agentsclimarketplace

Pexels media

Skill troykelly/claude-skills/skills/pexels-media

Opinionated GitHub-native development workflow with 28 skills for autonomous, issue-driven software development with Claude Code

Install
npx -y skills add troykelly/claude-skills --skill pexels-media

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 11 stars11 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Source royalty-free images and videos from Pexels API for design, placeholders, or content. Supports search, curated/popular content, collections, multiple resolutions, and ALWAYS creates detailed sidecar metadata files.

SKILL.md

9.1 KB, ~2.6k tokens by cl100k_base, as published. Nobody here has run it

Pexels Media Sourcing

Source high-quality, royalty-free images and videos from Pexels for design work, placeholders, or content creation.

Prerequisites

This skill requires the PEXELS_API_KEY environment variable to be set.

# Check if API key is available
echo $PEXELS_API_KEY

If not set, obtain a free API key from Pexels API.

API Base URLs

  • Photos: https://api.pexels.com/v1/
  • Videos: https://api.pexels.com/videos/

Authentication

All requests require the Authorization header:

curl -H "Authorization: $PEXELS_API_KEY" "https://api.pexels.com/v1/search?query=nature"

Photo Endpoints

Search Photos

curl -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/v1/search?query=QUERY&orientation=ORIENTATION&size=SIZE&color=COLOR&locale=LOCALE&page=PAGE&per_page=PER_PAGE"

Parameters:

ParameterRequiredValues
queryYesSearch term
orientationNolandscape, portrait, square
sizeNolarge (24MP), medium (12MP), small (4MP)
colorNored, orange, yellow, green, turquoise, blue, violet, pink, brown, black, gray, white, or hex code (e.g., #ffffff)
localeNoen-US, pt-BR, es-ES, de-DE, fr-FR, ja-JP, zh-CN, ko-KR, etc.
pageNoPage number (default: 1)
per_pageNoResults per page (default: 15, max: 80)

Curated Photos

Trending photos curated by the Pexels team (updated hourly):

curl -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/v1/curated?page=1&per_page=15"

Get Photo by ID

curl -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/v1/photos/PHOTO_ID"

Video Endpoints

Search Videos

curl -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/videos/search?query=QUERY&orientation=ORIENTATION&size=SIZE&min_width=MIN_WIDTH&min_height=MIN_HEIGHT&min_duration=MIN_DURATION&max_duration=MAX_DURATION&page=PAGE&per_page=PER_PAGE"

Additional Video Parameters:

ParameterDescription
min_widthMinimum width in pixels
min_heightMinimum height in pixels
min_durationMinimum duration in seconds
max_durationMaximum duration in seconds

Popular Videos

curl -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/videos/popular?min_width=1920&min_duration=10&max_duration=60&page=1&per_page=15"

Get Video by ID

curl -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/videos/videos/VIDEO_ID"

Collections

Featured Collections

curl -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/v1/collections/featured?page=1&per_page=15"

Collection Media

curl -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/v1/collections/COLLECTION_ID?type=TYPE&page=1&per_page=15"

Type parameter: photos, videos, or omit for both.

Photo Sizes Available

When downloading photos, these sizes are available in the API response:

KeyDescription
originalOriginal size uploaded by photographer
large2xWidth 940px, height doubled
largeWidth 940px
mediumHeight 350px
smallHeight 130px
portraitWidth 800px, height 1200px
landscapeWidth 1200px, height 627px
tinyWidth 280px, height 200px

Video Files Available

Videos include multiple quality files in the response:

QualityTypical Resolution
hd1280x720
sd640x360
hlsAdaptive streaming
VariousFull HD, 4K when available

MANDATORY: Sidecar Metadata Files

CRITICAL REQUIREMENT: For EVERY downloaded file, you MUST create a sidecar metadata file.

Sidecar File Naming

For a downloaded file mountain-sunset.jpg, create mountain-sunset.jpg.meta.json.

Photo Sidecar Content

{
  "source": "pexels",
  "type": "photo",
  "id": 12345,
  "url": "https://www.pexels.com/photo/12345/",
  "download_url": "https://images.pexels.com/photos/12345/pexels-photo-12345.jpeg",
  "downloaded_size": "large",
  "width": 1920,
  "height": 1080,
  "photographer": "John Doe",
  "photographer_url": "https://www.pexels.com/@johndoe",
  "photographer_id": 67890,
  "avg_color": "#7E5835",
  "alt": "Brown mountain during sunset",
  "license": "Pexels License - Free for personal and commercial use",
  "attribution": "Photo by John Doe on Pexels",
  "attribution_html": "<a href=\"https://www.pexels.com/photo/12345/\">Photo</a> by <a href=\"https://www.pexels.com/@johndoe\">John Doe</a> on <a href=\"https://www.pexels.com\">Pexels</a>",
  "downloaded_at": "2025-12-02T14:30:00Z",
  "api_response": {
    // Full original API response for this photo
  }
}

Video Sidecar Content

{
  "source": "pexels",
  "type": "video",
  "id": 12345,
  "url": "https://www.pexels.com/video/12345/",
  "download_url": "https://videos.pexels.com/video-files/12345/...",
  "downloaded_quality": "hd",
  "width": 1920,
  "height": 1080,
  "duration": 30,
  "user": {
    "id": 67890,
    "name": "John Doe",
    "url": "https://www.pexels.com/@johndoe"
  },
  "video_files": [
    {
      "id": 1,
      "quality": "hd",
      "file_type": "video/mp4",
      "width": 1920,
      "height": 1080,
      "link": "https://..."
    }
  ],
  "video_pictures": [
    {
      "id": 1,
      "picture": "https://...",
      "nr": 0
    }
  ],
  "license": "Pexels License - Free for personal and commercial use",
  "attribution": "Video by John Doe on Pexels",
  "downloaded_at": "2025-12-02T14:30:00Z",
  "api_response": {
    // Full original API response for this video
  }
}

Download Workflow

1. Search and Select

# Search for photos
RESPONSE=$(curl -s -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/v1/search?query=office+workspace&orientation=landscape&per_page=5")

# Parse and display results
echo "$RESPONSE" | jq '.photos[] | {id, photographer, alt, url: .src.large}'

2. Download with Sidecar

# Get photo details
PHOTO_ID=12345
PHOTO_DATA=$(curl -s -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/v1/photos/$PHOTO_ID")

# Extract download URL (choose size)
DOWNLOAD_URL=$(echo "$PHOTO_DATA" | jq -r '.src.large')
FILENAME="pexels-$PHOTO_ID-large.jpg"

# Download the image
curl -L -o "$FILENAME" "$DOWNLOAD_URL"

# Create sidecar metadata (MANDATORY)
echo "$PHOTO_DATA" | jq '{
  source: "pexels",
  type: "photo",
  id: .id,
  url: .url,
  download_url: .src.large,
  downloaded_size: "large",
  width: .width,
  height: .height,
  photographer: .photographer,
  photographer_url: .photographer_url,
  photographer_id: .photographer_id,
  avg_color: .avg_color,
  alt: .alt,
  license: "Pexels License - Free for personal and commercial use",
  attribution: ("Photo by " + .photographer + " on Pexels"),
  downloaded_at: (now | todate),
  api_response: .
}' > "$FILENAME.meta.json"

Rate Limits

  • Default: 200 requests/hour, 20,000 requests/month
  • Check response headers for current limits:
    • X-Ratelimit-Limit
    • X-Ratelimit-Remaining
    • X-Ratelimit-Reset

Attribution Best Practices

While not legally required by the Pexels license, attribution is encouraged:

  • Minimal: "Photo by [Photographer] on Pexels"
  • With link: "Photo by Photographer on Pexels"
  • HTML: Use the attribution_html from the sidecar file

Example Use Cases

Placeholder Images for UI Design

# Get 5 abstract/minimal images for placeholders
curl -s -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/v1/search?query=minimal+abstract&orientation=square&size=small&per_page=5"

Hero Background Video

# Find short, wide landscape videos
curl -s -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/videos/search?query=nature+aerial&orientation=landscape&min_width=1920&min_duration=5&max_duration=15"

Product Photography Backgrounds

# Search for clean, neutral backgrounds
curl -s -H "Authorization: $PEXELS_API_KEY" \
  "https://api.pexels.com/v1/search?query=white+background+texture&color=white&size=large"

Checklist

When using this skill:

  • Verify PEXELS_API_KEY is set
  • Choose appropriate endpoint (search, curated, popular, collection)
  • Apply relevant filters (orientation, size, color, duration)
  • Select appropriate resolution for use case
  • Download file to appropriate location
  • CREATE SIDECAR METADATA FILE (mandatory)
  • Consider attribution in final use

References

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most media documents skills give in ~2.6k tokens

Counted across 157 of the 158 authors here whose files we hold, read 2026-08-07

  • Provide posting time recommendationsin 7 of 157, across 5 files
  • Track metrics over time to identify trendsin 6 of 157, across 2 files
  • Read marketing context file before startingin 6 of 157, across 5 files
  • Choose platforms based on audience presencein 6 of 157, across 4 files
  • Adapt tone for each platformin 6 of 157, across 4 files
  • Ensure data completeness before analysisin 5 of 157, across 1 file
  • Compare metrics within same time periodsin 5 of 157, across 1 file
  • Account for platform-specific benchmarksin 5 of 157, across 1 file
  • Separate organic and paid metricsin 5 of 157, across 1 file
  • Include context when interpreting resultsin 5 of 157, across 1 file
  • Keep tweets under 280 charactersin 5 of 157, across 3 files
  • Download top-K results with an attribution sidecarin 5 of 157, across 2 files

Said here and by no other author read

  • Include the Authorization header in all requests
  • Choose appropriate endpoint for media retrieval
  • Apply relevant filters like orientation and size
  • Select appropriate resolution for the use case
  • Create a sidecar metadata file for every download
  • Include full original API response in sidecar

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,984. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.