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 yunshu0909/yunshu_skillshub --skill image-assistantgit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/image-assistant)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/image-assistant"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/image-assistant/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/yunshu0909/yunshu_skillshub/image-assistant"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/image-assistant.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 | $0.00073 | $0.01280 |
| Opus 5 | $0.00036 | $0.00640 |
| Sonnet 5 | $0.00015 | $0.00256 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
image-assistant scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
├── apimart-curl.md What it actually says
配图助手
触发方式
当用户说类似以下内容时触发：
- “这段内容做个图 / 配几张图？”
- “给我两张（或多张）出图提示词”
- “字太多不好看，帮我更趣味、更好读”
- “把这个流程封装成提示词模板/skills”
- “/image “/配图” “/出图”
流程概览
| 阶段 | 名称 | 目标 | 详细文件 |
|---|---|---|---|
| 1 | 需求澄清（Spec/DoD） | 先挖需求：内容/场景/受众/字多字少；尺寸与风格默认；产出一句话复述与需求小结 | stages/01-brief.md |
| 2 | 配图规划（拆块→清单） | 拆内容→定图清单（几张/每张讲啥/用啥模板） | stages/02-plan.md |
| 3 | 文案定稿（Copy Spec） | 逐字定稿“图上写什么”（唯一真值） | stages/03-copy.md |
| 4 | 提示词封装（Prompt Pack） | 把 Copy Spec 封装成可复制提示词；生成批量请求包并在用户确认后批量出图 | stages/04-prompts.md |
| 5 | 迭代润色 | 根据反馈减字、换隐喻、提可读性 | stages/05-iterate.md |
调度规则
如何判断当前阶段：
- 还没把需求讲清楚（内容 + 场景 + 受众 + 字多/字少）→ 阶段1
- 文章很长、需要拆块，或需要确定“几张图/每张讲什么”→ 阶段2
- 已确认图清单，但还没确定“图上逐字写什么”→ 阶段3
- Copy Spec 已确认，要出可复制提示词；（可选）提示词确认后批量出图 → 阶段4
- 用户反馈“字多/不好看/不符合封面” → 阶段5（必要时回退到阶段1重锁需求与字多/字少）
每个阶段开始时：
- 告诉用户当前阶段与本阶段输出物
- 读取对应阶段文件并按步骤执行
输出规范（必须遵守）
- 每张图一个“核心信息”，不把解释性段落塞进图里
- 所有中文必须清晰可读：大字号、少字短句、避免密集小字
- 每张提示词用一个独立代码块输出，便于复制
- 默认输出 16:9 横版（除非用户明确要 3:4 漫画/竖版）
- 默认风格：奶油纸底 + 彩铅水彩手绘 + 轻涂鸦，趣味但干净（可用
templates/style-block.md） - 阶段3产物（Copy Spec）一旦确认，阶段4不得擅自改文案，只做封装与参数/约束补全
快速使用（给用户的最小输入）
用户只要给这四项，就能开始：
- 要配图的内容（可是一段、一个小节、或整篇文章）
- 用在哪里 + 观看距离（PPT投影远看 / 手机近看 / 海报）
- 谁来看（小白/从业者/老板/学生…）
- 偏好：更“少字清爽”还是更“信息密度”
可选补充（不写也没关系）：
- 你大概想要哪类图：封面/目录、单页概览、讲义解释、社媒海报（不确定我会根据场景与偏好推荐）
你要做的交付顺序：
- 先输出：图清单（几张 + 每张一句话目的 + 模板建议）（阶段2）
- 用户确认后：逐张输出 Copy Spec（逐字定稿）（阶段3）
- Copy Spec 确认后：逐张输出可复制提示词/调用包（阶段4）
- （可选）提示词确认后：批量调用 API 出图（阶段4内连续流程）
- 用户说“字多/不好看”就进入迭代（阶段5）
文件结构
stages/
├── 01-brief.md
├── 02-plan.md
├── 03-copy.md
├── 04-prompts.md
└── 05-iterate.md
templates/
├── style-block.md
├── 16x9-infographic.md
├── 16x9-contrast-2cards.md
├── 16x9-3cards-insights.md
├── 16x9-cover-roadmap.md
├── 16x9-5panel-comic.md
├── api-config.md
├── apimart-curl.md
├── apimart-requests-jsonl.md
└── checklist.md
examples/
└── ai-tools-selection.md
scripts/
├── apimart_batch_generate.py
├── apimart.env.example
└── README.md
What ships with it
20 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.
- examples/ai-tools-selection.md 405 B
- out/apimart.requests.example.jsonl 242 B
- scripts/__pycache__/apimart_batch_generate.cpython-311.pyc 30 KB
- scripts/apimart_batch_generate.py 20 KB runs code
- scripts/apimart.env 203 B
- scripts/README.md 890 B
- stages/01-brief.md 2.0 KB
- stages/02-plan.md 2.4 KB
- stages/03-copy.md 2.2 KB
- stages/04-prompts.md 5.3 KB
- stages/05-iterate.md 881 B
- templates/16x9-3cards-insights.md 586 B
- templates/16x9-5panel-comic.md 440 B
- templates/16x9-contrast-2cards.md 507 B
- templates/16x9-cover-roadmap.md 800 B
- templates/16x9-infographic.md 503 B
- templates/api-config.md 295 B
- templates/apimart-requests-jsonl.md 249 B
- templates/checklist.md 690 B
- templates/style-block.md 658 B
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 · 107 lines · 73 tokens per session scan A 9eb9fdb31ef3
image-assistant is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,280 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…