Images Search logo

Images Search

Organization
brave
images-search

USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.

Overview

Publisherbrave
Repositorybrave-search-skills
Skill nameimages-search
Stars
182
Forks
17
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Images Search 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/brave/brave-search-skills/tree/main/skills/images-search
  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/brave/brave-search-skills.git /tmp/brave-search-skills
mkdir -p .claude/skills
cp -r /tmp/brave-search-skills/skills/images-search .claude/skills/images-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Images Search 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 Images Search 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 Images Search 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.

Images Search

Requires API Key: Get one at https://api.search.brave.com

Plan: Included in the Search plan. See https://api-dashboard.search.brave.com/app/subscriptions/subscribe

Quick Start (cURL)

Basic Search

bash
curl -s "https://api.search.brave.com/res/v1/images/search?q=mountain+landscape" \
  -H "Accept: application/json" \
  -H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}"

With Parameters

bash
curl -s "https://api.search.brave.com/res/v1/images/search" \
  -H "Accept: application/json" \
  -H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}" \
  -G \
  --data-urlencode "q=northern lights photography" \
  --data-urlencode "country=US" \
  --data-urlencode "search_lang=en" \
  --data-urlencode "count=20" \
  --data-urlencode "safesearch=strict"

Endpoint

http
GET https://api.search.brave.com/res/v1/images/search

Authentication: X-Subscription-Token: <API_KEY> header

Parameters

ParameterTypeRequiredDefaultDescription
qstringYes-Search query (1-400 chars, max 50 words)
countrystringNoUSSearch country (2-letter country code or ALL)
search_langstringNoen2+ char language code
countintNo50Results to return (1-200)
safesearchstringNostrictoff or strict (no moderate for images)
spellcheckboolNotrueAuto-correct query; corrected query in query.altered

Response Format

json
{
  "type": "images",
  "query": {
    "original": "mountain landscape",
    "altered": null,
    "spellcheck_off": false,
    "show_strict_warning": false
  },
  "results": [
    {
      "type": "image_result",
      "title": "Beautiful Mountain Landscape",
      "url": "https://example.com/mountain-photo",
      "source": "example.com",
      "page_fetched": "2025-09-15T10:30:00Z",
      "thumbnail": {
        "src": "https://imgs.search.brave.com/...",
        "width": 200,
        "height": 150
      },
      "properties": {
        "url": "https://example.com/images/mountain.jpg",
        "placeholder": "https://imgs.search.brave.com/placeholder/...",
        "width": 1920,
        "height": 1080
      },
      "meta_url": {
        "scheme": "https",
        "netloc": "example.com",
        "hostname": "example.com",
        "favicon": "https://imgs.search.brave.com/favicon/...",
        "path": "/mountain-photo"
      },
      "confidence": "high"
    }
  ],
  "extra": {
    "might_be_offensive": false
  }
}

Response Fields

FieldTypeDescription
typestringAlways "images"
query.originalstringOriginal query
query.alteredstring?Spellchecked query (null if no correction)
query.spellcheck_offbool?Whether spellcheck was disabled
query.show_strict_warningbool?True if strict safesearch hid relevant results
results[]arrayList of image results
results[].typestringAlways "image_result"
results[].titlestring?Image title
results[].urlstring?Page URL where image was found
results[].sourcestring?Source domain
results[].page_fetchedstring?ISO datetime of last page crawl
results[].thumbnail.srcstring?Brave-proxied thumbnail URL (~500px width)
results[].thumbnail.widthint?Thumbnail width
results[].thumbnail.heightint?Thumbnail height
results[].properties.urlstring?Original full-size image URL
results[].properties.placeholderstring?Low-res placeholder URL (Brave-proxied)
results[].properties.widthint?Original image width (may be null)
results[].properties.heightint?Original image height (may be null)
results[].meta_url.schemestring?URL protocol scheme
results[].meta_url.netlocstring?Network location
results[].meta_url.hostnamestring?Lowercased domain
results[].meta_url.faviconstring?Favicon URL
results[].meta_url.pathstring?URL path
results[].confidencestring?Relevance: low, medium, or high
extra.might_be_offensiveboolWhether results may contain offensive content

Use Cases

  • Visual content discovery: Build image galleries, mood boards, or visual research tools. Use count=200 for comprehensive coverage. Prefer over web-search when you need image-specific metadata (dimensions, thumbnails).
  • Content enrichment: Add relevant images to articles or generated content. Use country and search_lang to target your audience's locale.
  • Safe image retrieval: Default safesearch=strict ensures family-friendly results out of the box. Only two modes (off/strict) — no moderate option, unlike web/video/news search.
  • High-volume batch retrieval: Up to 200 images per request (vs 20 for web, 50 for videos/news). Ideal for bulk image sourcing or visual analysis pipelines.

Notes

  • SafeSearch: Defaults to strict for images (stricter than web search)
  • High volume: Can return up to 200 results per request
  • Thumbnails: Brave-proxied for user privacy (500px width). Use properties.url for original full-resolution image.
  • Dimensions: properties.width/height may be missing for some images
  • Placeholder: properties.placeholder is a low-res URL (not inline base64) useful for progressive loading UX

Frequently asked questions

What does the Images Search AI skill do?

USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.

Why use Images Search on TypingMind?

Because you install it once and use it with any model. Images Search 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 Images Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/brave/brave-search-skills/tree/main/skills/images-search. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Images Search?

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 Images Search?

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

Is the Images Search AI skill free?

Yes. It is published on GitHub by brave under the MIT 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 👇