> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nimbleway.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Nimble Web Expert

> Turn your AI coding assistant into a web scraping expert

The Nimble Web Expert skill gives your agent the ability to search, extract, scrape, map, crawl, and run pre-built extraction agents across any website. Fast, incremental, and immediately responsive. This is the only way your AI assistant can access live websites.

Powered by the [Nimble CLI](https://www.npmjs.com/package/@nimble-way/nimble-cli) and built on the open-source [Agent Skills](https://agentskills.io) standard for cross-platform agent compatibility.

<Card icon="github" href="https://github.com/Nimbleway/agent-skills/tree/main/skills/nimble-web-expert" title="View on GitHub">
  Source code for this skill
</Card>

## Tools Overview

| Tool | Description |
| - | - |
| **Search** | Accurate, real-time web search. 8 focus modes: general, coding, news, academic, shopping, social, geo, location. |
| **Extract** | Scalable data collection with stealth unblocking. Get clean, real-time HTML and structured data from any URL. Supports JS rendering and browser emulation. |
| **Map** | Fast URL discovery and site structure mapping. Plan extraction workflows before running them. |
| **Crawl** | Extract contents from entire websites in a single request. Collect large volumes of web data automatically. |
| **Agents** | Run pre-built extraction agents for structured data from popular websites (Amazon, Google, LinkedIn, and hundreds more). |

## Quick Install

<Tabs>
  <Tab title="Claude Code" icon="https://mintcdn.com/nimble-f5a8283f/cYuR4-Ul5fdRDxFH/images/icons/anthropic.svg?fit=max&auto=format&n=cYuR4-Ul5fdRDxFH&q=85&s=83583e95919ccfbce43a03d826d1a450" width="24" height="24" data-path="images/icons/anthropic.svg">
    <Steps>
      <Step title="Run this command in your terminal">
        Installs the Nimble skills and configures the MCP server.

        ```bash theme={"system"}
        claude plugin marketplace add Nimbleway/agent-skills && \
        claude plugin install nimble@nimble-plugin-marketplace
        ```
      </Step>

      <Step title="Verify installation">
        Run `/mcp` and confirm `nimble` appears in your connected servers.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Cursor" icon="https://mintcdn.com/nimble-f5a8283f/dCAomSe8Qhpb-TMg/images/icons/cursor.svg?fit=max&auto=format&n=dCAomSe8Qhpb-TMg&q=85&s=5d6d2ba4978a90f8ac20e1f15873200b" width="467" height="532" data-path="images/icons/cursor.svg">
    <Steps>
      <Step title="Add the MCP server">
        One click, then confirm the install in Cursor.

        <a href="cursor://anysphere.cursor-deeplink/mcp/install?name=nimble-mcp-server&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLm5pbWJsZXdheS5jb20vbWNwIiwiaGVhZGVycyI6eyJBdXRob3JpemF0aW9uIjoiQmVhcmVyIE5JTUJMRV9BUElfS0VZIn19">
          <img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Add to Cursor" noZoom style={{height: "32px"}} />
        </a>

        Then replace `NIMBLE_API_KEY` in **Settings → MCP Servers → nimble-mcp-server** with your [Nimble API key](https://online.nimbleway.com/settings/api-keys). The deeplink ships a placeholder, not a key.
      </Step>

      <Step title="Add the skills">
        Teaches the agent which Nimble product fits a given job.

        ```bash theme={"system"}
        npx skills add Nimbleway/agent-skills -a cursor
        ```
      </Step>

      <Step title="Verify installation">
        Open Settings, then MCP, and confirm `nimble-mcp-server` is listed.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Vercel CLI" icon="https://mintcdn.com/nimble-f5a8283f/QI59WYrXlaO5IK3k/images/icons/vercel.svg?fit=max&auto=format&n=QI59WYrXlaO5IK3k&q=85&s=d8fc3dacb6ed1105d08c0385d0d0f573" width="24" height="24" data-path="images/icons/vercel.svg">
    <Steps>
      <Step title="Run this command in your terminal">
        Installs the Nimble skills into your project.

        ```bash theme={"system"}
        npx skills add Nimbleway/agent-skills
        ```
      </Step>

      <Step title="Verify installation">
        Run `npx skills add Nimbleway/agent-skills --list` to see what was installed.
      </Step>
    </Steps>
  </Tab>
</Tabs>

## Prerequisites

### 1. Nimble CLI

Install the Nimble CLI globally:

```bash theme={"system"}
npm i -g @nimble-way/nimble-cli
```

Verify with:

```bash theme={"system"}
nimble --version
```

### 2. Nimble API Key

Get your key at [online.nimbleway.com](https://online.nimbleway.com/).

Set the `NIMBLE_API_KEY` environment variable using your platform's method:

<Tabs>
  <Tab title="Claude Code">
    Add to `~/.claude/settings.json`:

    ```json theme={"system"}
    {
      "env": {
        "NIMBLE_API_KEY": "your-api-key-here"
      }
    }
    ```
  </Tab>

  <Tab title="Shell / Terminal">
    ```bash theme={"system"}
    export NIMBLE_API_KEY="your-api-key-here"
    ```

    Or add to your shell profile (`~/.bashrc`, `~/.zshrc`):

    ```bash theme={"system"}
    echo 'export NIMBLE_API_KEY="your-api-key-here"' >> ~/.zshrc
    ```
  </Tab>

  <Tab title="VS Code / GitHub Copilot">
    * Add skills to `.github/skills/` in your repository
    * Configure API key using GitHub Actions secrets in the copilot environment
    * Or set as environment variable in your shell
  </Tab>
</Tabs>

## Quick Start

The Nimble Web Expert skill activates automatically when you ask for live web data:

```
"Search for recent AI developments"
  -> nimble search --query "recent AI developments" --search-depth lite

"Extract the content from this URL"
  -> nimble extract run --url "https://example.com" --parse --format markdown

"Scrape prices from this product page"
  -> nimble extract run --url "https://example.com/product" --render --parse --format markdown

"Map all the pages on this docs site"
  -> nimble map --url "https://docs.example.com" --limit 100

"Crawl the API docs section"
  -> nimble crawl run --url "https://docs.example.com/api" --limit 50
```

<Tip>
  Use this skill for immediate, one-off data needs. For workflows you will run
  repeatedly, have it build an [Extract Template](/nimble-sdk/web-tools/extract/template)
  or schedule an [Extract Job](/nimble-sdk/agentic/jobs) instead.
</Tip>

## Command Examples

### Search

Accurate, real-time web search with 8 focus modes (general, coding, news, academic, shopping, social, geo, location).

```bash theme={"system"}
# Lite search (default, fast, token-efficient)
nimble search --query "React hooks tutorial" --focus coding --search-depth lite

# Search with AI-generated answer summary
nimble search --query "what is WebAssembly" --include-answer --search-depth lite

# News search with time filter
nimble search --query "AI developments" --focus news --time-range week --search-depth lite

# Domain-filtered search
nimble search --query "auth best practices" \
  --include-domain github.com \
  --include-domain stackoverflow.com \
  --search-depth lite
```

<Tip>
  Use `--search-depth lite` (default) for fast responses (1-3s). Use
  `--search-depth deep` when you need full page content for archiving or
  full-text analysis.
</Tip>

### Extract

Get clean, structured data from any URL with stealth unblocking and JS rendering.

```bash theme={"system"}
# Standard extraction (always use --parse --format markdown)
nimble extract run --url "https://example.com/article" --parse --format markdown

# Render JavaScript for SPAs and dynamic content
nimble extract run --url "https://example.com/app" --render --parse --format markdown

# Extract with geolocation
nimble extract run --url "https://example.com" --country US --city "New York" --parse --format markdown
```

### Map

Discover all URLs on a site to plan extraction workflows.

```bash theme={"system"}
# Map URLs on a site
nimble map --url "https://docs.example.com" --limit 100

# Include subdomains
nimble map --url "https://example.com" --domain-filter subdomains
```

### Crawl

Extract content from entire websites asynchronously.

```bash theme={"system"}
# Start a crawl (always set --limit)
nimble crawl run --url "https://docs.example.com" --limit 50

# Crawl with path filtering
nimble crawl run --url "https://example.com" \
  --include-path "/docs" \
  --include-path "/api" \
  --limit 100

# Check crawl status
nimble crawl status --id "crawl-id"

# List all crawls
nimble crawl list
```

<Tip>
  For LLM-friendly output, prefer `map` + `extract --parse --format markdown` on
  individual pages. Crawl returns raw HTML which can be very large.
</Tip>

## One-off data vs reusable workflows

This skill covers both, so the choice is which Nimble product it reaches for:

| | **Immediate data** | **Reusable workflow** |
| - | - | - |
| **Reach for** | Search, Extract, Map, Crawl | [Extract Template](/nimble-sdk/web-tools/extract/template), [Extract Jobs](/nimble-sdk/agentic/jobs) |
| **Speed** | Fast and direct | Slower to set up, then repeatable |
| **Output** | Extracted data now | A template or a scheduled job |
| **Use when** | "Get me this data now" | "I'll need this repeatedly" |

For open-ended research with citations rather than extraction, use a [Web Search Agent](/nimble-sdk/web-search-agents/overview).

## About Agent Skills

This skill follows the [Agent Skills](https://agentskills.io) open-source standard, making it compatible with multiple AI agent platforms. Install using the [Skills CLI](https://www.npmjs.com/package/skills), the standard package manager for the Agent Skills ecosystem.

## Full Command Reference

For the complete list of options, flags, and advanced usage patterns, see the [SKILL.md on GitHub](https://github.com/Nimbleway/agent-skills/blob/main/skills/nimble-web-expert/SKILL.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.