gemini-deep-research
Run autonomous multi-step research with Google's Gemini Deep Research Agent: kick off a query, poll progress, and collect a cited report for market analysis or literature reviews.
- License 许可
- Apache-2.0
- 最近更新
- 2026-08-07
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- gemini-deep-research
- risk
- critical
- tags
- [ "research", "gemini", "google", "reports" ]
- tools
- [ "claude", "cursor", "gemini" ]
- author
- sanjay3290
- source
- https://github.com/sanjay3290/ai-skills/tree/main/skills/deep-research
- license
- Apache-2.0
- category
- research
- date_added
- 2026-07-09
- description
- Run autonomous multi-step research with Google's Gemini Deep Research Agent: kick off a query, poll progress, and collect a cited report for market analysis or literature reviews.
- source_repo
- sanjay3290/ai-skills
- source_type
- community
- license_source
- https://github.com/sanjay3290/ai-skills/blob/main/LICENSE
02 资源文件 3
- 参考文档README.md7.5 KB
- 参考文档requirements.txt35 B
- 脚本scripts/research.py23.6 KB
03 SKILL.md 正文
Gemini Deep Research Skill
When to Use
- Use when a question needs autonomous multi-step research with cited sources (market analysis, literature reviews, competitive scans)
- Use when you want to start a Gemini Deep Research run, poll its progress, and collect the final report
- Use when a quick web search is not enough and a structured, source-grounded report is required
Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.
Requirements
- Python 3.8+
- httpx:
pip install -r requirements.txt - GEMINI_API_KEY environment variable
Setup
- Get a Gemini API key from Google AI Studio
- Set the environment variable:
Or create aexport GEMINI_API_KEY=your-api-key-here.envfile in the skill directory.
Safety Gate
Before starting a research job, show the user the exact query, the fact that it will be sent to Google's Gemini service, the expected cost range, and the output destination. Start a job only after explicit approval. Do not include private workspace material, credentials, personal data, or confidential customer information in a query.
Usage
Start a research task
python3 scripts/research.py --query "Research the history of Kubernetes"
With structured output format
python3 scripts/research.py --query "Compare Python web frameworks" \
--format "1. Executive Summary\n2. Comparison Table\n3. Recommendations"
Stream progress in real-time
python3 scripts/research.py --query "Analyze EV battery market" --stream
Start without waiting
python3 scripts/research.py --query "Research topic" --no-wait
Check status of running research
python3 scripts/research.py --status <interaction_id>
Wait for completion
python3 scripts/research.py --wait <interaction_id>
Continue from previous research
python3 scripts/research.py --query "Elaborate on point 2" --continue <interaction_id>
List recent research
python3 scripts/research.py --list
Output Formats
- Default: Human-readable markdown report
- JSON (
--json): Structured data for programmatic use - Raw (
--raw): Unprocessed API response
Cost & Time
| Metric | Value |
|---|---|
| Time | 2-10 minutes per task |
| Cost | $2-5 per task (varies by complexity) |
| Token usage | ~250k-900k input, ~60k-80k output |
Best Use Cases
- Market analysis and competitive landscaping
- Technical literature reviews
- Due diligence research
- Historical research and timelines
- Comparative analysis (frameworks, products, technologies)
Workflow
- User requests research → Run
--query "..." - Inform user of estimated time (2-10 minutes)
- Monitor with
--streamor poll with--status - Return formatted results
- Use
--continuefor follow-up questions
Exit Codes
- 0: Success
- 1: Error (API error, config issue, timeout)
- 130: Cancelled by user (Ctrl+C)
Limitations
- Each research job is a paid, third-party API request; costs and availability can change, and the listed estimate is not a spending authorization.
- Reports may contain incomplete, stale, or incorrect citations. Verify consequential claims against primary sources.
- This skill cannot guarantee that a prompt is safe to disclose; redact proprietary or personal material before requesting user approval.
- An API key must remain local and must never be committed, printed, or sent in a query.
04 同仓库更多 Skills
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
stop-slop
Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells and produce more human-like writing.
ogilvy-copywriting
Apply David Ogilvy's advertising principles when writing or reviewing copy, headlines, product descriptions, landing pages, ads, emails, or any persuasive text. Use when the goal is copy that sells, not copy that wins awards. Covers positioning, headlines, promises, brand voice, long-form copy, and visual logic. Source: How to Create Advertising That Sells (1972) + Ogilvy on Advertising.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.