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 AgenticAIPlan/AgenticAISkills --skill ernie-image-assistantgit clone --depth 1 https://github.com/AgenticAIPlan/AgenticAISkillsWrote 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/agenticaiplan/agenticaiskills/ernie-image-assistant)<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/ernie-image-assistant"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/ernie-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/agenticaiplan/agenticaiskills/ernie-image-assistant"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/ernie-image-assistant.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 | $0.00149 | $0.01594 |
| Opus 5 | $0.00075 | $0.00797 |
| Sonnet 5 | $0.00030 | $0.00319 |
| Haiku 4.5 | $0.00015 | $0.00159 |
Grade A, and why
ernie-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 12d 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.
curl -s https://aistudio.baidu.com/llm/lmapi/v3/chat/completions \ How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ERNIE-Image Assistant: Enter Prompt, Auto-Generate
使用场景
用户说以下类似内容时触发此 skill：
- "帮我逆向这张图的提示词"
- "分析这张图片，生成文生图 prompt"
- "我想复现这张图，帮我写提示词"
- "反推一下这张图的 prompt"
- "逆向提示词"
- "图片转 prompt"
环境要求
- 需要设置星河社区 API Key：
export AISTUDIO_API_KEY="your-key" - API 端点：
https://aistudio.baidu.com/llm/lmapi/v3/chat/completions - 分析模型：
ernie-4.5-turbo-vl-32k（支持多模态图片理解） - 目标生图模型：Ernie-image-turbo（通过星河社区调用）
工作流程
Step 1: 获取图片
确认用户提供的图片来源：
- 用户粘贴本地图片路径（如
/path/to/image.png） - 如果用户未提供图片，主动询问
支持格式： PNG、JPG、JPEG、WebP、BMP
获取图片后，使用 Read 工具读取图片文件以确认图片可访问，然后将其转为 base64 编码用于 API 调用。
# 将图片转为 base64
base64 -i <图片路径>
Step 2: 多维度视觉分析
调用星河社区 ERNIE-4.5 多模态 API，对图片进行结构化深度分析。
API 调用方式：
curl -s https://aistudio.baidu.com/llm/lmapi/v3/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: bearer $AISTUDIO_API_KEY" \
-d '{
"model": "ernie-4.5-turbo-vl-32k",
"messages": [{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": "data:image/<ext>;base64,<BASE64_DATA>"}},
{"type": "text", "text": "<分析提示词>"}
]
}],
"temperature": 0.3,
"max_tokens": 4096
}'
分析提示词（系统级，写入 text 字段）：
参见 references/analysis-prompt.md 中的完整分析提示词模板。
分析维度：
| 维度 | 关注点 |
|---|---|
| 主体内容 | 画面中的核心对象、人物特征（发型/服装/表情/动作）、场景元素 |
| 艺术风格 | 动漫/胶片/写实/水彩/油画/像素/赛博朋克等风格识别 |
| 构图方式 | 视角（俯拍/仰拍/平视）、构图法则（三分法/对称/引导线）、景深 |
| 色彩基调 | 主色调、配色方案、色温（冷/暖）、饱和度、对比度 |
| 光影效果 | 光源方向、光线类型（自然光/逆光/霓虹灯）、阴影特征 |
| 氛围情绪 | 整体氛围（温馨/忧郁/热血/宁静）、情绪表达 |
| 文字渲染 | 图中出现的文字内容、字体风格、排版位置、文字特效（如果有） |
| 纹理质感 | 画面质感（颗粒感/平滑/磨砂）、特效（光斑/烟雾/雨滴） |
Step 3: 生成多版本提示词
基于 Step 2 的分析结果，生成 3 个版本的 ERNIE-Image 提示词：
版本说明：
| 版本 | 用途 | 特点 |
|---|---|---|
| 精准复现版 | 尽可能还原原图 | 包含全部细节描述，最长最详细 |
| 创意改编版 | 在原图基础上微调 | 保留核心风格，简化部分细节，留出创意空间 |
| 精简核心版 | 快速出图 | 只保留最关键的风格和主体描述 |
提示词撰写规范：
参见 references/prompt-writing-guide.md 中的 ERNIE-Image 提示词撰写指南。
Step 4: 输出结果
按以下格式输出完整的逆向分析报告：
## 图片逆向分析报告
### 一、视觉分析
#### 主体内容
...
#### 艺术风格
...
#### 构图与视角
...
#### 色彩分析
...
#### 光影效果
...
#### 氛围与情绪
...
#### 文字内容（如有）
...
#### 纹理与质感
...
---
### 二、逆向提示词
#### 版本 A — 精准复现版
> [完整提示词]
#### 版本 B — 创意改编版
> [提示词]
#### 版本 C — 精简核心版
> [提示词]
---
### 三、生图建议
- 推荐尺寸：...
- 推荐风格参数：...
- 注意事项：...
What ships with it
4 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.
- 12d ago First seen · 181 lines · 149 tokens per session scan A eb392b5d0bde
ernie-image-assistant is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 149 tokens to every session and 1,594 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…