gemini-deep-research
Perform complex, long-running research tasks using Gemini Deep Research Agent. Use when asked to research topics requiring multi-source synthesis, competitive analysis, market research, or comprehensive technical investigations that benefit from systematic web search and analysis.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/arun-8687/gemini-deep-researchWhat This Skill Does
The gemini-deep-research skill leverages the Gemini Deep Research Agent to execute complex, multi-step investigative tasks that standard LLM calls cannot handle. Unlike simple chat queries, this tool performs iterative web searching, decomposes complex queries into sub-questions, and synthesizes data from multiple sources into a professional-grade report. It is designed for deep-dive technical investigations, competitive analysis, and market research where exhaustive information gathering is required. The agent autonomously navigates through web results, verifying findings and structuring them according to your specified requirements.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/arun-8687/gemini-deep-research
Prerequisites:
- A valid
GEMINI_API_KEYobtained from Google AI Studio. - Note: This skill requires a direct API key and is incompatible with Antigravity OAuth tokens. Ensure your environment variables are configured correctly to point to this key.
Use Cases
This skill is ideal for:
- Competitive Intelligence: Comparing products, pricing, and market positioning of rival companies.
- Technical Documentation: Gathering historical context or architecture details on complex technologies like TPU design or distributed systems.
- Financial Analysis: Contrasting internal fiscal data against real-time public market news and industry shifts.
- Synthesis Tasks: Combining fragmented web sources into unified, structured markdown reports with executive summaries.
Example Prompts
- "Perform a deep research investigation into the impact of the latest AI regulations on European cloud computing providers, structure the output as an executive summary with a table of key legislative changes."
- "Research the history and evolution of transformer architecture, including key academic papers and their subsequent industry applications, saving the output as a technical report."
- "Conduct a comparative analysis of the current EV battery market, focusing on cost-per-kWh, supply chain bottlenecks for lithium and cobalt, and the competitive landscape for major manufacturers."
Tips & Limitations
- Timeframe: Since research tasks can take anywhere from several minutes to hours, utilize the
--streamflag to monitor progress in real-time. - Cost: Be aware that deep research consumes significantly more token capacity than standard prompts. Monitor your API usage in Google AI Studio to manage potential costs.
- Output: Every run generates two files: a
.mdmarkdown report for readability and a.jsonmetadata file for programmatic integration. - Accuracy: Always review critical data, as the agent relies on web-sourced content which may vary in reliability.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-arun-8687-gemini-deep-research": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, external-api
Related Skills
deepwiki
Query the DeepWiki MCP server for GitHub repository documentation, wiki structure, and AI-powered questions.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
tavily
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.