agentleFS
OpenCovenOpenCoven/coven/skills/tinyfish-search/SKILL.md

tinyfish-search

Skill75 starsChanged 4 months agoMITView on GitHub

Run web searches via TinyFish Search API and get structured JSON results (title, snippet, URL) ready for LLM consumption. Use when you need fresh web search results with reliable structure and optional geo/language targeting.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Search the web via the TinyFish Search API.

    line 12
  2. Distinctive:

    Before calling the API, verify the key is present:

    line 18
  3. Distinctive:

    If the key is not set, stop and ask the user to add it.

    line 24
  4. Very specific:

    Use results[] directly — each entry already has everything needed to cite or open the source.

    line 71

≈ “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

TinyFish Search

Search the web via the TinyFish Search API. Returns a JSON array of ranked results with title, snippet, site name, and URL.

Requires: TINYFISH_API_KEY environment variable.

Pre-flight Check (REQUIRED)

Before calling the API, verify the key is present:

[ -n "$TINYFISH_API_KEY" ] && echo "TINYFISH_API_KEY is set" || echo "TINYFISH_API_KEY is NOT set"

If the key is not set, stop and ask the user to add it. Get one at https://agent.tinyfish.ai/api-keys. Do NOT fall back to other search tools.

Basic Search

curl -G "https://api.search.tinyfish.ai" \
  -H "X-API-Key: $TINYFISH_API_KEY" \
  --data-urlencode "query=web automation tools"

Geo / Language Targeting

curl -G "https://api.search.tinyfish.ai" \
  -H "X-API-Key: $TINYFISH_API_KEY" \
  --data-urlencode "query=boulangerie paris" \
  --data-urlencode "location=FR" \
  --data-urlencode "language=fr"

Helper Script

scripts/search.sh <query> [--location CC] [--language LL] wraps the curl call:

scripts/search.sh "top trending openclaw youtube video"
scripts/search.sh "boulangerie paris" --location FR --language fr

Response Shape

{
  "query": "web automation tools",
  "results": [
    {
      "position": 1,
      "site_name": "example.com",
      "title": "Top 10 Web Automation Tools",
      "snippet": "A preview of the page content…",
      "url": "https://example.com/top-automation"
    }
  ],
  "total_results": 1234
}

Use results[] directly — each entry already has everything needed to cite or open the source.

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.