{
  "schema": "https://ai-atoms.com/schemas/skill-v1.json",
  "type": "skill",
  "id": "skill/deep-research",
  "version": "1.0.0",
  "name": "Deep Research",
  "description": "Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 ...",
  "system_prompt_fragment": "# Gemini Deep Research Skill\n\nRun autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.\n\n## When to Use This Skill\n\nUse this skill when:\n- Performing market analysis\n- Conducting competitive landscaping\n- Creating literature reviews\n- Doing technical research\n- Performing due diligence\n- Need detailed, cited research reports\n\n## Requirements\n\n- Python 3.8+\n- httpx: `pip install -r requirements.txt`\n- GEMINI_API_KEY environment variable\n\n## Setup\n\n1. Get a Gemini API key from [Google AI Studio](https://aistudio.google.com/)\n2. Set the environment variable:\n   ```bash\n   export GEMINI_API_KEY=your-api-key-here\n   ```\n   Or create a `.env` file in the skill directory.\n\n## Usage\n\n### Start a research task\n```bash\npython3 scripts/research.py --query \"Research the history of Kubernetes\"\n```\n\n### With structured output format\n```bash\npython3 scripts/research.py --query \"Compare Python web frameworks\" \\\n  --format \"1. Executive Summary\\n2. Comparison Table\\n3. Recommendations\"\n```\n\n### Stream progress in real-time\n```bash\npython3 scripts/research.py --query \"Analyze EV battery market\" --stream\n```\n\n### Start without waiting\n```bash\npython3 scripts/research.py --query \"Research topic\" --no-wait\n```\n\n### Check status of running research\n```bash\npython3 scripts/research.py --status <interaction_id>\n```\n\n### Wait for completion\n```bash\npython3 scripts/research.py --wait <interaction_id>\n```\n\n### Continue from previous research\n```bash\npython3 scripts/research.py --query \"Elaborate on point 2\" --continue <interaction_id>\n```\n\n### List recent research\n```bash\npython3 scripts/research.py --list\n```\n\n## Output Formats\n\n- **Default**: Human-readable markdown report\n- **JSON** (`--json`): Structured data for programmatic use\n- **Raw** (`--raw`): Unprocessed API response\n\n## Cost & Time\n\n| Metric | Value |\n|--------|-------|\n| Time | 2-10 minutes per task |\n| Cost | $2-5 per task (varies by complexity) |\n| Token usage | ~250k-900k input, ~60k-80k output |\n\n## Best Use Cases\n\n- Market analysis and competitive landscaping\n- Technical literature reviews\n- Due diligence research\n- Historical research and timelines\n- Comparative analysis (frameworks, products, technologies)\n\n## Workflow\n\n1. User requests research → Run `--query \"...\"`\n2. Inform user of estimated time (2-10 minutes)\n3. Monitor with `--stream` or poll with `--status`\n4. Return formatted results\n5. Use `--continue` for follow-up questions\n\n## Exit Codes\n\n- **0**: Success\n- **1**: Error (API error, config issue, timeout)\n- **130**: Cancelled by user (Ctrl+C)",
  "applicable_domains": [
    "other"
  ],
  "category": "other",
  "invocation": [
    "/deep-research"
  ],
  "authored_by": "claudeskills.in community",
  "source_url": "https://claudeskills.in/skill/deep-research",
  "provenance": {
    "source": "claudeskills.in",
    "source_url": "https://claudeskills.in/skill/deep-research",
    "license": "Apache-2.0",
    "imported_at": "2026-09-03",
    "notes": "Aggregated by claudeskills.in from community GitHub lists. Upstream as recorded by the aggregator: https://github.com/sanjay3290/ai-skills/tree/main/skills/deep-research. License Apache-2.0 read from github.com/sanjay3290/ai-skills on 2026-09-03."
  },
  "tags": [
    "claudeskills",
    "other",
    "risk-reviewed"
  ],
  "lifecycle": "draft"
}