About deep-research
deep-research is a research skill for multi-source search, evidence gathering, and structured reporting. It returns search results, fetched pages, and a synthesis prompt for an LLM to organize into findings and recommendations.
Key features
- 01Search across sources by topic
- 02Generate or specify search queries
- 03Fetch pages from supplied URLs
- 04Choose basic or advanced depth
- 05Return research inputs as JSON
Use cases
- 01Collect sources on a research topic
- 02Fetch full text from selected pages
- 03Organize findings by evidence and confidence
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/deep-researchin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
run.pytests/__init__.pytest_deep_research.pyDetails
From the project READMEdeep-research
多源检索 + 证据汇编 + 结构化报告。
调用
python3 skills/deep-research/run.py --topic '研究主题' --queries '["关键词1","关键词2"]' --max_results 5 --depth basic
参数
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
| topic | string | 是 | 研究主题 |
| queries | string[] | 否 | 搜索关键词，默认自动生成 3 条 |
| max_results | int | 否 | 每条 query 结果数，默认 5 |
| depth | string | 否 | "basic" 或 "advanced" |
| fetch_urls | string[] | 否 | 额外抓取全文的 URL |
输出
返回 JSON，包含 searches（搜索结果）、fetched_pages（抓取页面）、summary_prompt（综合提示）。
LLM 拿到结果后，按「问题→发现/证据→置信度→影响/建议」结构化整理。
Comments
Markdown supported