← Back to Skills Marketplace
9555
Downloads
30
Stars
83
Active Installs
1
Versions
Install in OpenClaw
/install gemini-deep-research
Description
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.
Usage Guidance
Install only if you are comfortable using a Gemini API key and sending your research prompts, plus any selected file-search context, to Google. Prefer the GEMINI_API_KEY environment variable over the --api-key argument on shared machines, monitor quota/costs for long-running jobs, and save outputs in a private directory if reports or metadata may contain sensitive information.
Capability Analysis
Type: OpenClaw Skill
Name: gemini-deep-research
Version: 1.0.0
The skill is designed to interact with the Gemini Deep Research API for complex research tasks. It correctly handles the `GEMINI_API_KEY` by reading it from environment variables or CLI arguments and uses it to authenticate with the legitimate Google API endpoint (`generativelanguage.googleapis.com`). The script saves research reports locally to user-specified or default directories, which is a core function. There is no evidence of unauthorized data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts against the OpenClaw agent, or obfuscation. All observed behaviors are aligned with the stated purpose.
Capability Assessment
Purpose & Capability
The SKILL.md and Python script consistently implement a Gemini Deep Research helper: submit a query, optionally attach a Gemini file-search store reference, poll the Gemini endpoint, and return a report.
Instruction Scope
Use is command-driven and examples are explicit; the remote Gemini call, long-running/background research behavior, and API endpoint are documented, though stronger privacy wording for sensitive prompts would help.
Install Mechanism
There is no installer, package hook, or remote bootstrapper; the artifact is a small readable skill plus script. Registry provenance is limited, but that is not matched by suspicious artifact behavior.
Credentials
Requiring GEMINI_API_KEY and making outbound requests to generativelanguage.googleapis.com is proportional to the stated purpose, but users should treat the key as account-bearing and expect API costs/data processing by Google.
Persistence & Privilege
No startup persistence, privilege escalation, credential harvesting, destructive action, or hidden background service was found. The script intentionally writes timestamped markdown and JSON outputs to the selected output directory.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install gemini-deep-research - After installation, invoke the skill by name or use
/gemini-deep-research - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: Complex research tasks via Gemini Deep Research Agent
Metadata
Frequently Asked Questions
What is 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. It is an AI Agent Skill for Claude Code / OpenClaw, with 9555 downloads so far.
How do I install Gemini Deep Research?
Run "/install gemini-deep-research" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Gemini Deep Research free?
Yes, Gemini Deep Research is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Gemini Deep Research support?
Gemini Deep Research is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Gemini Deep Research?
It is built and maintained by arun-8687 (@arun-8687); the current version is v1.0.0.
More Skills