tavily-research
Skill1 starsChanged 5 months agoMITView on GitHub
通过 Tavily Research API 对主题进行深度研究,生成研究报告。当用户需要进行多搜索、多来源的深度分析并生成结构化报告时使用。
- Installs packages
5 other projects use a version of this.
Adopted by
Most recently taken up by
- tavily-ai/skillstheir own version, first seen Nov 1, 2026
- PracticalSwan/agent-skillstheir own version, first seen Oct 19, 2026
- wkylin/pro-react-admintheir own version, first seen Oct 8, 2026
- mppyxx/claude-power-packtheir own version, first seen Oct 8, 2026
- jpoindexter/theft-kittheir own version, first seen May 20, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- wkylin/pro-react-admin★ 948same name
- tavily-ai/skills★ 492same name
- PracticalSwan/agent-skills★ 22same name
- jpoindexter/theft-kit★ 1same name
- mppyxx/claude-power-pack★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- tavily-crawlSkill
- tavily-extractSkill
- tavily-mapSkill
- tavily-searchSkill
The file
Files
Tavily 深度研究
使用 Tavily Research API 对指定主题执行多轮搜索、分析来源并生成详细研究报告。异步任务模型:先创建任务,再轮询获取结果。
环境准备
- Python 3.8+
- Tavily API key(在 https://app.tavily.com 获取)
- 安装依赖:
pip install requests python-dotenv
用法
# 创建研究任务(返回 request_id)
python scripts/tavily-research.py create --input "What are the latest developments in AI?"
# 创建任务并等待完成
python scripts/tavily-research.py create --input "What are the latest developments in AI?" --wait
# 查询任务结果
python scripts/tavily-research.py get --request-id "123e4567-..."create 参数
| 参数 | 类型 | 默认值 | 说明 |
--input | str | 必填 | 研究问题或主题 |
--model | str | auto | auto / mini(高效专注)/ pro(全面多角度) |
--output-length | str | standard | short / standard / long |
--citation-format | str | numbered | numbered / mla / apa / chicago |
--wait | flag | 关闭 | 开启后自动轮询直到完成,直接输出报告内容 |
get 参数
| 参数 | 类型 | 默认值 | 说明 |
--request-id | str | 必填 | 任务 ID(来自 create 返回的 request_id) |
示例
# 提交研究任务
python scripts/tavily-research.py create --input "量子计算的最新进展"
# 提交并等待报告
python scripts/tavily-research.py create --input "AI 监管政策趋势" --model pro --output-length long --wait
# 查询已有任务
python scripts/tavily-research.py get --request-id "123e4567-e89b-12d3-a456-426614174111"输出为 JSON,打印到 stdout。成功退出码 0,失败非 0。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

