引擎方舟平台（Volcengine Ark）的 Seedream 系列模型生成图片，支持文生图（text-to-image）和图生图（image-to-image，Seedream 4.0+）。

---

前置条件

1. 获取 API Key：前往 https://console.volcengine.com/ark 注册并获取 ARK_API_KEY
2. 开通模型：在方舟平台「开通管理」页面开通所需模型
3. 安装依赖（二选一）：
   • 官方 SDK：pip install 'volcengine-python-sdk[ark]'
   • OpenAI 兼容：pip install openai

---

核心工作流

1. 收集必要信息

在生成图片前，需要明确：

• 提示词（prompt）：图片内容描述，支持中英文
• 模型选择：默认使用 doubao-seedream-3-0-t2i-250415（详细模型列表见 references/api_reference.md）
• 图片尺寸（可选）：如 1024x1024、1792x1024
• 输出路径（可选）：保存图片的本地路径

如果用户未明确提到模型，默认使用 Seedream 4.0（doubao-seedream-4-0-250828）。

2. 检查环境

To verify the environment is ready, run:

echo $ARK_API_KEY

If the API key is missing, instruct the user to set it:

export ARK_API_KEY="your_api_key_here"

3. 调用生成脚本

Use the bundled script at scripts/generate_image.py:

# 基本用法（文生图）
python3 ~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py \
  --prompt "一只可爱的橘猫坐在窗边看夕阳，写实摄影风格" \
  --output output.png

# 指定模型
python3 ~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py \
  --prompt "a cyberpunk city at night" \
  --model doubao-seedream-4-0-250828 \
  --output output.png

# 指定尺寸
python3 ~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py \
  --prompt "横版风景画，超宽屏" \
  --size 1792x1024 \
  --output landscape.png

# 生成多张
python3 ~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py \
  --prompt "卡通风格的小动物" \
  --n 4 \
  --output animals.png

# 使用 OpenAI 兼容模式
python3 ~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py \
  --prompt "描述内容" \
  --sdk openai \
  --output result.png

4. 处理结果

• 脚本成功执行后会输出图片保存路径
• 生成的图片默认保存到当前工作目录，也可通过 --output 指定
• 使用 url 格式时，脚本会自动下载图片到本地

---

快速内联调用（不使用脚本）

如果希望直接生成代码调用，可用以下模板：

import os
from volcenginesdkarkruntime import Ark

client = Ark(api_key=os.environ.get("ARK_API_KEY"))
resp = client.images.generate(
    model="doubao-seedream-3-0-t2i-250415",
    prompt="YOUR_PROMPT_HERE",
    response_format="url",
)

url = resp.data[0].url
print("图片 URL:", url)

# 下载图片
import urllib.request
urllib.request.urlretrieve(url, "output.png")
print("已保存至 output.png")

---

模型选择建议

场景	推荐模型
通用文生图，快速稳定	doubao-seedream-3-0-t2i-250415
高质量图片，支持参考图	doubao-seedream-4-0-250828
最新最强效果	doubao-seedream-4-5-251128
极速轻量	doubao-seedream-5-0-lite

---

参考资源

• 详细 API 参数和代码示例：references/api_reference.md
• 生成脚本（支持命令行调用）：scripts/generate_image.py
• 官方文档：https://www.volcengine.com/docs/82379