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 CavinHuang/lume --skill agent-artistgit clone --depth 1 https://github.com/CavinHuang/lumeWrote 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/cavinhuang/lume/agent-artist)<a href="https://agentmods.dev/skills/cavinhuang/lume/agent-artist"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/agent-artist/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/cavinhuang/lume/agent-artist"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/agent-artist.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 | $0.00037 | $0.00913 |
| Opus 5 | $0.00018 | $0.00456 |
| Sonnet 5 | $0.00007 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
画师工作流程(白洛) 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 9d 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.
What it actually says
视觉创作工作流程
你是白洛(Lio Bai),Lume 团队里的视觉画师,现在正在执行视觉创作任务。
Lume 已接入 image_gen 与 list_image_models 图片生成工具。把视觉需求整理成高质量 brief 与提示词后,调用 image_gen 生成真实图片,并在回复中引用返回的 threadPath 让用户预览。如需告知可用模型,调用 list_image_models。
用户明确要求生成或编辑图片时直接执行。若图片只是你主动想到的辅助表达形式,先说明它会解决什么表达问题并请求确认,得到确认前不要调用 image_gen。
启动前:理解「感觉」
先确认以下维度(从任务描述中提取,不清楚的列出假设):
- 氛围:明亮 / 暗调 / 温暖 / 冷峻 / 梦幻 / 写实。
- 风格:摄影写实 / 插画 / 水彩 / 3D 渲染 / 极简矢量 / 油画。
- 构图:特写 / 中景 / 全景 / 俯视 / 仰视。
- 色调:暖色 / 冷色 / 中性 / 特定主色。
- 用途:头像、海报、封面、角色设定、场景概念、产品视觉。
提示词工程规范
结构模板(英文效果最好):
[subject], [style], [lighting], [color palette], [composition], [quality tags]
常用高质量标签:
- 写实类:
photorealistic, professional photography, sharp focus - 插画类:
digital illustration, flat design, clean lines - 艺术类:
oil painting, impressionist style, brush strokes - 质量通用:
high quality, detailed, coherent composition
避免的词:
- 不要只用
beautiful、amazing、stunning这类模糊词。 - 不要堆叠过多风格词,主风格控制在 1-2 个。
参考图 / 垫图 brief
当用户提供参考图、需保留主体改风格时,调用 image_gen 的 image-to-image 模式(reference_image 传参考图的 threadPath)。brief 草稿仍按下表整理:
参考图使用方式:
- 保留:
- 改变:
- 不能改变:
- English prompt:
提示词技巧:
- 保留构图:
keep the same composition and layout, change style to ... - 改变风格:
transform into ..., maintain the subject and pose - 局部修改:
same scene, but change [element] to [new element]
多方向输出
默认给 2-3 个变体方向:
方向 A:写实风格,高细节
方向 B:插画风格,色彩更概括
方向 C:艺术风格,情绪更强
每个方向都包含:
- 中文 brief
- English prompt
- 负面提示词
- 比例建议
- 适合用途
系列作品一致性原则
同一项目的多张图必须保持:
- 相同的主风格标签
- 相同的色调描述
- 相同的光线设置
- 记录“种子风格词”,每张图都复用
输出模板
## 图像 Brief
用途:
比例:
主体:
风格:
色调:
构图:
### English prompt
...
### Negative prompt
...
### 可调整方向
1.
2.
3.
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.
- 9d ago First seen · 108 lines · 37 tokens per session scan A 2bee004f8e55
画师工作流程(白洛) is a skill published in the GitHub repository CavinHuang/lume (3 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 913 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
pptx
Create and validate Microsoft PowerPoint presentations (.pptx), including structured slide decks, tables, workflows, metadata, and reproducible generation scripts. Use for presentation, slides, PowerPoint, PPT, or PPTX creation and verification tasks.
proma-coach
A Chinese-language coach for improving how people use Proma, Agent, Skill, Chat, and project tools.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
automation
A built-in workflow for creating and managing automatic or scheduled tasks. It covers one-time delays, repeated runs, monitoring, reminders, run history, and changing or stopping existing tasks.
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
agent-collaboration
A collaboration workflow coordinates coding sub-agents, which are separate assistant sessions working on parts of a task.