nimble-web-search

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Nimble Web Search

Nimble 网页搜索

Real-time web intelligence using Nimble Search API with specialized focus modes and AI-powered result synthesis.

基于Nimble Search API的实时网页智能工具，具备专业聚焦模式和AI驱动的结果合成功能。

Prerequisites

前置条件

Nimble API Key Required - Get your key at https://www.nimbleway.com/

需要Nimble API密钥 - 前往 https://www.nimbleway.com/ 获取密钥

Configuration

配置

Set the

NIMBLE_API_KEY

environment variable using your platform's method:

Claude Code:

json

// ~/.claude/settings.json
{
  "env": {
    "NIMBLE_API_KEY": "your-api-key-here"
  }
}

VS Code/GitHub Copilot:

Add to
```
.github/skills/
```
directory in your repository
Or use GitHub Actions secrets for the copilot environment

Shell/Terminal:

bash

export NIMBLE_API_KEY="your-api-key-here"

Any Platform: The skill checks for the

NIMBLE_API_KEY

environment variable regardless of how you set it.

通过对应平台的方式设置

NIMBLE_API_KEY

环境变量：

Claude Code：

json

// ~/.claude/settings.json
{
  "env": {
    "NIMBLE_API_KEY": "your-api-key-here"
  }
}

VS Code/GitHub Copilot：

添加到仓库的
```
.github/skills/
```
目录
或使用GitHub Actions密钥配置Copilot环境

Shell/终端：

bash

export NIMBLE_API_KEY="your-api-key-here"

任意平台： 无论通过哪种方式设置，该技能都会检查

NIMBLE_API_KEY

环境变量。

API Key Validation

API密钥验证

IMPORTANT: Before making any search request, verify the API key is configured:

bash

undefined

重要：在发起任何搜索请求前，请验证API密钥已配置：

bash

undefined

Check if API key is set

检查API密钥是否已设置

if [ -z "$NIMBLE_API_KEY" ]; then echo "❌ Error: NIMBLE_API_KEY not configured" echo "" echo "Get your API key: https://www.nimbleway.com/" echo "" echo "Configure using your platform's method:" echo "- Claude Code: Add to ~/.claude/settings.json" echo "- GitHub Copilot: Use GitHub Actions secrets" echo "- Shell: export NIMBLE_API_KEY="your-key"" echo "" echo "Do NOT fall back to other search tools - guide the user to configure first." exit 1 fi

undefined

if [ -z "$NIMBLE_API_KEY" ]; then echo "❌ 错误：NIMBLE_API_KEY未配置" echo "" echo "获取API密钥：https://www.nimbleway.com/" echo "" echo "通过对应平台方式配置：" echo "- Claude Code：添加到~/.claude/settings.json" echo "- GitHub Copilot：使用GitHub Actions密钥" echo "- Shell：执行export NIMBLE_API_KEY="your-key"" echo "" echo "请勿切换到其他搜索工具 - 引导用户先完成配置。" exit 1 fi

undefined

Overview

概述

Nimble Search provides real-time web intelligence with 8 specialized focus modes optimized for different types of queries. Get instant access to current web data with AI-powered answer generation, deep content extraction, URL discovery, and smart filtering by domain and date.

IMPORTANT: Always Specify These Parameters

When using this skill, always explicitly set the following parameters in your requests:

```
deep_search
```
: Default to
false
for 5-10x faster responses
- Use
  false
  (FAST MODE - 1-3 seconds): For 95% of use cases - URL discovery, research, comparisons, answer generation
- Use
  true
  (DEEP MODE - 5-15 seconds): Only when you specifically need full page content extracted for archiving or detailed analysis
```
focus
```
: Default to
"general"
for broad searches
- Change to specific mode (
```
coding
```
  ,
```
news
```
  ,
```
academic
```
  ,
```
shopping
```
  ,
```
social
```
  ,
```
geo
```
  ,
```
location
```
  ) for targeted results
```
max_results
```
: Default to
10
- Balanced speed and coverage

Performance Awareness: By explicitly setting

deep_search: false

, you're choosing fast mode and should expect results in 1-3 seconds. If you set

deep_search: true

, expect 5-15 seconds response time.

Nimble Search提供具备8种专业聚焦模式的实时网页智能功能，针对不同类型的查询进行优化。通过AI驱动的答案生成、深度内容提取、URL发现以及按域名和日期的智能过滤，即时获取最新网页数据。

重要：请始终指定以下参数

使用该技能时，请在请求中显式设置以下参数：

```
deep_search
```
：默认值为
false
，响应速度提升5-10倍
- 设置为
  false
  （快速模式 - 1-3秒）：适用于95%的场景 - URL发现、研究、对比、答案生成
- 设置为
  true
  （深度模式 - 5-15秒）：仅当你需要提取完整页面内容用于存档或详细分析时使用
```
focus
```
：默认值为
"general"
，适用于广泛搜索
- 可切换为特定模式（
```
coding
```
  、
```
news
```
  、
```
academic
```
  、
```
shopping
```
  、
```
social
```
  、
```
geo
```
  、
```
location
```
  ）以获取针对性结果
```
max_results
```
：默认值为
10
- 在速度和覆盖范围间取得平衡

性能说明： 显式设置

deep_search: false

即选择快速模式，响应时间约1-3秒。若设置

deep_search: true

，响应时间约5-15秒。

Quick Start

快速开始

Use the wrapper script for the simplest experience:

bash

undefined

使用包装脚本获得最简体验：

bash

undefined

ALWAYS specify deep_search explicitly

请始终显式指定deep_search

./scripts/search.sh '{ "query": "React hooks", "deep_search": false }'


The script automatically handles authentication, tracking headers, and output formatting.

./scripts/search.sh '{ "query": "React hooks", "deep_search": false }'


该脚本会自动处理身份验证、跟踪标头和输出格式化。

When to Use Each Mode

各模式适用场景

Use
deep_search: false
(FAST MODE - 1-3 seconds) - Default for 95% of cases:

✅ Finding URLs and discovering resources
✅ Research and topic exploration
✅ Answer generation and summaries
✅ Product comparisons
✅ News monitoring
✅ Any time you DON'T need full article text

Use
deep_search: true
(DEEP MODE - 5-15 seconds) - Only when specifically needed:

📄 Archiving full article content
📄 Extracting complete documentation
📄 Building text datasets
📄 Processing full page content for analysis

Decision Rule: If you're not sure, use

deep_search: false

. You can always re-run with

true

if needed.

使用
deep_search: false
（快速模式 - 1-3秒）- 95%场景的默认选择：

✅ 查找URL和发现资源
✅ 研究和主题探索
✅ 答案生成和摘要
✅ 产品对比
✅ 新闻监控
✅ 任何不需要完整文章文本的场景

使用
deep_search: true
（深度模式 - 5-15秒）- 仅在特定需求下使用：

📄 存档完整文章内容
📄 提取完整文档
📄 构建文本数据集
📄 处理完整页面内容用于分析

决策原则： 若不确定，使用

deep_search: false

。如有需要，可重新运行并设置为

true

。

Core Capabilities

核心功能

Focus Modes

聚焦模式

Choose the appropriate focus mode based on your query type:

general - Default mode for broad web searches
coding - Real-time access to technical documentation, code examples, programming resources
news - Real-time news articles, current events, breaking stories
academic - Research papers, scholarly articles, academic resources
shopping - Real-time product searches, e-commerce results, price comparisons
social - Real-time social media posts, discussions, trending community content
geo - Location-based searches, geographic information
location - Local business searches, place-specific queries

根据查询类型选择合适的聚焦模式：

general - 通用模式，适用于广泛网页搜索
coding - 实时访问技术文档、代码示例、编程资源
news - 实时新闻文章、当前事件、突发新闻
academic - 研究论文、学术文章、学术资源
shopping - 实时产品搜索、电商结果、价格对比
social - 实时社交媒体帖子、讨论、热门社区内容
geo - 基于位置的搜索、地理信息
location - 本地商家搜索、特定地点查询

Search Features

搜索特性

LLM Answer Generation

Request AI-generated answers synthesized from search results
Powered by Claude for high-quality summaries
Include citations to source URLs
Best for: Research questions, topic overviews, comparative analysis

URL Discovery

Extract 1-20 most relevant URLs for a query
Useful for building reading lists and reference collections
Returns URLs with titles and descriptions
Best for: Resource gathering, link building, research preparation

Deep Content Extraction

Default (Recommended):
```
deep_search=false
```
- Fastest response, returns titles, descriptions, and URLs
Optional:
```
deep_search=true
```
- Slower, extracts full page content
Important: Most use cases work perfectly with
```
deep_search=false
```
(the default)
Available formats when deep_search=true: markdown, plain_text, simplified_html
Only enable deep search for: Detailed content analysis, archiving, or comprehensive text extraction needs

Domain Filtering

Include specific domains (e.g., github.com, stackoverflow.com)
Exclude domains to remove unwanted sources
Combine multiple domains for focused searches
Best for: Targeted research, brand monitoring, competitive analysis

Time Filtering

Recommended: Use
```
time_range
```
for real-time recency filtering (hour, day, week, month, year)
Alternative: Use
```
start_date
```
/
```
end_date
```
for precise date ranges (YYYY-MM-DD)
Note:
```
time_range
```
and date filters are mutually exclusive
Best for: Real-time news monitoring, recent developments, temporal analysis

LLM答案生成

请求基于搜索结果合成的AI生成答案
由Claude驱动，生成高质量摘要
包含来源URL引用
适用场景：研究问题、主题概述、对比分析

URL发现

提取与查询最相关的1-20个URL
适用于构建阅读列表和参考资源集合
返回包含标题和描述的URL
适用场景：资源收集、链接构建、研究准备

深度内容提取

默认（推荐）：
```
deep_search=false
```
- 响应速度最快，返回标题、描述和URL
可选：
```
deep_search=true
```
- 速度较慢，提取完整页面内容
重要提示： 大多数场景使用
```
deep_search=false
```
（默认值）即可完美运行
当deep_search=true时支持的格式：markdown、plain_text、simplified_html
仅在以下场景启用深度搜索：详细内容分析、存档或全面文本提取需求

域名过滤

包含特定域名（如github.com、stackoverflow.com）
排除域名以移除不需要的来源
组合多个域名进行聚焦搜索
适用场景：针对性研究、品牌监控、竞品分析

时间过滤

推荐： 使用
```
time_range
```
进行实时时效性过滤（小时、天、周、月、年）
替代方案： 使用
```
start_date
```
/
```
end_date
```
设置精确日期范围（YYYY-MM-DD）
注意：
```
time_range
```
和日期过滤器互斥
适用场景：实时新闻监控、近期动态、时间维度分析

Usage Patterns

使用模式

All examples below use the

./scripts/search.sh

wrapper for simplicity. For raw API usage, see the API Integration section.

以下示例均使用

./scripts/search.sh

包装脚本以简化操作。如需原生API使用，请查看API集成部分。

Basic Search

基础搜索

Quick search in fast mode (ALWAYS specify deep_search explicitly):

bash

./scripts/search.sh '{
  "query": "React Server Components tutorial",
  "deep_search": false
}'

For technical content, specify coding focus (still fast mode):

bash

./scripts/search.sh '{
  "query": "React Server Components tutorial",
  "focus": "coding",
  "deep_search": false
}'

快速搜索（请始终显式指定deep_search）：

bash

./scripts/search.sh '{
  "query": "React Server Components tutorial",
  "deep_search": false
}'

针对技术内容，指定编程聚焦模式（仍为快速模式）：

bash

./scripts/search.sh '{
  "query": "React Server Components tutorial",
  "focus": "coding",
  "deep_search": false
}'

Research with AI Summary

带AI摘要的研究

Get synthesized insights from multiple sources (fast mode works great with answer generation):

bash

./scripts/search.sh '{
  "query": "impact of AI on software development 2026",
  "deep_search": false,
  "include_answer": true
}'

从多个源获取合成见解（快速模式非常适合答案生成）：

bash

./scripts/search.sh '{
  "query": "impact of AI on software development 2026",
  "deep_search": false,
  "include_answer": true
}'

Domain-Specific Search

特定域名搜索

Target specific authoritative sources (fast mode):

bash

./scripts/search.sh '{
  "query": "async await patterns",
  "focus": "coding",
  "deep_search": false,
  "include_domains": ["github.com", "stackoverflow.com", "dev.to"],
  "max_results": 8
}'

针对权威源进行搜索（快速模式）：

bash

./scripts/search.sh '{
  "query": "async await patterns",
  "focus": "coding",
  "deep_search": false,
  "include_domains": ["github.com", "stackoverflow.com", "dev.to"],
  "max_results": 8
}'

Real-Time News Monitoring

实时新闻监控

Track current events and breaking news as they happen (fast mode):

bash

./scripts/search.sh '{
  "query": "latest developments in quantum computing",
  "focus": "news",
  "deep_search": false,
  "time_range": "week",
  "max_results": 15,
  "include_answer": true
}'

跟踪当前事件和突发新闻（快速模式）：

bash

./scripts/search.sh '{
  "query": "latest developments in quantum computing",
  "focus": "news",
  "deep_search": false,
  "time_range": "week",
  "max_results": 15,
  "include_answer": true
}'

Academic Research - Fast Mode (Recommended)

学术研究 - 推荐使用快速模式

Find and synthesize scholarly content using fast mode:

bash

./scripts/search.sh '{
  "query": "machine learning interpretability methods",
  "focus": "academic",
  "deep_search": false,
  "max_results": 20,
  "include_answer": true
}'

When to use deep mode: Only use

"deep_search": true

if you need full paper content extracted for archiving:

bash

./scripts/search.sh '{
  "query": "machine learning interpretability methods",
  "focus": "academic",
  "deep_search": true,
  "max_results": 5,
  "output_format": "markdown"
}'

Note: Deep mode is 5-15x slower. Use only when specifically needed.

使用快速模式查找并合成学术内容：

bash

./scripts/search.sh '{
  "query": "machine learning interpretability methods",
  "focus": "academic",
  "deep_search": false,
  "max_results": 20,
  "include_answer": true
}'

何时使用深度模式： 仅当你需要提取完整论文内容用于存档时，才设置

"deep_search": true

：

bash

./scripts/search.sh '{
  "query": "machine learning interpretability methods",
  "focus": "academic",
  "deep_search": true,
  "max_results": 5,
  "output_format": "markdown"
}'

注意： 深度模式速度慢5-15倍。仅在特定需求下使用。

Real-Time Shopping Research

实时购物研究

Compare products and current prices (fast mode):

bash

./scripts/search.sh '{
  "query": "best mechanical keyboards for programming",
  "focus": "shopping",
  "deep_search": false,
  "max_results": 10,
  "include_answer": true
}'

对比产品和当前价格（快速模式）：

bash

./scripts/search.sh '{
  "query": "best mechanical keyboards for programming",
  "focus": "shopping",
  "deep_search": false,
  "max_results": 10,
  "include_answer": true
}'

Parallel Search Strategies

并行搜索策略

When to Use Parallel Searches

何时使用并行搜索

Run multiple real-time searches in parallel when:

Comparing perspectives: Search the same topic across different focus modes
Multi-faceted research: Investigate different aspects of a topic simultaneously
Competitive analysis: Search multiple domains or competitors at once
Real-time monitoring: Track multiple topics or keywords concurrently
Cross-validation: Verify information across different source types in real-time

在以下场景中并行运行多个实时搜索：

对比视角：在不同聚焦模式下搜索同一主题
多维度研究：同时研究主题的不同方面
竞品分析：同时搜索多个域名或竞品
实时监控：同时跟踪多个主题或关键词
交叉验证：实时在不同类型的源中验证信息

Implementation Methods

实现方法

Method 1: Background Processes (Recommended)

Run multiple searches concurrently using the wrapper script:

bash

undefined

方法1：后台进程（推荐）

使用包装脚本并行运行多个搜索：

bash

undefined

Start multiple searches in parallel

并行启动多个搜索

./scripts/search.sh '{"query": "React", "focus": "coding"}' > react_coding.json & ./scripts/search.sh '{"query": "React", "focus": "news"}' > react_news.json & ./scripts/search.sh '{"query": "React", "focus": "academic"}' > react_academic.json &

Wait for all to complete

等待所有搜索完成

wait

Combine results

合并结果

jq -s '.' react_*.json > combined_results.json


**Method 2: Loop with xargs (Controlled Parallelism)**

Process multiple queries with rate limiting:

```bash

jq -s '.' react_*.json > combined_results.json


**方法2：使用xargs循环（可控并行）**

通过速率限制处理多个查询：

```bash

Create queries file

创建查询文件

cat > queries.txt <<EOF {"query": "AI frameworks", "focus": "coding"} {"query": "AI regulation", "focus": "news"} {"query": "AI research", "focus": "academic"} EOF

Run with max 3 parallel processes

最多并行3个进程

cat queries.txt | xargs -n1 -P3 -I{} ./scripts/search.sh '{}'


**Method 3: Focus Mode Comparison**

Search the same query across different focus modes:

```bash
QUERY="artificial intelligence trends"

for focus in "general" "coding" "news" "academic"; do
  (
    ./scripts/search.sh "{\"query\": \"$QUERY\", \"focus\": \"$focus\"}" \
      > "${focus}_results.json"
  ) &
done

wait
echo "All searches complete!"

cat queries.txt | xargs -n1 -P3 -I{} ./scripts/search.sh '{}'


**方法3：聚焦模式对比**

在不同聚焦模式下搜索同一查询：

```bash
QUERY="artificial intelligence trends"

for focus in "general" "coding" "news" "academic"; do
  (
    ./scripts/search.sh "{\"query\": \"$QUERY\", \"focus\": \"$focus\"}" \
      > "${focus}_results.json"
  ) &
done

wait
echo "All searches complete!"

Best Practices for Parallel Execution

并行执行最佳实践

Rate Limiting: Limit parallel requests to 3-5 to avoid overwhelming the API
- Use
```
xargs -P3
```
  to set maximum concurrent requests
- Check your API tier limits before increasing parallelism

Error Handling: Capture and handle failures gracefully

bash

./scripts/search.sh '{"query": "test"}' || echo "Search failed" >> errors.log

Result Aggregation: Combine results after all searches complete

bash

# Wait for all searches
wait

# Merge JSON results
jq -s 'map(.results) | flatten' result*.json > combined.json

Progress Tracking: Monitor completion status

bash

echo "Running 5 parallel searches..."

for i in {1..5}; do
  ./scripts/search.sh "{\"query\": \"query$i\"}" > "result$i.json" &
done

wait
echo "All searches complete!"

速率限制：将并行请求限制在3-5个，避免超出API限制
- 使用
```
xargs -P3
```
  设置最大并发请求数
- 提升并行度前请查看你的API套餐限制

错误处理：优雅捕获并处理失败

bash

./scripts/search.sh '{"query": "test"}' || echo "Search failed" >> errors.log

结果聚合：所有搜索完成后合并结果

bash

# 等待所有搜索完成
wait

# 合并JSON结果
jq -s 'map(.results) | flatten' result*.json > combined.json

进度跟踪：监控完成状态

bash

echo "Running 5 parallel searches..."

for i in {1..5}; do
  ./scripts/search.sh "{\"query\": \"query$i\"}" > "result$i.json" &
done

wait
echo "All searches complete!"

Example: Multi-Perspective Research

示例：多视角研究

bash

#!/bin/bash

bash

#!/bin/bash

Research a topic across multiple focus modes simultaneously

同时在多个聚焦模式下研究同一主题

QUERY="artificial intelligence code generation" OUTPUT_DIR="./search_results" mkdir -p "$OUTPUT_DIR"

Run searches in parallel across different focus modes

在不同聚焦模式下并行运行搜索

for focus in "general" "coding" "news" "academic"; do ( ./scripts/search.sh "{ "query": "$QUERY", "focus": "$focus", "max_results": 10 }" > "$OUTPUT_DIR/${focus}_results.json" ) & done

Wait for all searches to complete

等待所有搜索完成

wait

Aggregate and analyze results

聚合并分析结果

jq -s '{ general: .[0].results, coding: .[1].results, news: .[2].results, academic: .[3].results }' "$OUTPUT_DIR"/*.json > "$OUTPUT_DIR/combined_analysis.json"

echo "✓ Multi-perspective search complete"

undefined

jq -s '{ general: .[0].results, coding: .[1].results, news: .[2].results, academic: .[3].results }' "$OUTPUT_DIR"/*.json > "$OUTPUT_DIR/combined_analysis.json"

echo "✓ 多视角搜索完成"

undefined

Performance Considerations

性能考量

Optimal Parallelism: 3-5 concurrent requests balances speed and API limits
Memory Usage: Each parallel request consumes memory; monitor for large result sets
Network Bandwidth: Parallel requests can saturate bandwidth on slow connections
API Costs: More parallel requests = faster API quota consumption

最优并行度：3-5个并发请求在速度和API限制间取得平衡
内存使用：每个并行请求都会占用内存；请监控大型结果集的内存使用
网络带宽：并行请求可能会在慢速网络下耗尽带宽
API成本：更多并行请求会更快消耗API配额

When NOT to Use Parallel Searches

何时不使用并行搜索

Single, focused query with one clear answer
Sequential research where each search informs the next
API quota is limited or expensive
Results need to be processed before next search
Simple URL collection that doesn't require multiple perspectives

单一、聚焦且答案明确的查询
顺序研究，后续搜索依赖前序结果
API配额有限或成本较高
需要先处理当前结果再进行下一次搜索
简单的URL收集，不需要多视角

API Integration

API集成

Note: For most use cases, use the

./scripts/search.sh

wrapper script shown in Usage Patterns. The raw API examples below are for advanced users who need direct API access or custom integration.

注意： 大多数场景下，请使用使用模式中展示的

./scripts/search.sh

包装脚本。以下原生API示例适用于需要直接API访问或自定义集成的高级用户。

Required Configuration

必要配置

Before making any API request, always validate the API key is configured:

bash

undefined

发起任何API请求前，请始终验证API密钥已配置：

bash

undefined

Validate API key is set

验证API密钥已设置

if [ -z "$NIMBLE_API_KEY" ]; then echo "❌ Nimble API key not configured." echo "Get your key at https://www.nimbleway.com/" echo "" echo "Set NIMBLE_API_KEY environment variable using your platform's method." exit 1 fi


The skill requires the `NIMBLE_API_KEY` environment variable. See [Prerequisites](#prerequisites) for platform-specific setup instructions.

Get your API key at: https://www.nimbleway.com/

if [ -z "$NIMBLE_API_KEY" ]; then echo "❌ Nimble API密钥未配置。" echo "前往https://www.nimbleway.com/获取密钥" echo "" echo "通过对应平台方式设置NIMBLE_API_KEY环境变量。" exit 1 fi


该技能需要`NIMBLE_API_KEY`环境变量。请查看[前置条件](#前置条件)获取各平台的设置说明。

前往以下地址获取API密钥：https://www.nimbleway.com/

API Endpoint

API端点

POST https://nimble-retriever.webit.live/search

POST https://nimble-retriever.webit.live/search

Request Format

请求格式

json

{
  "query": "search query string",  // REQUIRED
  "focus": "general",  // OPTIONAL: default "general" | coding|news|academic|shopping|social|geo|location
  "max_results": 10,  // OPTIONAL: default 10 (range: 1-100)
  "include_answer": false,  // OPTIONAL: default false
  "deep_search": false,  // OPTIONAL: default false (RECOMMENDED: keep false for speed)
  "output_format": "markdown",  // OPTIONAL: default "markdown" | plain_text|simplified_html
  "include_domains": ["domain1.com"],  // OPTIONAL: default [] (no filter)
  "exclude_domains": ["domain3.com"],  // OPTIONAL: default [] (no filter)
  "time_range": "week",  // OPTIONAL: hour|day|week|month|year
  "start_date": "2026-01-01",  // OPTIONAL: Use time_range OR start_date/end_date (not both)
  "end_date": "2026-12-31"  // OPTIONAL
}

Key Defaults:

```
focus
```
:
```
"general"
```
- Change to specific mode for targeted results
```
deep_search
```
:
```
false
```
- Keep false unless you need full page content
```
max_results
```
:
```
10
```
- Balanced speed and coverage

json

{
  "query": "search query string",  // 必填
  "focus": "general",  // 可选：默认值为"general" | coding|news|academic|shopping|social|geo|location
  "max_results": 10,  // 可选：默认值为10（范围：1-100）
  "include_answer": false,  // 可选：默认值为false
  "deep_search": false,  // 可选：默认值为false（推荐：保持false以提升速度）
  "output_format": "markdown",  // 可选：默认值为"markdown" | plain_text|simplified_html
  "include_domains": ["domain1.com"],  // 可选：默认值为[]（无过滤）
  "exclude_domains": ["domain3.com"],  // 可选：默认值为[]（无过滤）
  "time_range": "week",  // 可选：hour|day|week|month|year
  "start_date": "2026-01-01",  // 可选：请使用time_range或start_date/end_date（不可同时使用）
  "end_date": "2026-12-31"  // 可选
}

关键默认值：

```
focus
```
:
```
"general"
```
- 如需针对性结果，请切换为特定模式
```
deep_search
```
:
```
false
```
- 除非需要完整页面内容，否则保持默认值
```
max_results
```
:
```
10
```
- 在速度和覆盖范围间取得平衡

Response Format

响应格式

json

{
  "results": [
    {
      "url": "https://example.com/page",
      "title": "Page Title",
      "description": "Page description",
      "content": "Full page content (if deep_search=true)",
      "published_date": "2026-01-15"
    }
  ],
  "include_answer": "AI-generated summary (if include_answer=true)",
  "urls": ["url1", "url2", "url3"],
  "total_results": 10
}

json

{
  "results": [
    {
      "url": "https://example.com/page",
      "title": "Page Title",
      "description": "Page description",
      "content": "Full page content (if deep_search=true)",
      "published_date": "2026-01-15"
    }
  ],
  "include_answer": "AI-generated summary (if include_answer=true)",
  "urls": ["url1", "url2", "url3"],
  "total_results": 10
}

Best Practices

最佳实践

Focus Mode Selection

聚焦模式选择

Use
coding
for:

Programming questions
Technical documentation
Code examples and tutorials
API references
Framework guides

Use
news
for:

Real-time current events
Breaking stories as they happen
Recent announcements
Trending topics
Time-sensitive information

Use
academic
for:

Research papers
Scholarly articles
Scientific studies
Academic journals
Citations and references

Use
shopping
for:

Product searches
Price comparisons
E-commerce research
Product reviews
Buying guides

Use
social
for:

Real-time social media monitoring
Live community discussions
Current user-generated content
Trending hashtags and topics
Real-time public sentiment

Use
geo
for:

Geographic information
Regional data
Maps and locations
Area-specific queries

Use
location
for:

Local business searches
Place-specific information
Nearby services
Regional recommendations

使用
coding
模式：

编程问题
技术文档
代码示例和教程
API参考
框架指南

使用
news
模式：

实时当前事件
突发新闻
近期公告
热门话题
时效性信息

使用
academic
模式：

研究论文
学术文章
科学研究
学术期刊
引用和参考文献

使用
shopping
模式：

产品搜索
价格对比
电商研究
产品评测
购买指南

使用
social
模式：

实时社交媒体监控
实时社区讨论
当前用户生成内容
热门话题标签
实时公众情绪

使用
geo
模式：

地理信息
区域数据
地图和位置
特定区域查询

使用
location
模式：

本地商家搜索
特定地点信息
周边服务
区域推荐

Result Limits

结果数量限制

Quick searches: 5-10 results for fast overview
Comprehensive research: 15-20 results for depth
Answer generation: 10-15 results for balanced synthesis
URL collection: 20 results for comprehensive resource list

快速搜索：5-10个结果，快速概览
全面研究：15-20个结果，深入分析
答案生成：10-15个结果，平衡合成质量
URL收集：20个结果，全面资源列表

When to Use LLM Answers

何时使用LLM答案

✅ Use LLM answers when:

You need a synthesized overview of a topic
Comparing multiple sources or approaches
Summarizing recent developments
Answering specific questions
Creating research summaries

❌ Skip LLM answers when:

You just need a list of URLs
Building a reference collection
Speed is critical
You want to analyze sources manually
Original source text is needed

✅ 使用LLM答案的场景：

需要主题的合成概述
对比多个源或方法
总结近期动态
回答特定问题
创建研究摘要

❌ 不使用LLM答案的场景：

仅需要URL列表
构建参考资源集合
对速度要求极高
需要手动分析源内容
需要原始源文本

Content Extraction

内容提取

Default (Recommended):
deep_search=false

The default setting works for 95% of use cases:

✅ Fastest response times
✅ Returns titles, descriptions, URLs
✅ Works perfectly with
```
include_answer=true
```
✅ Sufficient for research, comparisons, and URL discovery

Only use
deep_search=true
when you specifically need:

Full page content extraction
Archiving complete articles
Processing full text for analysis
Building comprehensive datasets

Performance impact:

```
deep_search=false
```
: ~1-3 seconds
```
deep_search=true
```
: ~5-15 seconds (significantly slower)

默认（推荐）：
deep_search=false

默认设置适用于95%的场景：

✅ 响应速度最快
✅ 返回标题、描述和URL
✅ 与
```
include_answer=true
```
完美兼容
✅ 满足研究、对比和URL发现需求

仅在以下场景使用
deep_search=true
：

完整页面内容提取
完整文章存档
处理完整文本用于分析
构建全面数据集

性能影响：

```
deep_search=false
```
: ~1-3秒
```
deep_search=true
```
: ~5-15秒（显著变慢）

Error Handling

错误处理

Common Issues

常见问题

Authentication Failed

Verify NIMBLE_API_KEY is set correctly
Check API key is active at nimbleway.com
Ensure key has search API access

Rate Limiting

Reduce max_results
Add delays between requests
Check your plan limits
Consider upgrading API tier

No Results

Try different focus mode
Broaden search query
Remove domain filters
Adjust date filters

Timeout Errors

Reduce max_results
Disable deep content extraction
Simplify query
Try again after brief delay

身份验证失败

验证NIMBLE_API_KEY是否设置正确
在nimbleway.com检查API密钥是否有效
确保密钥具备搜索API访问权限

速率限制

减少max_results数量
在请求间添加延迟
查看你的套餐限制
考虑升级API套餐

无结果返回

尝试不同的聚焦模式
放宽搜索查询
移除域名过滤器
调整日期过滤器

超时错误

减少max_results数量
禁用深度内容提取
简化查询
短暂延迟后重试

Performance Tips

性能优化技巧

Use Defaults: Keep
```
deep_search=false
```
(default) for 5-10x faster responses
Start Simple: Begin with just
```
{"query": "..."}
```
- defaults work great
Choose Right Focus: Proper focus mode dramatically improves relevance (default: "general")
Optimize Result Count: Default of 10 results balances speed and coverage
Domain Filtering: Pre-filter sources for faster, more relevant results
Avoid Deep Search: Only enable
```
deep_search=true
```
when you truly need full content
Batch Queries: Group related searches to minimize API calls
Cache Results: Store results locally when appropriate

使用默认值：保持
```
deep_search=false
```
（默认值），响应速度提升5-10倍
从简开始：初始仅使用
```
{"query": "..."}
```
- 默认设置效果优异
选择正确的聚焦模式：合适的聚焦模式可显著提升结果相关性（默认："general"）
优化结果数量：默认10个结果在速度和覆盖范围间取得平衡
域名过滤：预先过滤源，获取更快速、更相关的结果
避免深度搜索：仅在确实需要完整内容时启用
```
deep_search=true
```
批量查询：将相关搜索分组，减少API调用次数
缓存结果：在合适的场景下本地存储结果

Integration Examples

集成示例

See the

examples/

directory for detailed integration patterns:

```
basic-search.md
```
- Simple search implementation
```
deep-research.md
```
- Multi-step research workflow
```
competitive-analysis.md
```
- Domain-specific research pattern

See

references/

directory for detailed documentation:

```
focus-modes.md
```
- Complete focus mode guide
```
search-strategies.md
```
- Advanced search patterns
```
api-reference.md
```
- Full API documentation

查看

examples/

目录获取详细集成模式：

```
basic-search.md
```
- 简单搜索实现
```
deep-research.md
```
- 多步骤研究流程
```
competitive-analysis.md
```
- 特定域名研究模式

查看

references/

目录获取详细文档：

```
focus-modes.md
```
- 完整聚焦模式指南
```
search-strategies.md
```
- 高级搜索模式
```
api-reference.md
```
- 完整API文档

Scripts

脚本

search.sh - Main Search Wrapper

search.sh - 主搜索包装脚本

The recommended way to use the Nimble Search API:

bash

./scripts/search.sh '{"query": "your search", "focus": "coding"}'

Features:

Automatic authentication with
```
$NIMBLE_API_KEY
```
Platform detection (claude-code, github-copilot, vscode, cli)
Request tracking headers for analytics
JSON validation and error handling
Formatted output with
```
jq
```

Usage:

bash

undefined

使用Nimble Search API的推荐方式：

bash

./scripts/search.sh '{"query": "your search", "focus": "coding"}'

特性：

使用
```
$NIMBLE_API_KEY
```
自动处理身份验证
平台检测（claude-code、github-copilot、vscode、cli）
用于分析的请求跟踪标头
JSON验证和错误处理
使用
```
jq
```
格式化输出

使用方法：

bash

undefined

Basic search

基础搜索

./scripts/search.sh '{"query": "React hooks"}'

With all options

全选项搜索

./scripts/search.sh '{ "query": "AI frameworks", "focus": "coding", "max_results": 15, "include_answer": true, "include_domains": ["github.com"] }'

undefined

./scripts/search.sh '{ "query": "AI frameworks", "focus": "coding", "max_results": 15, "include_answer": true, "include_domains": ["github.com"] }'

undefined

validate-query.sh - API Configuration Test

validate-query.sh - API配置测试

Test your API configuration and connectivity:

bash

./scripts/validate-query.sh "test query" general

This verifies:

API key is configured
Endpoint is accessible
Response format is correct
Focus mode is supported

测试你的API配置和连通性：

bash

./scripts/validate-query.sh "test query" general

该脚本会验证：

API密钥已配置
端点可访问
响应格式正确
聚焦模式受支持