tavily by intellectronica/agent-skills
npx skills add https://github.com/intellectronica/agent-skills --skill tavily提供基于 curl 的接口,用于访问 Tavily 的 REST API,以进行网络搜索、内容提取、站点地图生成、爬取以及可选的研究功能。返回适用于 LLM 工作流和多步骤调查的结构化结果。
TAVILY_API_KEY。TAVILY_API_KEY,请在继续操作前提示用户提供 API 密钥。https://api.tavily.comAuthorization: Bearer $TAVILY_API_KEYContent-Type: application/jsonX-Project-ID: <project-id>。广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
用于网络搜索,可选择包含答案和内容提取。
推荐的最小请求:
curl -sS -X POST "https://api.tavily.com/search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"query": "<query>",
"search_depth": "basic",
"max_results": 5,
"include_answer": true,
"include_raw_content": false,
"include_images": false
}'
关键参数(除非注明,否则均为可选):
query (必需):搜索文本search_depth:basic | advanced | fast | ultra-fastchunks_per_source:1–3 (仅限 advanced 模式)max_results:0–20topic:general | news | financetime_range:day|week|month|year|d|w|m|ystart_date, end_date:YYYY-MM-DDinclude_answer:false | true | basic | advancedinclude_raw_content:false | true | markdown | textinclude_images:布尔值include_image_descriptions:布尔值include_favicon:布尔值include_domains, exclude_domains:字符串数组country:国家名称(仅限 general 主题)auto_parameters:布尔值include_usage:布尔值预期响应字段:
answer (如果请求),results[] 包含 title, url, content, score, raw_content (可选),favicon (可选)response_time, usage, request_id用于从特定 URL 提取内容。
curl -sS -X POST "https://api.tavily.com/extract" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"urls": ["https://example.com/article"],
"query": "<optional intent for reranking>",
"chunks_per_source": 3,
"extract_depth": "basic",
"format": "markdown",
"include_images": false,
"include_favicon": false
}'
关键参数:
urls (必需):URL 数组query:根据意图对内容块重新排序chunks_per_source:1–5 (仅在提供 query 时有效)extract_depth:basic | advancedformat:markdown | texttimeout:1–60 秒include_usage:布尔值预期响应字段:
results[] 包含 url, raw_content, images, faviconfailed_results[], response_time, usage, request_id用于生成站点地图(仅限 URL 发现)。
curl -sS -X POST "https://api.tavily.com/map" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"url": "https://docs.tavily.com",
"max_depth": 1,
"max_breadth": 20,
"limit": 50,
"allow_external": true
}'
关键参数:
url (必需)instructions:自然语言指导(会增加成本)max_depth:1–5max_breadth:1+limit:1+select_paths, select_domains, exclude_paths, exclude_domains:正则表达式字符串数组allow_external:布尔值timeout:10–150 秒include_usage:布尔值预期响应字段:
base_url, results[] (URL 列表),response_time, usage, request_id用于结合内置提取功能的站点遍历。
curl -sS -X POST "https://api.tavily.com/crawl" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"url": "https://docs.tavily.com",
"instructions": "Find all pages about the Python SDK",
"max_depth": 1,
"max_breadth": 20,
"limit": 50,
"extract_depth": "basic",
"format": "markdown",
"include_images": false
}'
关键参数:
url (必需)instructions:可选;会增加成本并启用 chunks_per_sourcechunks_per_source:1–5 (仅与 instructions 一起使用)max_depth, max_breadth, limit:与 map 相同extract_depth:basic | advancedformat:markdown | textinclude_images, include_favicon, allow_externaltimeout:10–150 秒include_usage:布尔值预期响应字段:
base_url, results[] 包含 url, raw_content, faviconresponse_time, usage, request_id当查询需要多步骤分析和引用时使用。
curl -sS -X POST "https://api.tavily.com/research" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"input": "<research question>",
"model": "auto",
"stream": false,
"citation_format": "numbered"
}'
预期响应字段:
request_id, created_at, status (pending), input, model, response_timecurl -sS -X GET "https://api.tavily.com/research/<request_id>" \
-H "Authorization: Bearer $TAVILY_API_KEY"
预期响应字段:
status:completedcontent:报告文本或结构化对象sources[]:{ title, url, favicon }在 POST 请求体中设置 "stream": true,并使用带 -N 参数的 curl 来流式接收事件:
curl -N -X POST "https://api.tavily.com/research" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{"input":"<question>","stream":true,"model":"pro"}'
处理 SSE 事件(工具调用、工具响应、内容块、来源、完成)。
search、extract、map 和 crawl 视为用于发现和内容检索的主要端点。search_depth: basic, max_results: 5)。TAVILY_API_KEY。max_depth/limit 或使用 search_depth: basic。max_results 或 chunks_per_source。每周安装量
216
代码仓库
GitHub 星标数
228
首次出现
Jan 20, 2026
安全审计
安装于
opencode175
gemini-cli167
codex162
claude-code161
cursor158
github-copilot139
Provide a curl-based interface to Tavily’s REST API for web search, extraction, mapping, crawling, and optional research. Return structured results suitable for LLM workflows and multi-step investigations.
TAVILY_API_KEY in the environment.TAVILY_API_KEY is missing, prompt the user to provide the API key before proceeding.https://api.tavily.comAuthorization: Bearer $TAVILY_API_KEYContent-Type: application/jsonX-Project-ID: <project-id> if project attribution is needed.Use for web search with optional answer and content extraction.
Recommended minimal request:
curl -sS -X POST "https://api.tavily.com/search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"query": "<query>",
"search_depth": "basic",
"max_results": 5,
"include_answer": true,
"include_raw_content": false,
"include_images": false
}'
Key parameters (all optional unless noted):
query (required): search textsearch_depth: basic | advanced | fast | ultra-fastchunks_per_source: 1–3 (advanced only)max_results: 0–20topic: general | news | Expected response fields:
answer (if requested), results[] with title, url, content, score, raw_content (optional), favicon (optional)response_time, usage, request_idUse for extracting content from specific URLs.
curl -sS -X POST "https://api.tavily.com/extract" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"urls": ["https://example.com/article"],
"query": "<optional intent for reranking>",
"chunks_per_source": 3,
"extract_depth": "basic",
"format": "markdown",
"include_images": false,
"include_favicon": false
}'
Key parameters:
urls (required): array of URLsquery: rerank chunks by intentchunks_per_source: 1–5 (only when query provided)extract_depth: basic | advancedformat: markdown | texttimeout: 1–60 secondsExpected response fields:
results[] with url, raw_content, images, faviconfailed_results[], response_time, usage, request_idUse for generating a site map (URL discovery only).
curl -sS -X POST "https://api.tavily.com/map" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"url": "https://docs.tavily.com",
"max_depth": 1,
"max_breadth": 20,
"limit": 50,
"allow_external": true
}'
Key parameters:
url (required)instructions: natural language guidance (raises cost)max_depth: 1–5max_breadth: 1+limit: 1+select_paths, select_domains, exclude_paths, exclude_domains: arrays of regex stringsallow_external: booleanExpected response fields:
base_url, results[] (list of URLs), response_time, usage, request_idUse for site traversal with built-in extraction.
curl -sS -X POST "https://api.tavily.com/crawl" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"url": "https://docs.tavily.com",
"instructions": "Find all pages about the Python SDK",
"max_depth": 1,
"max_breadth": 20,
"limit": 50,
"extract_depth": "basic",
"format": "markdown",
"include_images": false
}'
Key parameters:
url (required)instructions: optional; raises cost and enables chunks_per_sourcechunks_per_source: 1–5 (only with instructions)max_depth, max_breadth, limit: same as mapextract_depth: basic | advancedExpected response fields:
base_url, results[] with url, raw_content, faviconresponse_time, usage, request_idUse when a query needs multi-step analysis and citations.
curl -sS -X POST "https://api.tavily.com/research" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{
"input": "<research question>",
"model": "auto",
"stream": false,
"citation_format": "numbered"
}'
Expected response fields:
request_id, created_at, status (pending), input, model, response_timecurl -sS -X GET "https://api.tavily.com/research/<request_id>" \
-H "Authorization: Bearer $TAVILY_API_KEY"
Expected response fields:
status: completedcontent: report text or structured objectsources[]: { title, url, favicon }Set "stream": true in the POST body and use curl with -N to stream events:
curl -N -X POST "https://api.tavily.com/research" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-d '{"input":"<question>","stream":true,"model":"pro"}'
Handle SSE events (tool calls, tool responses, content chunks, sources, done).
search, extract, map, and crawl as the primary endpoints for discovery and content retrieval.search_depth: basic, max_results: 5) unless deeper recall is needed.TAVILY_API_KEY.max_depth/limit or use search_depth: basic.max_results or chunks_per_source.Weekly Installs
216
Repository
GitHub Stars
228
First Seen
Jan 20, 2026
Security Audits
Gen Agent Trust HubFailSocketPassSnykWarn
Installed on
opencode175
gemini-cli167
codex162
claude-code161
cursor158
github-copilot139
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
58,500 周安装
financetime_range: day|week|month|year|d|w|m|ystart_date, end_date: YYYY-MM-DDinclude_answer: false | true | basic | advancedinclude_raw_content: false | true | markdown | textinclude_images: booleaninclude_image_descriptions: booleaninclude_favicon: booleaninclude_domains, exclude_domains: string arrayscountry: country name (general topic only)auto_parameters: booleaninclude_usage: booleaninclude_usage: booleantimeoutinclude_usage: booleanformat: markdown | textinclude_images, include_favicon, allow_externaltimeout: 10–150 secondsinclude_usage: boolean