Ecom Details Image logo

Ecom Details Image

OrganizationPopular
ZJU-REAL
ecom-details-image

生成电商商品视觉方案:主图概念、场景图、详情页视觉方向和 AI 生图 Prompt。 当用户说"商品主图""详情页视觉""电商配图方案""商品场景图""带货视觉""产品视觉方向""详情页设计"时使用。 本 SKILL 出视觉方案+生图 Prompt(策划);实际抠白底图用 remove-bg,实际生成图片用 ai-image-gen。

Overview

PublisherZJU-REAL
RepositoryEasel
Skill nameecom-details-image
Stars
1.2K
Forks
175
Bundled files
31
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 31 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ZJU-REAL on GitHub. Read the source before you install it.

Installation

Install the Ecom Details Image AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ZJU-REAL/Easel.git /tmp/Easel
mkdir -p .claude/skills
cp -r /tmp/Easel/skills/openclaw/ecom-details-image .claude/skills/ecom-details-image
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ecom Details Image in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ecom Details Image on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ecom Details Image is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ecom-details-image Skill

当用户需要视觉策略、图片 Prompt、商品主图、营销图、社媒图、广告图、电商 PDP 视觉,或要求直接 AI 生图时,使用这个 Skill。

两种模式:

  1. Brief / Prompt 模式:只输出视觉简报和可执行图片 Prompt。
  2. Generate 模式:当用户明确要求"生图、生成图片、出图、render image"时,先输出最终 Prompt,再调用 scripts/generate_image.py

审美方向对齐 card-design:详情页信息图 / 营销图的视觉方向遵守同一套去 AI 廉价感原则——禁蓝紫科技渐变、禁 emoji 当图标、字大字细、留白克制、填满不空。把这些写进 Prompt 的正向/否定约束里(本 SKILL 出 t2i Prompt,非 HTML 渲染,故是"审美方向"层面对齐,不走 render_card)。

不要暴露、索要、写入、提交或回显真实 API key。使用者必须通过自己的环境变量配置 API。

References(按需加载,不要一次性全读)

文件内容何时读
references/templates.md25 个场景模板匹配表、使用方式、风格变体速查判断场景类型、匹配模板时
references/templates/*.json具体场景模板(prompt_template/variants/category_tips/anti_ai_tips只读匹配到的那一个
references/image-gen-rules.md通用 Prompt 结构、文生图铁律、精简原则、Anti-AI 技巧、翻车点防护写每一条 Prompt 时
references/campaign-style-lock.md多图任务的 Campaign Style Lock 规则与默认模板任务含多张图时
references/pdp-sequences.md转化驱动诊断、主图/详情页序列、多角度镜头、详情页信息图结构、字体搭配商品图/详情页/PDP 任务时

核心流程

  1. 判断视觉任务类型和场景 → 读 references/templates.md 匹配模板。
  2. references/templates/ 读取匹配到的那一个 JSON,取 prompt_templatevariantscategory_tips 作为 Prompt 基础结构。
  3. 只收集会实质影响图片结果的缺失信息(见下方最小输入)。
  4. 构建视觉简报。
  5. 多图任务:先按 references/campaign-style-lock.md 建立 Campaign Style Lock,锁定整套图的色板、冷暖调、字体、背景、光线、布局和图标风格。
  6. references/image-gen-rules.md 写出可执行图片 Prompt(保持简洁,逐条对照铁律);多图任务必须把同一段 Campaign Style Lock 原样放进每张 Prompt。
  7. 商品图/详情页/营销图:按 references/pdp-sequences.md 先做转化驱动力诊断,再排序列。
  8. 用户要求电商详情页 / PDP / 主图堆栈 / 整套商品图时,默认输出 5 张主图 + 7-9 张详情页图片 的图片包(详情页每屏必须是电商信息图格式,见 references/pdp-sequences.md)。
  9. 用户要求直接出图 → 调用 scripts/generate_image.py;用户提供参考产品图时传入 --image
  10. 返回 Prompt、生成文件路径和关键假设。

最小输入

任何视觉任务优先确认:目标、用途(主图/广告图/社媒图/Banner/PDP 模块/缩略图等)、主体、受众与语境、风格、构图与比例、是否需要图内文字、负面约束。缺少非关键字段时,明确假设后继续,不要无谓阻塞。

生图脚本调用(scripts/generate_image.py)

直接生图走 apimart.ai 图像生成接口(模型由 IMG_MODEL 指定,model-agnostic,异步轮询);也可改用统一生图入口 skill ai-image-gen。优先在 .claude/skills/ecom-details-image/.env,不要把真实 API key 写进仓库:

dotenv
IMG_BASE_URL=https://api.apimart.ai/v1
IMG_MODEL=gpt-image-2
IMG_API_KEY=your-api-key

脚本兼容别名:OPENAI_BASE_URLOPENAI_API_BASEOPENAI_IMAGE_MODELOPENAI_MODELOPENAI_API_KEY

调用形状:

bash
python3 skills/openclaw/ecom-details-image/scripts/generate_image.py --prompt "..." --size 1:1 --resolution 2k
python3 skills/openclaw/ecom-details-image/scripts/generate_image.py --prompt-file prompt.txt --output-dir outputs
python3 skills/openclaw/ecom-details-image/scripts/generate_image.py --env-file .env --image product.jpg --prompt-file prompt.txt

参数:--prompt / --prompt-file--output-dir(仅用户指定时用,否则 generated-images/);--size(比例格式,14 种,如 1:1/16:9/2:3/4:5,默认 1:1);--resolution1k/2k/4k,默认 2k,4K 仅限 6 个宽幅比例);--image(参考产品图路径,对保证产品外观准确非常有效);--poll-interval(默认 5);--timeout(默认 180);--format(默认 png)。

生图规则:

  1. 先输出最终 Prompt,再调脚本。短 Prompt 用 --prompt,长 Prompt 用 --prompt-file
  2. 根据平台选 --size,没要求时默认 1:1
  3. 缺少 IMG_API_KEY 等配置时不要调用脚本,只输出完整 Prompt 包 + 配置命令示例,说明需要在 .env 里配置什么,交给用户自行运行。
  4. 如果 API/模型不支持某尺寸,改用最接近的支持尺寸并说明。

QA 检查(输出前逐条确认)

  • Prompt 符合用户真实目标,已匹配正确场景模板并基于其 prompt_template 组装。
  • Prompt 简洁、只含核心信息,主体/构图/风格/用途明确。
  • 商品/营销任务包含转化驱动力诊断;证据缺失时不虚构效果、认证、数据、评分、销量、评价或授权。
  • 已应用文生图铁律:hex 颜色、数字占比、显式留白、否定清单、平台预留空间(详见 references/image-gen-rules.md)。
  • UGC/直播/社媒场景已应用 anti-AI 技巧(模板的 anti_ai_tips 字段)。
  • 多图任务:每张以同一段 Campaign Style Lock 开头;已分配不同角度和景别,无连续 3 张相同角度,全景图占比 ≤ 40%。
  • 详情页图片必须是电商信息图格式(含标题、图标、标签、利益点、步骤或信任徽章),每张详情页 Prompt 以 E-commerce infographic 开头,不是单纯多角度产品照片。
  • 图内文字短且必要;有用户参考图时已传 --image;负面约束覆盖常见失败点。
  • 输出和文件里没有 API key 或私密凭据。
  • 提醒用户出图后放大 200% 逐字核对中文笔画。

输出格式

Brief / Prompt 模式返回:

  1. 匹配模板(模板文件名 + 场景类型)
  2. Visual Brief
  3. Final Image Prompt
  4. Negative Constraints
  5. Assumptions

商品或营销任务追加:Conversion Driver DiagnosisCampaign Style Lock(多图时)、Hero Image Sequence(标注每张对应模板)、PDP Detail Image Sequence(涉及详情页/PDP/整套商品图时)、Copy Lines(需要文字时)、Test Priorities

Generate 模式返回:

  1. 匹配模板(模板文件名 + 场景类型)
  2. Final Image Prompt
  3. Campaign Style Lock(多图任务必须返回)
  4. Image Pack Plan(每张图的编号、用途、尺寸、对应模板和短文案)
  5. Generated Files
  6. Assumptions / Notes

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ecom Details Image AI skill do?

生成电商商品视觉方案:主图概念、场景图、详情页视觉方向和 AI 生图 Prompt。 当用户说"商品主图""详情页视觉""电商配图方案""商品场景图""带货视觉""产品视觉方向""详情页设计"时使用。 本 SKILL 出视觉方案+生图 Prompt(策划);实际抠白底图用 remove-bg,实际生成图片用 ai-image-gen。

Why use Ecom Details Image on TypingMind?

Because you install it once and use it with any model. Ecom Details Image is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ecom Details Image in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/ecom-details-image. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ecom Details Image?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ecom Details Image?

As many as you like. As long as a model supports skills, you can use Ecom Details Image with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ecom Details Image AI skill free?

Yes. It is published on GitHub by ZJU-REAL under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇