search by tavily-ai/skills
npx skills add https://github.com/tavily-ai/skills --skill search搜索网络并获取针对 LLM 消费优化的相关结果。
该脚本通过 Tavily MCP 服务器使用 OAuth 进行身份验证。无需手动设置 - 首次运行时,它将:
~/.mcp-auth/ 中是否存在现有令牌注意: 您必须拥有一个现有的 Tavily 账户。OAuth 流程仅支持登录 - 不支持通过此流程创建账户。如果您还没有账户,请先在 tavily.com 注册。
如果您更喜欢使用 API 密钥,请在 https://tavily.com 获取一个,并添加到 ~/.claude/settings.json 中:
{
"env": {
"TAVILY_API_KEY": "tvly-your-api-key-here"
}
}
./scripts/search.sh '<json>'
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
# 基本搜索
./scripts/search.sh '{"query": "python async patterns"}'
# 带选项的搜索
./scripts/search.sh '{"query": "React hooks tutorial", "max_results": 10}'
# 带过滤器的高级搜索
./scripts/search.sh '{"query": "AI news", "time_range": "week", "max_results": 10}'
# 域名过滤搜索
./scripts/search.sh '{"query": "machine learning", "include_domains": ["arxiv.org", "github.com"], "search_depth": "advanced"}'
curl --request POST \
--url https://api.tavily.com/search \
--header "Authorization: Bearer $TAVILY_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"query": "latest developments in quantum computing",
"max_results": 5
}'
curl --request POST \
--url https://api.tavily.com/search \
--header "Authorization: Bearer $TAVILY_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"query": "machine learning best practices",
"max_results": 10,
"search_depth": "advanced",
"include_domains": ["arxiv.org", "github.com"]
}'
POST https://api.tavily.com/search
| 请求头 | 值 |
|---|---|
Authorization | Bearer <TAVILY_API_KEY> |
Content-Type | application/json |
| 字段 | 类型 | 默认值 | 描述 |
|---|---|---|---|
query | string | 必填 | 搜索查询(保持在 400 字符以内) |
max_results | integer | 10 | 最大结果数(0-20) |
search_depth | string | "basic" | ultra-fast, fast, basic, advanced |
topic | string | "general" | 搜索主题(仅限 general) |
time_range | string | null | day, week, month, year |
start_date | string | null | 返回此日期之后的结果(YYYY-MM-DD) |
end_date | string | null | 返回此日期之前的结果(YYYY-MM-DD) |
include_domains | array | [] | 要包含的域名(最多 300 个) |
exclude_domains | array | [] | 要排除的域名(最多 150 个) |
country | string | null | 提升来自特定国家的结果(仅限 general 主题) |
include_raw_content | boolean | false | 包含完整页面内容 |
include_images | boolean | false | 包含图片结果 |
include_image_descriptions | boolean | false | 包含图片的描述 |
include_favicon | boolean | false | 为每个结果包含网站图标 URL |
{
"query": "latest developments in quantum computing",
"results": [
{
"title": "Page Title",
"url": "https://example.com/page",
"content": "Extracted text snippet...",
"score": 0.85
}
],
"response_time": 1.2
}
| 深度 | 延迟 | 相关性 | 内容类型 |
|---|---|---|---|
ultra-fast | 最低 | 较低 | NLP 摘要 |
fast | 低 | 良好 | 文本块 |
basic | 中等 | 高 | NLP 摘要 |
advanced | 较高 | 最高 | 文本块 |
何时使用每种模式:
ultra-fast:实时聊天、自动补全fast:需要文本块但对延迟敏感时basic:通用、平衡advanced:精度至关重要(默认推荐)curl --request POST \
--url https://api.tavily.com/search \
--header "Authorization: Bearer $TAVILY_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"query": "Python async best practices",
"include_domains": ["docs.python.org", "realpython.com", "github.com"],
"search_depth": "advanced"
}'
curl --request POST \
--url https://api.tavily.com/search \
--header "Authorization: Bearer $TAVILY_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"query": "React hooks tutorial",
"max_results": 3,
"include_raw_content": true
}'
include_domains 来专注于可信来源time_range 获取最新信息score (0-1) 进行过滤 以获取相关性最高的结果每周安装量
11.9K
代码仓库
GitHub 星标数
142
首次出现
2026年1月25日
安全审计
安装于
opencode11.1K
gemini-cli11.0K
codex10.9K
github-copilot10.8K
kimi-cli10.7K
amp10.6K
Search the web and get relevant results optimized for LLM consumption.
The script uses OAuth via the Tavily MCP server. No manual setup required - on first run, it will:
~/.mcp-auth/Note: You must have an existing Tavily account. The OAuth flow only supports login — account creation is not available through this flow. Sign up at tavily.com first if you don't have an account.
If you prefer using an API key, get one at https://tavily.com and add to ~/.claude/settings.json:
{
"env": {
"TAVILY_API_KEY": "tvly-your-api-key-here"
}
}
./scripts/search.sh '<json>'
Examples:
# Basic search
./scripts/search.sh '{"query": "python async patterns"}'
# With options
./scripts/search.sh '{"query": "React hooks tutorial", "max_results": 10}'
# Advanced search with filters
./scripts/search.sh '{"query": "AI news", "time_range": "week", "max_results": 10}'
# Domain-filtered search
./scripts/search.sh '{"query": "machine learning", "include_domains": ["arxiv.org", "github.com"], "search_depth": "advanced"}'
curl --request POST \
--url https://api.tavily.com/search \
--header "Authorization: Bearer $TAVILY_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"query": "latest developments in quantum computing",
"max_results": 5
}'
curl --request POST \
--url https://api.tavily.com/search \
--header "Authorization: Bearer $TAVILY_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"query": "machine learning best practices",
"max_results": 10,
"search_depth": "advanced",
"include_domains": ["arxiv.org", "github.com"]
}'
POST https://api.tavily.com/search
| Header | Value |
|---|---|
Authorization | Bearer <TAVILY_API_KEY> |
Content-Type | application/json |
| Field | Type | Default | Description |
|---|---|---|---|
query | string | Required | Search query (keep under 400 chars) |
max_results | integer | 10 | Maximum results (0-20) |
search_depth | string | "basic" | ultra-fast, fast, , |
{
"query": "latest developments in quantum computing",
"results": [
{
"title": "Page Title",
"url": "https://example.com/page",
"content": "Extracted text snippet...",
"score": 0.85
}
],
"response_time": 1.2
}
| Depth | Latency | Relevance | Content Type |
|---|---|---|---|
ultra-fast | Lowest | Lower | NLP summary |
fast | Low | Good | Chunks |
basic | Medium | High | NLP summary |
advanced | Higher | Highest | Chunks |
When to use each:
ultra-fast: Real-time chat, autocompletefast: Need chunks but latency mattersbasic: General-purpose, balancedadvanced: Precision matters (default recommendation)curl --request POST \
--url https://api.tavily.com/search \
--header "Authorization: Bearer $TAVILY_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"query": "Python async best practices",
"include_domains": ["docs.python.org", "realpython.com", "github.com"],
"search_depth": "advanced"
}'
curl --request POST \
--url https://api.tavily.com/search \
--header "Authorization: Bearer $TAVILY_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"query": "React hooks tutorial",
"max_results": 3,
"include_raw_content": true
}'
include_domains to focus on trusted sourcestime_range for recent informationscore (0-1) to get highest relevance resultsWeekly Installs
11.9K
Repository
GitHub Stars
142
First Seen
Jan 25, 2026
Security Audits
Gen Agent Trust HubWarnSocketPassSnykWarn
Installed on
opencode11.1K
gemini-cli11.0K
codex10.9K
github-copilot10.8K
kimi-cli10.7K
amp10.6K
React 组合模式指南:Vercel 组件架构最佳实践,提升代码可维护性
102,200 周安装
basicadvancedtopic | string | "general" | Search topic (general only) |
time_range | string | null | day, week, month, year |
start_date | string | null | Return results after this date (YYYY-MM-DD) |
end_date | string | null | Return results before this date (YYYY-MM-DD) |
include_domains | array | [] | Domains to include (max 300) |
exclude_domains | array | [] | Domains to exclude (max 150) |
country | string | null | Boost results from a specific country (general topic only) |
include_raw_content | boolean | false | Include full page content |
include_images | boolean | false | Include image results |
include_image_descriptions | boolean | false | Include descriptions for images |
include_favicon | boolean | false | Include favicon URL for each result |