Anycrawl

Web scraping, search, crawling, and site mapping via the AnyCrawl CLI. Use when the user wants to search the web, scrape a page, find URLs on a site, or bulk...

Security Scan

The skill is an instruction-only wrapper for the AnyCrawl CLI and its instructions, install guidance, and security notes are consistent with that purpose; a minor metadata mismatch about environment variables should be fixed before trusting it fully.

Purpose & Capability

The name/description match the instructions: the skill expects the AnyCrawl CLI and explains search/scrape/map/crawl workflows. Nothing requested or documented is unrelated to web crawling/scraping.

Instruction Scope

SKILL.md only instructs use of the anycrawl CLI and contains safe-sounding handling guidance (write outputs to .anycrawl/, incremental reads, URL quoting, avoid returning fetched pages directly). It does not instruct reading unrelated system files or exfiltrating data.

Install Mechanism

There is no formal install spec (instruction-only), and install guidance points to the npm package anycrawl-cli and npx usage — a standard approach. Users should still verify the npm package and upstream docs before installing.

Credentials

SKILL.md and rules/install.md reference an ANYCRAWL_API_KEY and describe persistent credentials in ~/.config or %APPDATA%, but the skill metadata lists no required environment variables or primary credential. The skill should declare ANYCRAWL_API_KEY (or be explicit it is optional).

Persistence & Privilege

The skill is not forced-always, is user-invocable, and does not request persistent platform privileges or modify other skills' configs. Autonomous invocation is allowed by default but not unusual here.

Assessment

This skill is an instruction-only wrapper for the AnyCrawl CLI and appears internally consistent with that purpose. Before installing or using it: 1) Verify the upstream npm package (anycrawl-cli) and its source/release provenance; prefer using npx if you don't want a global install. 2) Be aware the CLI fetches arbitrary third‑party web content and will store an API key under your user config directory — use a scoped/rotatable key and inspect where it is stored. 3) The SKILL.md references ANYCRAWL_API_KEY but the skill metadata doesn't declare it; ask the author to declare required env vars explicitly. 4) Follow the included security advice (write output to .anycrawl/, add to .gitignore, and read files incrementally) to reduce prompt‑injection and data exposure risk.

AnyCrawl CLI

Web scraping, search, and crawling CLI. Returns clean markdown optimized for LLM context windows. Default engine: playwright.

Run anycrawl --help or anycrawl <command> --help for full option details.

Prerequisites

Must be installed and authenticated. Run anycrawl login or set ANYCRAWL_API_KEY.

If not ready, see rules/install.md. For output handling guidelines, see rules/security.md.

Commands

• Search - No specific URL yet. Find pages, answer questions. Use --scrape to get full page content with results.
• Scrape - Have a URL. Extract its content directly.
• Map - Need to locate a specific page on a site. Discover URLs, then scrape the ones you need.
• Crawl - Need bulk content from a site or section. Use crawl directly — no need for map first.

Need	Command	When
Find pages on a topic	search	No specific URL yet
Get a page's content	scrape	Have a URL
Find URLs within a site	map	Need to locate a specific subpage
Bulk extract a site section	crawl	Need many pages (e.g., all /docs/)

For detailed command reference, run anycrawl <command> --help (e.g., anycrawl search, anycrawl scrape).

Avoid redundant fetches: search --scrape already fetches full page content. Don't re-scrape those URLs. Check .anycrawl/ for existing data before fetching again.

Output & Organization

Write results to .anycrawl/ with -o. Add .anycrawl/ to .gitignore. Always quote URLs in shell commands. Never read entire output files at once — use grep, head, or incremental reads.

Documentation

• AnyCrawl API Docs