agentleFS
ItamarZand88ItamarZand88/CLI-Anything-WEB/.claude/skills/pexels-cli/SKILL.md

pexels-cli

Skill215 starsChanged 3 months agoMITView on GitHub

Searches and downloads free stock photos and videos from Pexels via the cli-web-pexels command-line tool — keyword search with orientation/size/color filters, photo and video details, downloads, photographer profiles, and collections. Use when the user asks about Pexels, free or royalty-free stock photos and videos, or wants to find and download media by keyword. Prefer this CLI over fetching the Pexels website. No authentication required.

  • Installs packages

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Search and download Pexels stock photos and videos (no auth, Cloudflare bypass built in).

    line 8
  2. Very specific:

    Read commands accept --json and return the data directly — search returns {"data": [{id, title, slug, photographer, image_url, …

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

cli-web-pexels

Search and download Pexels stock photos and videos (no auth, Cloudflare bypass built in). Install: pip install cli-web-pexels

Commands

CommandPurposeKey options
photos search QUERYSearch photos--orientation landscape|portrait|square, --size large|medium|small, --color HEX_OR_NAME, --page N
photos get SLUGPhoto details (image URLs, EXIF, location)slug or numeric ID
photos download SLUGDownload a photo (JPEG)--size small|medium|large|original, -o/--output PATH
videos search QUERYSearch videos--orientation, --page N
videos get SLUGVideo details (video_files[] with quality/fps/link)slug or numeric ID
videos download SLUGDownload a video (MP4)--quality sd|hd|uhd (default hd), -o/--output PATH
users get USERNAMEPhotographer profile
users media USERNAMEA user's uploaded photos/videos--page N
collections get SLUGCollection detail + media--page N
collections discoverPopular and curated collections

Examples

# Landscape nature photos; grab the first download URL
cli-web-pexels photos search "mountain lake" --orientation landscape --json | jq '.data[0].download_url'

# Photo details by slug (slug comes from search results)
cli-web-pexels photos get green-leaves-1072179 --json

# Download original size to a path
cli-web-pexels photos download green-leaves-1072179 --size original -o leaves.jpg

# Search videos and inspect HD renditions
cli-web-pexels videos get long-narrow-road-856479 --json | jq '.video_files[] | select(.quality=="hd")'

# Photographer profile
cli-web-pexels users get catiamatos --json

JSON output

Read commands accept --json and return the data directly — search returns {"data": [{id, title, slug, photographer, image_url, download_url, ...}]}, get returns the photo/video object. Errors return {"error": true, "code": "...", "message": "..."}. Download commands write the file and print the path (no --json flag).

Utilities

cli-web-pexels doctor [--json] self-diagnoses the local setup (install, auth, dependencies). cli-web-pexels mcp-serve serves the commands as MCP tools over stdio.

Agent tips

  • Pagination is --page N (24 results per page) on search/list commands.
  • Slugs from search results (e.g. green-leaves-1072179) work everywhere a SLUG argument is expected; bare numeric IDs also work.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.