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 staruhub/ClaudeSkills --skill geek-skills-seedream-imagegengit clone --depth 1 https://github.com/staruhub/ClaudeSkillsWrote 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/staruhub/claudeskills/geek-skills-seedream-imagegen)<a href="https://agentmods.dev/skills/staruhub/claudeskills/geek-skills-seedream-imagegen"><img src="https://agentmods.dev/badge/skills/staruhub/claudeskills/geek-skills-seedream-imagegen/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/staruhub/claudeskills/geek-skills-seedream-imagegen"><img src="https://agentmods.dev/badge/skills/staruhub/claudeskills/geek-skills-seedream-imagegen.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 | $0.00125 | $0.01361 |
| Opus 5 | $0.00063 | $0.00681 |
| Sonnet 5 | $0.00025 | $0.00272 |
| Haiku 4.5 | $0.00013 | $0.00136 |
Grade A, and why
seedream-imagegen 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 13d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seedream 4.0 图像生成
通过 scripts/generate_image.py 调用 Seedream 4.0 生成专业级图像。
验收标准（每次生成任务完成前自查）
- 提示词经过结构化优化（[主题]+[风格]+[细节]+[质量词]），不是用户原话直接透传
- size / aspect_ratio 与用途匹配（见参数对照表），不是默认值裸跑
- 图像已落盘并把实际文件路径回报给用户
- 重要用途（海报/品牌）生成 ≥3 张供选择
- 告知了本次消耗（张数×分辨率），4K 提前说明更耗时耗额度
不做什么
- 不编辑、重绘、扩展已有图片——只做文生图（参考图仅用于风格指导）
- 无
SEGMIND_API_KEY时不硬试：告知用户去 segmind.com 获取，或改用环境内其他生图 skill - 不对生成内容的版权归属下结论
- 用户只要一张随手配图时,不展开完整需求问卷,合理默认直接出
工作流程
1. 收集需求（缺什么问什么，不逐项走问卷）
必需：图像内容描述。推荐确认：尺寸（默认 2K）、比例（默认 1:1）、数量（默认 1）。
用途 → 参数对照表
| 用途 | size | aspect_ratio | max_images |
|---|---|---|---|
| 社交媒体 | 2K | 1:1 或 9:16 | 1-3 |
| 网页横幅 | 2K | 16:9 或 21:9 | 1 |
| 打印海报 | 4K | 4:3 或自定义 | 1-2 |
| 产品图 | 2K | 3:2 或 4:3 | 3-5 |
| 概念设计 | 2K | 16:9 | 5-10 |
2. 优化提示词
结构：[主题] + [风格] + [细节] + [质量修饰词]，补光照与氛围；需要图内文字时明确指定文字内容与字体风格；建议 200-300 词内。
示例："一只猫" → "A fluffy orange tabby cat on a wooden windowsill, golden hour lighting, cozy interior, warm palette, professional photography, detailed fur texture"。
风格关键词库与更多范式：references/prompt_engineering.md。
3. 执行
python scripts/generate_image.py \
--prompt "优化后的提示词" \
--size 2K --aspect-ratio 16:9 --max-images 1 \
--output-dir ./outputs
# API key 从环境变量 SEGMIND_API_KEY 读取，或用 --api-key 传入
高级用法（参考图 image_input ≤3 张 / 顺序批量 sequential=True 保持系列一致 / size=custom 自定义宽高）：
Python 调用示例见 references/quick_start.md，参数完整说明见 references/api_reference.md。
4. 迭代
不满意时先问具体不满意什么，再对症调整：细节不足→加描述；风格不对→换风格关键词或上参考图；清晰度→升 4K；选择面→加张数。
已知陷阱
| 陷阱 | 具体表现 | 应对 |
|---|---|---|
| 401 / 额度耗尽 | API 报 401 或 quota 错误 | 检查 SEGMIND_API_KEY；额度问题如实告知用户，不静默重试烧额度 |
| 内容审核拒绝 | 提示词含敏感元素被拒 | 告知被拒原因类别，改写提示词规避后重试一次；连续被拒则停下与用户确认 |
| 图内文字模糊 | 生成的海报文字发虚、错字 | 提示词明确指定文字内容+字体风格，加 "high contrast, bold typography"；升 4K；仍不行改"留位后期加字" |
| 4K 时间预期 | 用户以为卡住 | 提前说明 2K 约 2 秒、4K 约 4-6 秒，批量线性叠加 |
| 超限参数静默失败 | >15 张或 >3 参考图 | 生成前校验参数上限，超限先拆分或询问 |
| 直接透传短提示词 | "一只猫"直接发 API，出图平庸 | 验收标准第一条：必须先优化 |
参考文档（按需加载）
What ships with it
5 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.
- 13d ago First seen · 82 lines · 125 tokens per session scan A f0d8094e5bab
seedream-imagegen is a skill published in the GitHub repository staruhub/ClaudeSkills (712 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 1,361 once invoked, about $0.0006 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
report-helper
A Chinese-language research workflow that searches the internet and produces a formatted PDF report about a specified topic.
giasip-dispatch
A skill for sending a task to other AI models and collecting their results. It supports direct API calls, command-line tools and built-in internal agents, depending on the model.
searchcans-deep-research
Conduct bounded, evidence-led, account-aware web research with SearchCans SERP API and Reader API. Use for cited-source research that needs current localized web evidence, such as market, competitor, technology, policy, company, or product research; plan 3–5 subquestions, set a source budget, read selected pages…
searchcans-serp-content-gap
Analyze a current, geo-targeted Google or Bing SERP with SearchCans and turn observed result features, People Also Ask questions, related searches, knowledge graph, and news signals into an evidence-backed, account-aware content decision brief. Use for localized SEO/GEO planning, keyword research, competitor-page…
searchcans-market-watch
Build a current, geo-targeted market-watch snapshot from Google Search, Google News, Bing Search, and selected Reader extracts. Use for competitor and category monitoring, PR/news tracking, launch intelligence, and URL-level change checks between two bounded runs; reject malformed, placeholder, or un-attributable News…
searchcans-product-serp-brief
Create a localized product-search evidence brief from Google Shopping, Google web results, Google Images, and optional Reader extracts of explicit merchant URLs. Use for e-commerce category research, competitor assortment discovery, product-page planning, and market-specific merchandising briefs.