Skip to main content
Install the Nimble plugin and your AI coding assistant can create Web Search Agents for any website, extract structured data at scale, and search the live web — all from natural language prompts.

​
Prerequisites

1. Nimble CLI — Required by the nimble-web-tools skill: 
npm install -g @nimble-way/nimble-cli
2. Nimble API Key — Get yours from Account Settings and set it as an environment variable: 
export NIMBLE_API_KEY="your-api-key"
Or persist it in ~/.claude/settings.json for Claude Code: 
{
  "env": {
    "NIMBLE_API_KEY": "your-api-key"
  }
}

​
Installation

Install from the Nimble Marketplace — this adds both skills and configures the MCP server automatically:
claude plugin marketplace add Nimbleway/agent-skills &&
claude plugin install nimble@nimble-plugin-marketplace
Or load directly from a local clone:
git clone https://github.com/Nimbleway/agent-skills.git &&
claude --plugin-dir /path/to/agent-skills

​
What’s Included

Agent Skills are plug-and-play extensions that give AI coding assistants direct access to Nimble’s web data tools. Install once and your AI can search the live web, extract pages, map sites, and run structured data agents — automatically, from natural language.
SkillDescription
nimble-web-toolsReal-time web intelligence — search, extract, map, and crawl via the Nimble CLI
nimble-agentsFind, generate, and run agents to extract structured data from any website
MCP ServerPre-configured Nimble MCP server connection for agent-to-API access

​
nimble-web-tools Skill

The nimble-web-tools skill activates automatically when you ask your AI assistant to search the web, extract a page, map a site, or crawl for content.

​
What it can do

ToolWhat it does
SearchReal-time web search with 8 focus modes: general, coding, news, academic, shopping, social, geo, location
ExtractGet clean HTML or markdown from any URL — supports JS rendering and stealth unblocking
MapDiscover all URLs in a domain or sitemap — useful for planning extraction workflows
CrawlExtract content from an entire website in one request

​
Example prompts

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

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

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

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

# Lite search (default — fast, token-efficient)
nimble search --query "React hooks tutorial" --topic coding --search-depth lite

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

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

# Filter to specific domains
nimble search --query "auth best practices" \
  --include-domain github.com \
  --include-domain stackoverflow.com \
  --search-depth lite
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.

​
Extract

# Standard extraction — always pass --parse --format markdown for LLM-readable output
nimble extract --url "https://example.com/article" --parse --format markdown

# With JavaScript rendering (for SPAs and dynamic pages)
nimble extract --url "https://example.com/app" --render --parse --format markdown

# With geo-targeting
nimble extract --url "https://example.com" --country US --city "New York" --parse --format markdown

​
Map

# Discover all 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

# Crawl a site (always set --limit)
nimble crawl run --url "https://docs.example.com" --limit 50

# Filter to specific paths
nimble crawl run --url "https://example.com" \
  --include-path "/docs" \
  --include-path "/api" \
  --limit 100

# Check crawl status
nimble crawl status --id "crawl-id"
For LLM-friendly output, prefer map + extract --parse --format markdown on individual pages rather than crawl — crawl returns raw HTML which can be very large.

​
nimble-agents Skill

The nimble-agents skill gives your AI assistant the power to extract structured data from any website. It uses a find-or-generate workflow: search for an existing agent, run it, and get structured data. If no agent exists for a site, it generates a custom one automatically.

​
How it works

1

Search

Find an existing agent matching your target website using nimble_agents_list
2

Inspect

Review the agent’s input/output schema with nimble_agents_get
3

Run

Execute the agent and get clean, structured results via nimble_agents_run
4

Generate

If no existing agent fits, create a custom one with nimble_agents_generate
5

Publish

Save generated agents for future reuse with nimble_agents_publish

​
Usage

Use the slash command:
/nimble:nimble-agents extract product details from this Amazon page: https://www.amazon.com/dp/B0DGHRT7PS
Or just describe what you need in plain language — the skill activates automatically when relevant.

​
MCP Tools

ToolPurpose
nimble_agents_listBrowse agents by keyword
nimble_agents_getGet agent details and input/output schema
nimble_agents_generateCreate a custom agent via natural language
nimble_agents_runExecute an agent and get structured results
nimble_agents_publishSave a generated agent for reuse

​
Source Code

agent-skills on GitHub

Plugin source, skill definitions, and SKILL.md references

Plugin Installation

Detailed platform-specific installation guide

Web Tools Skill

Full command reference for nimble-web-tools

Agents Skill

Full guide for the nimble-agents skill