深度调研技能，多源检索 + 证据汇编 + 结构化报告。
This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.
Install skill "deep-research" with this command: npx skills add cklxx/elephant.ai/cklxx-elephant-ai-deep-research
多源检索 + 证据汇编 + 结构化报告。
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 | 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 |
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。
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
No summary provided by upstream source.
No summary provided by upstream source.
No summary provided by upstream source.
No summary provided by upstream source.