Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tengmmvp/Seedream_MCP --skill seedream-image-generationgit clone --depth 1 https://github.com/tengmmvp/Seedream_MCPWrote 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/tengmmvp/seedream_mcp/seedream-image-generation)<a href="https://agentmods.dev/skills/tengmmvp/seedream_mcp/seedream-image-generation"><img src="https://agentmods.dev/badge/skills/tengmmvp/seedream_mcp/seedream-image-generation/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/tengmmvp/seedream_mcp/seedream-image-generation"><img src="https://agentmods.dev/badge/skills/tengmmvp/seedream_mcp/seedream-image-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00147 | $0.01558 |
| Opus 5 | $0.00073 | $0.00779 |
| Sonnet 5 | $0.00029 | $0.00312 |
| Haiku 4.5 | $0.00015 | $0.00156 |
Grade A, and why
seedream-image-generation 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seedream 图像生成指南
何时使用本技能
- 用户要求生成图片、画图、作画（文生图）
- 用户要求修改图片、换风格、换背景、去水印元素（图生图）
- 用户要求把多张图片融合、合成、拼贴（多图融合）
- 用户要求制作连环画、故事书、分镜组图（组图生成）
- 用户要求拆分图层、生成透明背景素材（仅 5.0 Pro）
- 用户询问当前模型、尺寸档位，或要找回之前生成的图片
环境与前置
- 本 skill 假定客户端已连接 Seedream MCP 服务器并完成鉴权配置
- 生效模型由服务器配置决定，单次调用不可切换
- 不确定当前配置时，先读资源
seedream://server/info确认模型、默认尺寸与自动保存开关
工具速查
| 工具 | 用途 | 必需参数 | 关键限制 |
|---|---|---|---|
text_to_image |
文生图 | prompt |
无 |
image_to_image |
图生图、编辑、图层拆分 | image；prompt 仅图层拆分场景可缺省 |
图层拆分与透明背景仅 5.0 Pro |
multi_image_fusion |
多张参考图融合 | image（2 张起）、prompt |
用"图1/图2"引用各输入图 |
sequential_generation |
一次生成一组连贯组图 | prompt |
5.0 Pro 不支持组图 |
browse_images |
浏览已保存图片 | 无（全部可选） | 只读，不访问网络 |
模型差异
模型由部署方经服务器配置选定，以下差异供理解当前配置的能力边界，单次调用不可切换：
doubao-seedream-5.0（默认）：能力面最全，组图、联网搜索、流式均支持doubao-seedream-5.0-pro：独占图层拆分与透明背景，支持 fast 档提示词优化；但没有组图、联网搜索、流式，可参考图数量更少、尺寸档位更少doubao-seedream-4.5/doubao-seedream-4.0：输出仅 jpeg，不支持提示词优化
完整能力数据以读取 seedream://models/info 资源为准，不要凭记忆复述像素区间、档位清单等数值。
提示词写法
- 用连贯自然语言写明主体 + 行为 + 环境，再以短语补充风格、色彩、光影、构图等美学元素
- 建议不超过 300 个汉字或 600 个英文单词；超出后信息分散，模型可能忽略细节
- 组图与多图融合场景给每张图独立的画面描述，保持叙事顺序
- 服务器内置四个风格预设 prompt：
seedream_style_anime、seedream_style_realistic、seedream_style_watercolor、seedream_style_oil_painting，可作为风格后缀参考
关键参数规则
- 模型：由服务器配置决定，单次调用不可切换；图层拆分与透明背景需部署方将服务器配置为 5.0 Pro
size：档位（1K/1.5K/2K/3K/4K）或宽x高像素；省略时默认2K；图层拆分场景仅接受档位或autowatermark：默认不加水印optimize_prompt_options：standard或fast；fast仅 5.0 Pro 与 4.0 支持response_format：默认url；output_format仅 5.0 系列支持 jpeg/png 选择stream：5.0 Pro 不支持tools：[{"type": "web_search"}]开启联网搜索，5.0 Pro 不支持request_count：1-10 张候选图；组图场景语义为"每次产出一组"max_images（组图）：1-15，省略时自动取 15 减去参考图数量layer_decomposition（图层拆分）：输出 1 张底图 + 至多 16 张透明 PNG 图层，仅 5.0 Pro 图生图auto_save/save_path/custom_name：控制单次保存行为，见下节
What ships with it
2 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.
- 11d ago First seen · 77 lines · 147 tokens per session scan A 00fbab5e6f3e
seedream-image-generation is a skill published in the GitHub repository tengmmvp/Seedream_MCP (22 stars, last pushed today), licensed MIT. It adds 147 tokens to every session and 1,558 once invoked, about $0.0007 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
post-to-xhs
A publishing guide for 小红书, a Chinese social-media platform. It covers posting image-and-text content or a longer formatted article, using supplied content or a webpage.
screenshot-camera
Capture a screenshot from a Unity Camera and return it as a PNG image for direct LLM inspection. Falls back to Camera.main (then any active camera) when cameraRef is null. Width and height are capped to keep response size manageable.
screenshot-game-view
Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.
screenshot-scene-view
Capture a screenshot from the Unity Editor Scene View at the requested size. Renders via the Scene View's active camera onto a temporary RenderTexture. Requires an open Scene View.
AI Image & Video Generator — GPT Image 2, Seedance, ComfyUI
Generate images and videos from text with multi-provider routing — supports GPT Image 2.0 (near-perfect text rendering), Nanobanana 2, Seedream 5.0, Midjourney V8.1 (unified photorealistic + anime), Flux 2 Klein (cheap drafts), Seedance 2.0 / Veo 3.1 / Grok Video / Agnes Video, and local ComfyUI workflows. Includes…
image-prompting
Use when generating or editing images via blockrunimage — especially with GPT Image 2, Nano Banana, or Grok Imagine for posters, UI mockups, marketing assets, product shots, or anything with on-image text. Turns vague user requests ("make me a cool poster") into structured, text-accurate prompts that actually render…