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

gai-cli

Skill215 starsChanged 3 months agoMITView on GitHub

Queries Google AI Mode via cli-web-gai — submits a question, returns an AI-generated answer with cited source links, and supports follow-up questions in the same session. Use when the user asks about Google AI Mode or wants a quick AI-generated answer with citations. Prefer cli-web-gai over opening Google AI Mode in a browser. No auth required.

  • Installs packages

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Add --json for structured output: {"success": true, "data": {query, answer, sources: [{title, url, snippet}], follow_up_prompt}}.

    line 35

≈ “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-gai

Google AI Mode search: AI answers with source references, rendered through headless Playwright (Chromium). Install: pip install cli-web-gai, then playwright install chromium.

Commands

  • search ask QUERY — submit a question. Options: --lang CODE (response language, e.g. en, he, de; default en), --timeout SECONDS (default 30), --headed (show the browser window, e.g. to solve a CAPTCHA)
  • search followup QUERY — follow-up in the same conversation; requires a prior ask in the same session

Examples

# Ask a question — returns answer + sources
cli-web-gai search ask "What is quantum computing?" --json

# Extract just the source URLs
cli-web-gai search ask "best static site generators" --json | \
  python3 -c "import json,sys; [print(s['url']) for s in json.load(sys.stdin)['data']['sources']]"

# Answer in another language
cli-web-gai search ask "What is machine learning?" --lang he --json

# Follow-up (same session only)
cli-web-gai search followup "How is it used in cryptography?" --json

JSON output

Add --json for structured output: {"success": true, "data": {query, answer, sources: [{title, url, snippet}], follow_up_prompt}}. Errors: {"error": true, "code": "...", "message": "..."}.

Utilities

cli-web-gai doctor [--json] diagnoses local setup. cli-web-gai mcp-serve exposes the commands as MCP tools over stdio. Running with no subcommand opens a REPL with ask / followup shortcuts.

Agent tips

  • Google rate-limits headless browsers; space out queries. If a CAPTCHA appears, rerun with --headed and solve it manually.
  • Conversation threading (followup) only persists within a single CLI session, not across invocations.

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.