LaunchKit · 2026
Back to Skills

agent-deep-research

Autonomous deep research powered by Google Gemini.

3
2.0k downloads
by @24601

Setup & Installation

openclaw skills install @24601/agent-deep-research

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install agent-deep-research

Version History

v2.1.3Feb 25, 2026 - Version note by skill developer:

Fix: nested YAML metadata for Codex compatibility (was JSON string which Codex rejects). All YAML values with colons are now properly quoted.

What This Skill Does

Runs deep research queries through Google Gemini's research API without requiring the Gemini CLI. Supports grounding queries in local files via RAG by uploading them to ephemeral file search stores. Works as a universal skill across Claude Code, Amp, Codex, and Gemini CLI.

Calls the Gemini API directly via uv, so it works in any environment without installing the Gemini CLI or managing Python virtual environments.

When to use it

  • Researching a library or framework before adopting it in a project
  • Answering architecture questions grounded in local source files
  • Generating a security audit report from uploaded project documentation
  • Previewing API costs before running an expensive research task
  • Running async research queries from CI pipelines or agent workflows

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Analyze the authentication architecture of my codebase

AGENT
  1. 1Run research.py start with --context ./src and --dry-run to preview upload costs and file list
  2. 2Start grounded research, uploading source files to an ephemeral file search store
  3. 3Poll for completion using adaptive intervals tuned to past research history
  4. 4Save the full report, metadata, and source citations to a structured output directory
  5. 5Return a compact JSON summary to the agent with the report path and duration
OUTPUT

A directory containing report.md, metadata.json, sources.json, and interaction.json, with a compact JSON summary printed to stdout

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

One of GOOGLE_API_KEY, GEMINI_API_KEY, or GEMINI_DEEP_RESEARCH_API_KEY environment variable