AGENT SKILL

unsplash

暂无简介

License 许可
MIT
最近更新
2026-06-07
Stars
★ 0
Forks
1

03 SKILL.md 正文

Unsplash API

Search, browse, and download high-quality free photos from Unsplash's library of millions of images.

Setup & Authentication

Get your Access Key

  1. Create account at https://unsplash.com/developers
  2. Register a new application
  3. Copy your Access Key (starts with your app name)

Store credentials

mkdir -p ~/.config/unsplash
echo "YOUR_ACCESS_KEY" > ~/.config/unsplash/access_key
chmod 600 ~/.config/unsplash/access_key

Or set environment variable:

export UNSPLASH_ACCESS_KEY="your_access_key_here"

Rate Limits

  • Demo: 50 requests/hour
  • Production: 5,000 requests/hour (after app approval)
  • Only /v1/messages endpoints count; image URLs (images.unsplash.com) don't

Common Operations

Search Photos

curl "https://api.unsplash.com/search/photos?query=nature&per_page=10" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

Parameters:

  • query: Search terms (required)
  • page: Page number (default: 1)
  • per_page: Results per page (default: 10, max: 30)
  • order_by: relevant (default) or latest
  • color: Filter by color (black_and_white, black, white, yellow, orange, red, purple, magenta, green, teal, blue)
  • orientation: landscape, portrait, or squarish

Get Random Photo

curl "https://api.unsplash.com/photos/random?query=coffee&count=1" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

Parameters:

  • query: Limit to search term (optional)
  • count: Number of photos (1-30, default: 1)
  • orientation: Filter by orientation
  • collections: Filter by collection IDs (comma-separated)

Get Photo Details

curl "https://api.unsplash.com/photos/PHOTO_ID" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

Returns full photo metadata including EXIF, location, user info, and all image URLs.

Track Download (Required!)

Important: You MUST trigger this endpoint when downloading a photo to comply with API guidelines.

curl "https://api.unsplash.com/photos/PHOTO_ID/download" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

This increments the download counter. Response includes the download URL.

List Editorial Feed

curl "https://api.unsplash.com/photos?per_page=10" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

Browse Collections

# List all collections
curl "https://api.unsplash.com/collections?per_page=10" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

# Get collection photos
curl "https://api.unsplash.com/collections/COLLECTION_ID/photos" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

User Photos

curl "https://api.unsplash.com/users/USERNAME/photos?per_page=10" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

Working with Images

Image URLs

Every photo response includes these URLs:

{
  "urls": {
    "raw": "https://images.unsplash.com/photo-xxx?ixid=xxx",
    "full": "...?ixid=xxx&q=80&fm=jpg",
    "regular": "...?ixid=xxx&w=1080&fit=max",
    "small": "...?w=400&fit=max",
    "thumb": "...?w=200&fit=max"
  }
}

Dynamic Resizing

Add parameters to any image URL (keep the ixid parameter!):

  • w=1500: Set width
  • h=800: Set height
  • dpr=2: Device pixel ratio
  • q=75: Quality (1-100)
  • fm=jpg: Format (jpg, png, webp, avif)
  • fit=crop: Fit mode (crop, max, clip)
  • crop=entropy: Crop mode

Example:

https://images.unsplash.com/photo-xxx?ixid=xxx&w=1500&h=1000&fit=crop&q=85

BlurHash Placeholders

Each photo includes a blur_hash field - a compact string representation for showing blurred placeholders while images load.

{
  "blur_hash": "LoC%a7IoIVxZ_NM|M{s:%hRjWAo0"
}

Response Structure

Photo Object (abbreviated)

{
  "id": "LBI7cgq3pbM",
  "created_at": "2016-05-03T11:00:28-04:00",
  "width": 5245,
  "height": 3497,
  "color": "#60544D",
  "blur_hash": "LoC%a7IoIVxZ_NM|M{s:%hRjWAo0",
  "description": "A man drinking coffee",
  "urls": { "raw": "...", "full": "...", "regular": "..." },
  "links": {
    "download": "...",
    "download_location": "https://api.unsplash.com/photos/xxx/download"
  },
  "user": {
    "username": "johndoe",
    "name": "John Doe",
    "profile_image": { "small": "...", "medium": "...", "large": "..." }
  }
}

Search Response

{
  "total": 133,
  "total_pages": 7,
  "results": [ /* array of photo objects */ ]
}

Best Practices

Attribution

Always attribute photos to their creators:

Photo by [Name] on Unsplash

Link to photographer's Unsplash profile when possible.

Download Tracking

  • Call /photos/:id/download before allowing users to download
  • This is required by Unsplash API Guidelines
  • Don't use it for just displaying images (that's tracked automatically via hotlinking)

Hotlinking

  • You can hotlink images directly from images.unsplash.com
  • These don't count against rate limits
  • Views are tracked automatically
  • Always keep the ixid parameter in URLs

Caching

  • Public endpoints (search, photos) are cacheable
  • Consider caching search results client-side to reduce API calls

Quick Reference

# Store key
export UNSPLASH_ACCESS_KEY="your_key"

# Search
curl "https://api.unsplash.com/search/photos?query=ocean&per_page=5" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

# Random photo
curl "https://api.unsplash.com/photos/random?query=mountains" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

# Get photo
curl "https://api.unsplash.com/photos/PHOTO_ID" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

# Track download (required when downloading!)
curl "https://api.unsplash.com/photos/PHOTO_ID/download" \
  -H "Authorization: Client-ID ${UNSPLASH_ACCESS_KEY}"

Notes

  • Base URL: https://api.unsplash.com
  • All responses are JSON
  • Pagination via page and per_page parameters
  • Link headers provide first/prev/next/last page URLs
  • Image requests to images.unsplash.com don't count against rate limits
  • Keep the ixid parameter when using/manipulating image URLs
  • For production use, apply for increased rate limits in your dashboard

Common Filters

Colors

black_and_white, black, white, yellow, orange, red, purple, magenta, green, teal, blue

Orientations

landscape, portrait, squarish

Sort Options

  • Photos: latest, oldest, popular
  • Search: relevant, latest

Error Handling

  • 401 Unauthorized: Invalid or missing access key
  • 403 Forbidden: Rate limit exceeded or forbidden action
  • 404 Not Found: Photo/user/collection doesn't exist

Check X-Ratelimit-Remaining header to monitor your rate limit status.

04 同仓库更多 Skills

javimosch
javimosch/open-claw-skills

crowd-prompting

A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.

★ 0
javimosch
javimosch/open-claw-skills

ceaser

Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).

★ 0
javimosch
javimosch/open-claw-skills

ceaser-send

Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.

★ 0
javimosch
javimosch/open-claw-skills

dilemm-ai

Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).

★ 0
javimosch
javimosch/open-claw-skills

moldium

Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.

★ 0
javimosch
javimosch/open-claw-skills

arxiv-paper-reviews

Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.

★ 0