How do I install the Nimble Map skill?

Run npx skillmds@latest add yigityildiz0/nimble-map in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Nimble Map safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Nimble Map?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Nimble Map free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Nimble Map?

yigityildiz0 (@yigityildiz0) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Nimble Map by yigityildiz0 — Agent Skill

Name: Nimble Map
Author: yigityildiz0

File contents

nimble map — reference

Discovers all URLs on a site in seconds. Returns URL metadata (url, title, description) — run extract on results to get page content. Single synchronous call — no polling required.

Parameters
CLI
Python SDK
Response
Common patterns
Map vs Crawl

Parameters

Parameter	CLI flag	Type	Default	Description
`url`	`--url`	string	required	Starting URL
`limit`	`--limit`	int	`100`	Max URLs returned (1–100,000)
`sitemap`	`--sitemap`	string	`include`	`include` (sitemap + crawl) \| `only` (sitemap only, fastest) \| `skip` (crawl only)
`domain_filter`	`--domain-filter`	string	—	`domain` (exact) \| `subdomain` (include subdomains) \| `all` (follow all links)
`country`	`--country`	string	`ALL`	ISO Alpha-2 proxy location (e.g. `US`)
`locale`	`--locale`	string	—	LCID locale (e.g. `en-US`) or `auto`

CLI

nimble map --url "https://docs.example.com" --limit 100

# Sitemap only (fastest)
nimble map --url "https://example.com" --sitemap only --limit 500

# Extract just the URL list
nimble --transform "links.#.url" map --url "https://docs.example.com" --limit 100

Python SDK

from nimble_python import Nimble
nimble = Nimble(api_key=os.environ["NIMBLE_API_KEY"])

resp = nimble.map(url="https://docs.example.com", limit=100, sitemap="include")
links = resp.links  # list of link objects
urls = [l.url for l in links]

Response

Field	Type	Description
`task_id`	string	Request identifier
`success`	boolean	Whether the request succeeded
`links`	array	Discovered URLs
`links[].url`	string	The discovered URL
`links[].title`	string	Page title (if available)
`links[].description`	string	Page meta description (if available)

Common patterns

# Map → filter → extract
nimble --transform "links.#.url" map --url "https://docs.stripe.com" --limit 200 > .nimble/urls.txt
grep "charges\|refund" .nimble/urls.txt

# Specific path section
nimble map --url "https://shop.example.com/products/" --limit 200

Map vs Crawl

	`map`	`crawl`
Speed	Seconds (sync)	Minutes (async)
Output	URL list with metadata	Full page content per URL
Best for	Discover URLs, then selectively extract	Archive all pages at once
LLM use	✅ Combine with `extract --format markdown`	⚠️ Returns raw HTML

---name: nimble-mapdescription: "Reference for nimble map command. Load when discovering URLs on a site before bulk extraction. Contains: all flags (limit 1-100000, sitemap."---# nimble map — referenceDiscovers all URLs on a site in seconds. Returns URL metadata (url, title, description) — run `extract` on results to get page content. Single synchronous call — no polling required.## Table of Contents- [Parameters](#parameters)- [CLI](#cli)- [Python SDK](#python-sdk)- [Response](#response)- [Common patterns](#common-patterns)- [Map vs Crawl](#map-vs-crawl)---## Parameters| Parameter | CLI flag | Type | Default | Description || --------------- | ----------------- | ------ | --------- | ------------------------------------------------------------------------------------ || `url` | `--url` | string | required | Starting URL || `limit` | `--limit` | int | `100` | Max URLs returned (1–100,000) || `sitemap` | `--sitemap` | string | `include` | `include` (sitemap + crawl) \| `only` (sitemap only, fastest) \| `skip` (crawl only) || `domain_filter` | `--domain-filter` | string | — | `domain` (exact) \| `subdomain` (include subdomains) \| `all` (follow all links) || `country` | `--country` | string | `ALL` | ISO Alpha-2 proxy location (e.g. `US`) || `locale` | `--locale` | string | — | LCID locale (e.g. `en-US`) or `auto` |## CLI```bashnimble map --url "https://docs.example.com" --limit 100# Sitemap only (fastest)nimble map --url "https://example.com" --sitemap only --limit 500# Extract just the URL listnimble --transform "links.#.url" map --url "https://docs.example.com" --limit 100```## Python SDK```pythonfrom nimble_python import Nimblenimble = Nimble(api_key=os.environ["NIMBLE_API_KEY"])resp = nimble.map(url="https://docs.example.com", limit=100, sitemap="include")links = resp.links # list of link objectsurls = [l.url for l in links]```## Response| Field | Type | Description || --------------------- | ------- | ------------------------------------ || `task_id` | string | Request identifier || `success` | boolean | Whether the request succeeded || `links` | array | Discovered URLs || `links[].url` | string | The discovered URL || `links[].title` | string | Page title (if available) || `links[].description` | string | Page meta description (if available) |---## Common patterns```bash# Map → filter → extractnimble --transform "links.#.url" map --url "https://docs.stripe.com" --limit 200 > .nimble/urls.txtgrep "charges\|refund" .nimble/urls.txt# Specific path sectionnimble map --url "https://shop.example.com/products/" --limit 200```---## Map vs Crawl| | `map` | `crawl` || -------- | ------------------------------------------- | ------------------------- || Speed | Seconds (sync) | Minutes (async) || Output | URL list with metadata | Full page content per URL || Best for | Discover URLs, then selectively extract | Archive all pages at once || LLM use | ✅ Combine with `extract --format markdown` | ⚠️ Returns raw HTML |

Frequently asked questions

Nimble Map