Deep Research (Gemini)
Delegates multi-step research to Google's Gemini Deep Research agent and returns detailed, cited reports from the command line.
Data & AnalyticsIntermediate★ 198⑂ 50AI score 9/10Last updated: Feb 26, 2026
What it does
- Claude runs
scripts/research.pyto hand a research brief to the Gemini Deep Research agent. - The agent autonomously plans, searches, reads and synthesizes sources into a cited, comprehensive report.
- Supports live progress with
--stream, background runs with--no-wait, polling via--status/--wait, follow-ups with--continue, and history via--list. - Output can be Markdown (default), JSON (
--json) or raw API response (--raw), with an optional--formatoutline.
Who it's for
- Strategy, corp-dev and market research teams doing competitive landscaping or due diligence.
- Engineers and tech leads needing literature reviews or framework/product comparisons.
- Automation builders who want structured JSON research output for downstream pipelines.
- Requires a Gemini API key and tolerance for $2–5 and 2–10 minutes per task.
Examples
python3 scripts/research.py --query "Analyze EV battery market" --streamto watch the report build in real time.- Add
--format "1. Executive Summary\n2. Comparison Table\n3. Recommendations"for a structured Python web framework comparison. - Use
--continue <interaction_id>to drill down: "Elaborate on point 2" from a finished report.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/w95/awesome-claude-corporate-skills/HEAD/01-executive-leadership/deep-research/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the 01-executive-leadership/deep-research folder from the GitHub repo w95/awesome-claude-corporate-skills into my ~/.claude/skills/w95-deep-research/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/w95/awesome-claude-corporate-skills.git && mkdir -p ~/.claude/skills && cp -r awesome-claude-corporate-skills/01-executive-leadership/deep-research ~/.claude/skills/deep-research⚠ This is a third-party skill. Check the source repository before installing.
- Clone the repo:
git clone https://github.com/w95/awesome-claude-corporate-skills.git - Copy the skill into place:
mkdir -p ~/.claude/skills && cp -r awesome-claude-corporate-skills/01-executive-leadership/deep-research ~/.claude/skills/deep-research - Verify Python 3.8+:
python3 --version - Install dependencies:
cd ~/.claude/skills/deep-research && pip install -r requirements.txt(needs httpx). - Create a Gemini API key at Google AI Studio.
- Export it:
export GEMINI_API_KEY=your-api-key-here(or add a.envfile in the skill folder). - Restart Claude Code and ask something like "use deep research to analyze the EV battery market". Expect 2–10 minutes and $2–5 in API cost per task.
View source on GitHub ↗License: MIT