Agent Deep Research

What it does

This skill enables deep research and retrieval-augmented generation (RAG) capabilities within AI agents. It leverages the Google Gemini Interactions API to search files and provide grounded responses, integrating seamlessly with a wide range of agent platforms. The skill utilizes the google-genai Python SDK directly via uv run, eliminating the need for the Gemini CLI.

When to use it

• Complex Research Tasks: When an agent needs to gather information from multiple files and synthesize a comprehensive answer, such as researching competitor strategies or summarizing legal documents.
• File-Based Knowledge Base: To enable agents to access and utilize specific data stored in files, like product documentation or internal reports.
• Code Understanding & Assistance: Help an agent understand and debug code by searching relevant files within a project repository.
• Automated Report Generation: Generate reports based on information extracted from various documents.

Key capabilities

• Google Gemini Interactions API integration
• Retrieval-Augmented Generation (RAG)
• File search functionality
• Compatibility with Claude Code, Amp, Codex, OpenCode, Cursor, Gemini CLI, Pi, and 30+ other agents.
• Direct use of google-genai Python SDK

Example prompts

• "Research the latest trends in sustainable energy and summarize your findings."
• "Find all files related to 'Project Phoenix' and create a brief overview."
• "What are the key differences between these two code snippets, based on available documentation?"

Tips & gotchas

• A Google API key is required for this skill. Ensure you have configured either GEMINI_DEEP_RESEARCH_API_KEY, GOOGLE_API_KEY, or GEMINI_API_KEY environment variable.
• The skill relies on uv; ensure it's installed correctly before attempting to use the skill.