Add Firecrawl skill for web scraping, search, and content extraction

[leonardogrig]

I'm Leo, dev rel at Firecrawl. The agent-skills collection already covers WordPress development patterns well, but agents often need to pull in web content too: docs, changelogs, API references. Adding Firecrawl here so WordPress developers get a clean way to search, scrape, and extract web data as LLM-friendly markdown.

If you need help with the integration, extra API credits for the community, or anything else, feel free to reach out.

---

What this adds

A new firecrawl skill that gives AI assistants the ability to search the web, scrape pages, and extract clean markdown content via the Firecrawl CLI. This adds a web data layer that complements the existing WordPress-focused skills.

Files:

• skills/firecrawl/SKILL.md - Main skill instructions: CLI usage, search/scrape/map commands, parallelization, output organization
• skills/firecrawl/references/install.md - Installation, authentication, and troubleshooting reference

Why this matters for Agent Skills

The existing skills are excellent at teaching AI assistants how to build WordPress. But many WordPress development tasks also require pulling in information from the web: reading documentation, checking API references, researching plugin approaches, or looking up code examples.

Firecrawl fills the gap between "the agent knows WordPress patterns" and "the agent can fetch live web content." When an AI assistant needs to check the latest WordPress docs, scrape a plugin's changelog, or search for a Gutenberg deprecation notice, this skill gives it a structured way to do that.

What it adds:

• Web search with optional scraping - find and read relevant pages in one step
• Full page scraping to clean markdown - handles JS-rendered pages, removes nav/ads/footers
• Site-wide URL discovery - map all URLs on a domain before targeted scraping
• Parallel execution - run multiple scrapes concurrently for speed
• File-based output - results go to .firecrawl/ to keep agent context clean

Example usage

# Search WordPress docs for block deprecation patterns
firecrawl search "WordPress block deprecation migration" --scrape -o .firecrawl/search-deprecations.json

# Scrape a specific developer docs page
firecrawl scrape "https://developer.wordpress.org/block-editor/reference-guides/block-api/block-deprecation/" -o .firecrawl/block-deprecation-docs.md

# Discover all URLs on a plugin's documentation site
firecrawl map https://developer.wordpress.org/plugins/ --limit 200 -o .firecrawl/plugin-docs-urls.txt

Setup

npm install -g firecrawl-cli
firecrawl login --browser

Auth errors are handled in references/install.md with browser-based and manual API key options.

Follows repo conventions

• Placed in skills/firecrawl/ alongside the existing 13 skills
• Uses YAML frontmatter with name, description, and compatibility fields
• Supporting docs in references/ subdirectory (matching the pattern used by other skills)
• Auto-discovered by skillpack-build.mjs - no changes to build/install scripts needed
• Purely additive: no existing files modified

[github-actions]

The following accounts have interacted with this PR and/or linked issues. I will continue to update these lists as activity occurs. You can also manually ask me to refresh this list by adding the props-bot label.

If you're merging code through a pull request on GitHub, copy and paste the following into the bottom of the merge commit message.

Co-authored-by: leonardogrig <leonardogrig@git.wordpress.org>

To understand the WordPress project's expectations around crediting contributors, please review the Contributor Attribution page in the Core Handbook.