agentleFS
claude-worldclaude-world/claude-agent/.claude/skills/gif-search/SKILL.md

gif-search

Skill5 starsChanged 8 months agoMITView on GitHub

Search and download GIFs from Giphy and Tenor using gifgrep CLI or direct API calls. Use when user says "find a gif of", "search for a funny gif", "get me a reaction gif", "download a gif", or any GIF search/download request.

  • Reads credentials
  • Installs packages

17 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search and download GIFs from Giphy or Tenor.

    line 21
  2. Very specific:

    Check if gifgrep is installed first: which gifgrep

    line 107
  3. Distinctive:

    If gifgrep not installed, fall back to curl + Giphy API

    line 108
  4. Very specific:

    If neither gifgrep nor GIPHY_API_KEY/TENOR_API_KEY is set, show install/setup instructions

    line 109
  5. Very specific:

    Default content rating: g (general audiences) unless user explicitly requests otherwise

    line 110
  6. Very specific:

    Default download directory: ~/Downloads/

    line 111
  7. Distinctive:

    When downloading, report the saved file path

    line 114
  8. Distinctive:

    Never cache or store API keys — read from environment only

    line 115

“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “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

GIF Search

Search and download GIFs from Giphy or Tenor.

Prerequisites

Install gifgrep:

brew install steipete/tap/gifgrep
# GitHub: https://github.com/steipete/gifgrep

Or use curl with Giphy/Tenor APIs directly (no extra install, requires API key):

# Giphy free API key: register at https://developers.giphy.com/
# Tenor free API key: register at https://developers.google.com/tenor/guides/quickstart
export GIPHY_API_KEY=your_key_here
export TENOR_API_KEY=your_key_here

Commands

gifgrep (recommended)

gifgrep search "dancing cat"              # Search and preview
gifgrep search "excited" --limit 5        # Limit results
gifgrep download "celebration" --out ~/Downloads/  # Search and download
gifgrep trending                           # Show trending GIFs

Giphy API (curl fallback)

# Search GIFs
curl -s "https://api.giphy.com/v1/gifs/search?api_key=$GIPHY_API_KEY&q=QUERY&limit=5&rating=g" \
  | jq '.data[].url'

# Get direct GIF URL
curl -s "https://api.giphy.com/v1/gifs/search?api_key=$GIPHY_API_KEY&q=QUERY&limit=1&rating=g" \
  | jq -r '.data[0].images.original.url'

# Download first result
GIF_URL=$(curl -s "https://api.giphy.com/v1/gifs/search?api_key=$GIPHY_API_KEY&q=QUERY&limit=1&rating=g" \
  | jq -r '.data[0].images.original.url') && curl -s -L "$GIF_URL" -o ~/Downloads/result.gif

Tenor API (curl fallback)

# Search
curl -s "https://tenor.googleapis.com/v2/search?q=QUERY&key=$TENOR_API_KEY&limit=5" \
  | jq '.results[].url'

# Get media URL
curl -s "https://tenor.googleapis.com/v2/search?q=QUERY&key=$TENOR_API_KEY&limit=1" \
  | jq -r '.results[0].media_formats.gif.url'

Usage Examples

"Find a gif of a happy dog"

gifgrep search "happy dog" --limit 5 2>/dev/null || \
  curl -s "https://api.giphy.com/v1/gifs/search?api_key=$GIPHY_API_KEY&q=happy+dog&limit=5&rating=g" \
  | jq '.data[] | {title: .title, url: .url}'

"Download a celebration gif"

gifgrep download "celebration" --out ~/Downloads/ 2>/dev/null || {
  GIF_URL=$(curl -s "https://api.giphy.com/v1/gifs/search?api_key=$GIPHY_API_KEY&q=celebration&limit=1&rating=g" \
    | jq -r '.data[0].images.original.url')
  curl -s -L "$GIF_URL" -o ~/Downloads/celebration.gif
  echo "Downloaded: ~/Downloads/celebration.gif"
}

"Show trending GIFs"

gifgrep trending 2>/dev/null || \
  curl -s "https://api.giphy.com/v1/gifs/trending?api_key=$GIPHY_API_KEY&limit=10&rating=g" \
  | jq '.data[].title'

"Convert gif to mp4 (smaller file)"

ffmpeg -y -i input.gif -movflags faststart -pix_fmt yuv420p -vf "scale=trunc(iw/2)*2:trunc(ih/2)*2" output.mp4

Rules

  • Check if gifgrep is installed first: which gifgrep
  • If gifgrep not installed, fall back to curl + Giphy API
  • If neither gifgrep nor GIPHY_API_KEY/TENOR_API_KEY is set, show install/setup instructions
  • Default content rating: g (general audiences) unless user explicitly requests otherwise
  • Default download directory: ~/Downloads/
  • Show GIF URLs in output so user can preview in browser
  • Limit search results to 5 by default to avoid overwhelming output
  • When downloading, report the saved file path
  • Never cache or store API keys — read from environment only

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.