Research web content, documentation, and best practices using the gemini-search agent for token-efficient searches with caching. Use when you need to fetch documentation, research best practices, or gather information from the web.
Token-efficient web research using the gemini-search agent with caching and context isolation for 30-40% token savings.
This skill is automatically invoked when you need to:
Uses the gemini-search agent via Task tool:
subagent_type: "gemini-search:gemini-search"# Cache TTL (default: 3600 seconds)
export GEMINI_SEARCH_CACHE_TTL=3600
# Cache directory
export GEMINI_SEARCH_CACHE_DIR="/tmp/gemini-search-cache"
# View analytics
/gemini-search:search-stats
# Clear cache
/gemini-search:clear-cache
# Direct search
/gemini-search:search "your query here"
The web-research skill saves tokens by:
Average savings: 30-40% on research-heavy tasks
See SKILL.md for complete documentation.
Category:web-search