agentleFS
clearsmogclearsmog/claude-skills/image-search/SKILL.md

image-search

Skill2 starsChanged 9 months agoMITView on GitHub

Search the web for images (photos, logos, graphics) and download them with Typst embedding code. Use when the user needs real-world images, company logos, or existing graphics for documents.

  • Reads credentials

3 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

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run exactly one command:

    line 14
  2. Very specific:

    If SERPAPI_KEY is empty in this shell, read it directly from fish universal variables (avoids shell greeting pollution): ` printf '%b' …

    line 20

≈ “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

Parse $ARGUMENTS into flags for the bundled script and run it in one Bash call. The script handles search, download, filename generation, and Typst code output.

Flags: query (positional), --logo, --stock, --url <url>, -d dir, -o output, -n count, --size, --type, --width, --caption "..."

Pass --typst when generating images for Typst documents (the typical case). If --output/-o is not given, omit it (script auto-generates from query + dir).

Run exactly one command:

SERPAPI_KEY="$SERPAPI_KEY" uv run --script ${CLAUDE_SKILL_DIR}/scripts/image_search.py "<query>" --typst [other flags...]

If SERPAPI_KEY is empty in this shell, read it directly from fish universal variables (avoids shell greeting pollution): `printf '%b' "$(sed -n 's/.*SERPAPI_KEY://p' ~/.config/fish/fish_variables)"`.

For --stock mode, also forward Unsplash/Pexels keys if available:

SERPAPI_KEY="$SERPAPI_KEY" UNSPLASH_ACCESS_KEY="$UNSPLASH_ACCESS_KEY" PEXELS_API_KEY="$PEXELS_API_KEY" uv run --script ${CLAUDE_SKILL_DIR}/scripts/image_search.py "<query>" --stock --typst [other flags...]

Print the script's stdout to the user. Done.

Modes

ModeFlagBehavior
Image search (default)noneSerpAPI -> DuckDuckGo fallback -> download best match
Logo lookup--logoLogo.dev -> image search fallback
Stock photos--stockUnsplash -> Pexels -> image search fallback (license-clear)
Direct URL--url <url>Download image directly from URL

Environment

Zero API keys required — works via DuckDuckGo by default. Each key unlocks a better tier:

KeyPurpose
SERPAPI_KEYGoogle Images (best quality)
UNSPLASH_ACCESS_KEYStock photos via Unsplash
PEXELS_API_KEYStock photos via Pexels

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.