firecrawl-knowledge-ingest Skill for Claude: What It Does and How to Install It

Makes your agent export a docs portal or help center to local markdown or JSON, even if it needs clicking or a login.

Installs: 31.5K; on skills.sh
Stars: 214; on GitHub
Updated: Nov 2026; last repo commit

This skill makes your agent open a documentation portal in a Firecrawl browser, follow the sidebar, next links, pagination and load-more controls, and scrape each article to markdown. It also pulls the title, section, last updated date, author and tags.

It is for portals that need browser navigation, sign-in or JavaScript rendering. It needs a Firecrawl API key and the Firecrawl CLI, and it writes markdown or JSON, or one merged file.

Good for

Support and docs teams saving a help center as files
Developers who need an API reference portal offline
Teams feeding a help center into a knowledge base

Install firecrawl-knowledge-ingest

Claude Code

Copy this prompt.

Install the firecrawl-knowledge-ingest skill in Claude Code. Run this command:

/plugin marketplace add firecrawl/firecrawl-workflows
/plugin install firecrawl-workflows@firecrawl-workflows

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Pick one route. The plugin routes install the whole firecrawl-workflows plugin: 16 skills (counted from the skills list in its plugin.json), and the repo tree has no hooks, agents or MCP config files. The skills-only routes install just firecrawl-knowledge-ingest. The skill drives the Firecrawl CLI and needs a Firecrawl API key. Install the Firecrawl CLI first, since the skill runs firecrawl commands: npm install -g firecrawl-cli (Firecrawl CLI docs), or npx -y firecrawl-cli@latest init -y --browser to install it, sign in and add the shared skills in one step. Then run firecrawl login or export FIRECRAWL_API_KEY. Who pays: the Firecrawl account that owns the key. Every call uses credits; a new account starts on the free plan with 1,000 credits a month and no card. Per Firecrawl's billing docs: Interact (browser sessions) 2 to 7 credits per browser minute; scrape 1 credit per page; map 1 credit per call.

Built from the package data we hold. Not yet tested by us. Source.

What's in the skill

When it loads

Export documentation portals, help centers and API reference sites into local markdown or JSON with Firecrawl browser, including pages that render with JavaScript, hide content behind collapsible navigation or paginate. Use when the user wants a docs site, help center or support knowledge base saved as files, even without an explicit request to scrape.

Sections in SKILL.md

Onboarding Interview
Firecrawl Collection Plan
Final Deliverable
Summary
Output
Sections
Failed Or Restricted Pages
Sources
Rerun Inputs
JSON Shape
Quality Bar

Key facts

Author: Firecrawl (frontmatter author, and the repo owner)
License: ISC (frontmatter and the README)
Installs on skills.sh: 31,489 (Nov 2, 2026)
GitHub stars: 214 for the whole firecrawl/firecrawl-workflows repo (Nov 2, 2026)
Last repo commit: Nov 1, 2026
What it includes: 1 file: SKILL.md (bundles no scripts)
Needs: A Firecrawl API key (FIRECRAWL_API_KEY) with credits, and the Firecrawl CLI (npm install -g firecrawl-cli)
Part of: The firecrawl-workflows plugin: 16 skills in its Claude plugin.json (counted), 19 skill folders in the repo tree
Works in: AI coding agents, per the README. The repo also ships plugin manifests for Claude Code, Codex and Cursor

What it includes

Opens the portal and reads its navigation, sections and article URLs
Uses a Firecrawl browser.
Network · Open and inspect
Sidebar links, next links, pagination, load-more controls and search
Handles content hidden behind collapsible navigation.
Network · Follow the navigation
Scrapes each article as markdown and extracts metadata
Title, section, last updated date, author and tags.
Write · Scrape articles
Tries Firecrawl map for public URLs
Browser navigation is used for sign-in or JavaScript-heavy content.
Network · Map as a supplement
JSON, markdown or a merged file
JSON uses source, url, extractedAt, totalArticles and sections with article title, url, section, content and metadata.
Write · Output formats
Six sections from Summary to Rerun Inputs
Summary, Output, Sections, Failed Or Restricted Pages, Sources and Rerun Inputs. Rerun inputs include url, format and max_pages.
Read · Ingest report

From the official docs

Permissions

Medium risk

It reads whole portals through a browser, including signed-in ones, and saves them as files. Set a page limit and make sure you may copy the content.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It can copy a private portal's content to files
For auth-gated portals it saves article content to local files. Check you are allowed to copy that content before you run it. github.com
It follows links and pagination across the portal
SKILL.md tracks page failures and a max_pages rerun input. Set max_pages in your prompt (our advice). github.com
It spends your Firecrawl credits
Every call is billed in credits to the account behind the key. Per Firecrawl's billing docs: Interact (browser sessions) 2 to 7 credits per browser minute; scrape 1 credit per page; map 1 credit per call. A free account has 1,000 credits a month, so a large run can use it up. docs.firecrawl.dev

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only mode is documented in SKILL.md. Use version control for files it writes.
Talks to	Firecrawl hosted service. The documentation portal you point it at
Sign-in and keys	SKILL.md declares FIRECRAWL_API_KEY as a required input and covers auth-gated portals. It does not say where the key or a portal login is kept.
Scopes	Runs Firecrawl browser sessions and scrape commands with your API key Writes markdown, JSON or merged files Spends credits on the Firecrawl account that owns your API key

Questions

What does the firecrawl-knowledge-ingest skill do?

It makes your agent export a docs portal, help center or API reference site to local markdown or JSON. It uses a browser so it can handle JavaScript, collapsible menus and pagination.

How do I install it in Claude Code or Codex?

Use the install box at the top of this page. Each client has a plugin route and skills CLI commands. Install the Firecrawl CLI first (npm install -g firecrawl-cli, per its docs), then run firecrawl login or set FIRECRAWL_API_KEY.

Who pays for it?

You do, through the Firecrawl account that owns your API key. Firecrawl bills in credits, and a new account starts on the free plan with 1,000 credits a month and no card. Per its billing docs: Interact (browser sessions) 2 to 7 credits per browser minute; scrape 1 credit per page; map 1 credit per call. Check your balance with firecrawl credit-usage.

firecrawl-knowledge-ingest vs firecrawl-knowledge-base?

Ingest is for portals that need browser navigation, sign-in, pagination or JavaScript rendering. Knowledge-base builds LLM-ready corpora with map, search and scrape, with reference, RAG, training and docs-mirror modes.

Can it read a help center behind a login?

SKILL.md names auth-gated portals and tells the agent to respect authentication boundaries. It asks whether authentication is required if that is not clear. It does not say how the login is provided.

Is it safe to install?

It is a single SKILL.md file and bundles no scripts. When it runs, your agent drives a browser through the portal and saves what it reads as files. For a private portal, make sure you are allowed to copy its content.

Information

updated Nov 2, 2026

Repository: firecrawl/firecrawl-workflows
Folder: skills/firecrawl-knowledge-ingest

firecrawl/firecrawl-workflows skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 8

firecrawl-workflows README · github.com
firecrawl-knowledge-ingest SKILL.md · github.com
firecrawl-workflows plugin.json · github.com
firecrawl-workflows marketplace.json · github.com
firecrawl-workflows Codex plugin.json · github.com
Firecrawl CLI docs · docs.firecrawl.dev
Firecrawl billing and credits · docs.firecrawl.dev
firecrawl/cli README · github.com