Image Catch Skill logo

Image Catch Skill

Community
jiushiwon
image-catch-skill

Use when 用户需要按语义搜索并下载高清图片。

Overview

Publisherjiushiwon
Repositorywg-skills
Skill nameimage-catch-skill
Stars
123
Forks
38
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by jiushiwon on GitHub. Read the source before you install it.

Installation

Install the Image Catch Skill 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.
    https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/frontend/icon-image-catch-skill/image-catch-skill
  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/jiushiwon/wg-skills.git /tmp/wg-skills
mkdir -p .claude/skills
cp -r /tmp/wg-skills/vibeCoding/frontend/icon-image-catch-skill/image-catch-skill .claude/skills/image-catch-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Image Catch Skill 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 Image Catch Skill 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 Image Catch Skill 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.

image-catch-skill — 图片抓取规范

本技能提供图片抓取流程,不执行本地脚本。Claude 应根据以下规范,直接调用图库 API 或浏览器/网络工具完成下载。

数据源

本技能采用可配置源优先设计:

源类型配置方式说明
自定义源(推荐)用户提供的远程图片服务 / CDN地址内容由用户控制
正版图库Pexels / Pixabay / Unsplash API Key质量更高,适合正式项目
默认兜底Lorem Flickr(关键词语义)+ Picsum(随机占位)无需任何配置

各图源特点

源质量推荐场景是否需要 Key
Pexels⭐⭐⭐⭐⭐正式项目、Hero、Banner免费 Key
Pixabay⭐⭐⭐⭐内容运营、营销页、插画免费 Key
Unsplash⭐⭐⭐⭐⭐大图/Hero/品牌视觉免费 Key
Lorem Flickr⭐⭐⭐Demo、原型、占位图无需 Key
Picsum⭐⭐纯视觉占位、测试无需 Key

使用前询问规范

当用户要求抓图片时,Claude 必须先询问用户想用的图源,给出风格/质量推荐,再执行。示例:

准备抓「科技感办公」配图,可选图源:

  1. Pexels — 高质量真实照片(推荐正式项目)
  2. Pixabay — 量大,含插画/矢量
  3. Unsplash — 画质最高,艺术感强
  4. Lorem Flickr — 无需 Key,真实照片但授权不确定
  5. Picsum — 无需 Key,纯占位
  6. 全部自动 — 按 Pexels → Pixabay → Unsplash → Lorem Flickr → Picsum 顺序自动降级(默认)

你想用哪个?直接回车默认全部自动。

如果用户明确指定了源,或已配置自定义源,则不再询问。

标准抓取流程

  1. 明确主题:从需求提取图片内容词(如「团队配图」→ teamwork),越具体越好。
  2. 询问图源:向用户展示可选源及风格推荐,确认后执行;用户已指定则跳过。
  3. 英文关键词:优先使用英文搜索;中文需求参考 references/image-sources.md 的中英文映射表。
  4. 定规格:按使用位置定方向(横版/竖版/方形)与尺寸。
    • 若项目已执行过素材审计,优先使用 assets-requirements-report.md 中的平台与推荐尺寸。
    • 若未审计,根据项目关键文件探测平台(参考 ../references/project-type-detection.md),再匹配 ../references/image-sizes.md 中的默认尺寸。
    • 用户已明确指定尺寸时,以用户为准。
  5. 询问压缩:下载图片时先询问是否压缩。若需要本地压缩/裁剪/格式转换,转 frontend-icon-skill;若仅需远程缩放,使用各图源支持的缩放参数。
  6. 选源降级:优先使用用户自定义源;未配置则尝试 Pexels/Pixabay/Unsplash;仍无则使用 Lorem Flickr 和 Picsum 兜底。
  7. 落地保存:保存到项目图片目录(uniapp 默认 static/images/)。

API 调用参考

Pexels

GET https://api.pexels.com/v1/search?query={query}&per_page={count}&orientation={landscape|portrait|square}
Authorization: {PEXELS_API_KEY}

Pixabay

GET https://pixabay.com/api/?key={KEY}&q={query}&per_page={count}&image_type=photo&safesearch=true&orientation={horizontal|vertical}

Unsplash

GET https://api.unsplash.com/search/photos?query={query}&per_page={count}&orientation={landscape|portrait|squarish}
Authorization: Client-ID {ACCESS_KEY}

Lorem Flickr

GET https://loremflickr.com/{width}/{height}/{keyword}?lock={seed}

Picsum

GET https://picsum.photos/seed/{seed}/{width}/{height}

参数规范

参数说明示例
source指定源pexels / pixabay / unsplash / loremflickr / picsum / custom / all
count数量5
out下载目录./static/images
width目标宽度1920
height目标高度600
orientation方向landscape / portrait / squarish
name文件名前缀hero-bg

压缩/切图/格式转换

本技能不本地执行图片处理脚本。需要时:

  • 优先使用 frontend-icon-skill 处理本地图片。
  • 或在下载时利用图源远程缩放参数(如 Unsplash ?w=1920&q=80)。

异常处理

  • 无可用源:提示用户配置自定义源或 API Key;未配置时自动使用 Lorem Flickr 和 Picsum 兜底。
  • 某源限流/失败:自动降级到下一源。
  • 搜不到合适图片:换更具体的英文词,或加风格词(如 minimal、flat lay)。

使用规范

  • 需要图片的场景尽量用真实图片,禁止用渐变色区块占位。
  • 背景图上的文字需加遮罩确保对比度。
  • 按显示区域选尺寸;首屏图预加载、非首屏懒加载;支持时优先 WebP。
  • 图片必须添加 alt 属性描述内容。
  • 图片加载失败时要有纯色背景 fallback。

触发词

image-catch、image-catch-skill — 图片抓取规范

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 Image Catch Skill AI skill do?

Use when 用户需要按语义搜索并下载高清图片。

Why use Image Catch Skill on TypingMind?

Because you install it once and use it with any model. Image Catch Skill 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 Image Catch Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jiushiwon/wg-skills/tree/main/vibeCoding/frontend/icon-image-catch-skill/image-catch-skill. 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 Image Catch Skill?

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 Image Catch Skill?

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

Is the Image Catch Skill AI skill free?

Yes. It is published on GitHub by jiushiwon 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 👇