Gemini Web Search
Use Gemini CLI (@google/gemini-cli) to do web search / fact-finding and return a sourced summary. Use when the user asks “why did X happen today”, “what’s the latest news”, “search…
fengjiajie
@fengjiajie
What This Skill Does
Uses the Gemini CLI to perform web searches and return a concise, sourced summary with key facts, catalysts, and links. Formulates tight queries for financial data, news, or general fact-finding, and includes quality control steps to prioritize reputable sources.
Replaces manual web searching and note-taking by automating fact-finding with source attribution and quality checks.
When to Use It
- Find why a specific stock moved today with exact percentage and dollar change
- Get the latest news on a company or event with reputable source links
- Search the web for a fact or answer that requires up-to-date information
- Collect multiple reputable sources on a topic and summarize them
- Verify or cross-check a financial claim using Reuters, SEC filings, or company IR
Install
$ openclaw skills install @fengjiajie/gemini-web-searchGemini Web Search
Use Gemini CLI to search the web and produce a concise, sourced answer.
Quick workflow
- Formulate a tight query
- Include: entity + ticker/name + date/time window + what you need (%, $, cause, quotes, links)
- Example:
PayPal (PYPL) fell Feb 4 2026: % change, $ change, main catalyst(s), 3 sources
- Run Gemini CLI with a TTY and long timeout Gemini CLI can hang or be slow without a pseudo-TTY.
Preferred (OpenClaw tool call):
- Use
functions.execwithpty: true - Use
timeout300–600s (longer for heavy searches) - Use
yieldMs~10000 thenprocess.polluntil completion
Command template:
~/.npm-global/bin/gemini -p "<prompt>"
If pty:true still behaves poorly, use a pseudo-tty wrapper:
script -q -c "~/.npm-global/bin/gemini -p \"<prompt>\"" /dev/null
- Extract the answer in a structured way Return:
- The key numeric facts (e.g., % move, $ move, close/intraday)
- 2–4 bullets of the main catalyst(s)
- Links (always)
- Quality control (mandatory)
- Prefer: company IR/SEC filing, Reuters, Bloomberg, WSJ/FT, CNBC, reputable outlets.
- Avoid relying on low-quality finance blogs/SEO sites.
- If sources conflict or look unreliable: say so and ask user for a screenshot/link, or re-run with a stricter prompt.
Prompts that work well
-
Fast triage:
Search the web: <topic>. Give 3 bullets + 2 reputable links. -
Market move:
Search the web: Why did <TICKER> move today (<date>)? Provide exact % and $ move (close + intraday if available) and the main catalyst(s). Cite sources with links. -
Force better sources:
Search the web and prioritize Reuters/company IR/SEC filing. If you cannot find them, say so. Topic: <...>. Provide links.
Failure modes & fixes
-
Gemini prints “I will search…” then stalls
- Wait longer (it can be slow).
- Ensure TTY: run with
pty:trueorscript -q -c ... /dev/null.
-
Output has suspicious claims (e.g., odd CEO news)
- Re-run with: “use Reuters/company IR/SEC filing only; otherwise say unknown”.
- Cross-check with at least 2 independent reputable sources.
-
Need numbers but sources don’t show them
- Ask user for the quote/screenshot from their market data app and reconcile.
Local setup notes
- Gemini CLI binary:
~/.npm-global/bin/gemini - Auth: already completed by Jiajie (should work without re-login)
Top skills in this category
Multi Search Engine
@gpyangyoujunMulti search engine integration with 16 engines (7 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and Wolfra...
Agent Browser
@matrixyHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
Openai Whisper
@steipeteLocal speech-to-text with the Whisper CLI (no API key).
Tavily Search
@jacky1n7Search the public web through Tavily and return structured results with URLs and snippets. Use when an agent needs current information, source discovery, link lookup, news or finance search, or a fallback for unavailable built-in web search. Do not use for private or authenticated pages.
Baidu web search
@ide-reaSearch the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.