agent-deep-research

---
name: deep-research
description: "Async deep research via Gemini Interactions API (no Gemini CLI dependency). RAG-ground queries on local files (--context), preview costs (--dry-run), structured JSON output, adaptive polling. Universal skill for 30+ AI agents including Claude Code, Amp, Codex, and Gemini CLI."
license: MIT
compatibility: "Requires uv and one of GOOGLE_API_KEY / GEMINI_API_KEY / GEMINI_DEEP_RESEARCH_API_KEY. Optional env vars for model config: GEMINI_DEEP_RESEARCH_AGENT, GEMINI_DEEP_RESEARCH_MODEL, GEMINI_MODEL. Network access to Google Gemini API. --context uploads local files to ephemeral stores (auto-deleted)."
allowed-tools: "Bash(uv:*) Bash(python3:*) Read"
metadata:
  version: "2.1.2"
  author: "24601"
  clawdbot:
    emoji: "🔬"
    category: "research"
    primaryEnv: "GOOGLE_API_KEY"
    homepage: "https://github.com/24601/agent-deep-research"
    requires:
      bins:
        - "uv"
      env:
        - "GOOGLE_API_KEY"
        - "GEMINI_API_KEY"
        - "GEMINI_DEEP_RESEARCH_API_KEY"
        - "GEMINI_DEEP_RESEARCH_AGENT"
        - "GEMINI_DEEP_RESEARCH_MODEL"
        - "GEMINI_MODEL"
    install:
      - kind: "uv"
        label: "uv (Python package runner)"
        package: "uv"
    config:
      requiredEnv:
        - "GOOGLE_API_KEY"
        - "GEMINI_API_KEY"
        - "GEMINI_DEEP_RESEARCH_API_KEY"
      example: "export GOOGLE_API_KEY=your-key-from-aistudio.google.com"
---

# Deep Research Skill

Perform deep research powered by Google Gemini's deep research agent. Upload documents to file search stores for RAG-grounded answers. Manage research sessions with persistent workspace state.

## For AI Agents

Get a full capabilities manifest, decision trees, and output contracts:

```bash
uv run {baseDir}/scripts/onboard.py --agent
```

See [AGENTS.md]({baseDir}/AGENTS.md) for the complete structured briefing.

| Command | What It Does |
|---------|-------------|
| `uv run {baseDir}/scripts/research.py start "question"` | Launch de