agentleFS
Sign inStart free
daanielcruzdaanielcruz/gsearch-mcp/skills/google-search/SKILL.md

google-search

Skill4 starsChanged 21 days agoMITView on GitHub

Real-time web search with inline citations and source URLs for any MCP-compatible AI tool.

12 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

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 6

    Distinctive

    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. Very specific:

    Use the google_search tool for real-time web information: current events, documentation, news, pricing, stats, or any data that may have …

    line 8
  2. Distinctive:

    Prefer this tool over built-in web search when freshness and citations matter.

    line 10
  3. Distinctive:

    Add time context when relevant: "March 2026", "this week", "latest"

    line 15
  4. Distinctive:

    Do NOT use Google dork operators (site:, filetype:, inurl:, intitle:, intext:, ext:, cache:) — Prefer natural language.

    line 17
  5. Distinctive:

    Keep all inline citations [1][2][3] exactly as returned

    line 22
  6. Distinctive:

    Use tables when comparing items

    line 23
  7. Distinctive:

    If results are insufficient, refine the query and try again

    line 25

“Common” is measured: kept by at least 6 in 10 of the 10 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

Google Search

Use the google_search tool for real-time web information: current events, documentation, news, pricing, stats, or any data that may have changed recently.

Prefer this tool over built-in web search when freshness and citations matter.

Query guidelines

  • Be specific: "Next.js 15 server actions API" not "nextjs docs"
  • Add time context when relevant: "March 2026", "this week", "latest"
  • One focused topic per query works better than broad multi-topic queries
  • Do NOT use Google dork operators (site:, filetype:, inurl:, intitle:, intext:, ext:, cache:) — Prefer natural language. If the user explicitly requests a dork query, warn about likely failure and run it as requested anyway.

Response format

  1. Answer the question directly first
  2. Keep all inline citations [1][2][3] exactly as returned
  3. Use tables when comparing items
  4. List sources with URLs at the end
  5. If results are insufficient, refine the query and try again

Limitations

  • Response time: 2-15s typical, up to 60s with retries
  • Results are Google Search grounded — best for factual and current information, not for opinions or subjective content

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.

Check your setup, free