Repo No. 36Firecrawl · Updated 22 September 2026 · In print

Skills Docs · No. 36

Firecrawl

firecrawl / skills

29 skills published from this repository, read as one issue.

Start reading — 1 min

29 skills11,515 words

Inside this issue

1 — Install

$ npx skills add firecrawl/skills

» /plugin marketplace add firecrawl/skills

ISC106 stars11,515 wordsUpdated 22 September 2026

2 — Skills

29 skills · 57 minutes

Firecrawl AgentAutonomously navigate websites and extract structured data across pages.1 min
Firecrawl AlexandriaFind a direct path to structured data through ready-made workflows, data APIs, and indexes.3 min
Firecrawl CrawlBulk-extract many pages from one site or section.1 min
Firecrawl Developer IndexSearch issues, merged pull requests, and READMEs from public code repositories, plus curated documentation.5 min
Firecrawl DownloadSave a site or section as local files (markdown, screenshots).1 min

Skills Docs · Repo No. 36Whole repo as markdown

Provenance

Weekly installs — firecrawl/skills8 weekly install buckets for firecrawl/skills, ending 1.4K below where it began. Highest week 2.9K, lowest 1.2K.241.1Kinstalls

Weekly installs — firecrawl/skills. 8 weekly install buckets for firecrawl/skills, ending 1.4K below where it began. Highest week 2.9K, lowest 1.2K.
Week	Installs
Week 1	2,592
Week 2	2,948
Week 3	2,727
Week 4	2,483
Week 5	2,016
Week 6	1,503
Week 7	1,358
Week 8	1,218

Typeset in this issue’s own colours, resolved from the owner’s published design.md.

Front matter

From the README

Firecrawl Skills

The full catalog of Firecrawl skills for AI coding agents, following the Agent Skills (opens in a new tab) format. Available as a plugin for Claude Code, Cursor, and OpenAI Codex.

This repository is a distribution catalog. Every directory under skills/ is a CI-synced mirror. Install skills from here; contribute skill changes at the source repository. Repository-level metadata is maintained here.

Install

npx skills add firecrawl/skills

Without -y this opens an interactive picker over the whole catalog. Install a specific skill by name (names are path-independent):

npx skills add firecrawl/skills --skill firecrawl-build

For CLI onboarding (installs the Firecrawl CLI plus the core skills, with optional workflow skills):

npx -y firecrawl-cli@latest init

Catalog layout

Category	Path	What it’s for	Source of truth
Core	`skills/core/` (opens in a new tab)	The Firecrawl primitives for live web work during an agent session (search, scrape, crawl, interact — via the CLI or MCP), plus the research paper index and developer index skills	`firecrawl/cli` (opens in a new tab)
Build	`skills/build/` (opens in a new tab)	Integrating Firecrawl APIs into product code: SDKs, REST, endpoint selection, API keys	`firecrawl/firecrawl` (opens in a new tab) (`skills/`)
Workflows	`skills/workflows/` (opens in a new tab)	End-to-end session recipes: lead gen, deep research, SEO audit, knowledge bases, and more	`firecrawl/firecrawl-workflows` (opens in a new tab)

Contributing: where does my PR go?

Core skills, including the research and developer index skills → PR firecrawl/cli (opens in a new tab).
Build/SDK skills → PR firecrawl/firecrawl (opens in a new tab) (skills/).
Workflow skills → PR firecrawl/firecrawl-workflows (opens in a new tab).

Do not submit changes to files under skills/ in this catalog. CI replaces those directories during the next source sync. Repository-level metadata is maintained here.

Skills that teach agents the Firecrawl CLI (opens in a new tab) for live web work — firecrawl, firecrawl-scrape, firecrawl-search, firecrawl-crawl, firecrawl-map, firecrawl-interact, firecrawl-agent, firecrawl-monitor, firecrawl-parse, firecrawl-download — plus the index skills backing the firecrawl research and firecrawl developer commands:

Skill	Description
`firecrawl-research-index` (opens in a new tab)	Find papers in the research paper index — biomedical and life-science literature (PubMed, bioRxiv, medRxiv) plus arXiv preprints
`firecrawl-developer-index` (opens in a new tab)	Answer developer questions from issues, pull requests, READMEs, and documentation pages

Build (`skills/build/`)

Skill	Description
`firecrawl-build` (opens in a new tab)	Firecrawl application API umbrella skill
`firecrawl-build-onboarding` (opens in a new tab)	Get `FIRECRAWL_API_KEY` into a project and choose the right SDK/docs
`firecrawl-build-scrape` (opens in a new tab)	Integrate `/scrape` for single-page extraction
`firecrawl-build-search` (opens in a new tab)	Integrate `/search` for discovery-first workflows
`firecrawl-build-interact` (opens in a new tab)	Integrate `/interact` for clicks, forms, and dynamic flows after scrape

Workflows (`skills/workflows/`)

End-to-end recipes such as firecrawl-lead-gen (opens in a new tab), firecrawl-deep-research (opens in a new tab), firecrawl-seo-audit (opens in a new tab), firecrawl-competitive-intel (opens in a new tab), and more — see skills/workflows/ (opens in a new tab) for the full set, and firecrawl-workflows (opens in a new tab) for the umbrella skill and authoring guide.

MCP Server

The plugin includes Firecrawl MCP configuration for the official Firecrawl MCP server (opens in a new tab), so editors that support bundled MCP metadata can wire Firecrawl tools with FIRECRAWL_API_KEY.

Plugins

This repo serves as a plugin for multiple platforms, bundling the core and build skills (workflows are session recipes, not editor-integration material):

Claude Code - .claude-plugin/
Cursor - .cursor-plugin/
OpenAI Codex - .codex-plugin/

Prerequisites

A Firecrawl account or self-hosted Firecrawl deployment
API key stored in FIRECRAWL_API_KEY for cloud usage

Get your API key at firecrawl.dev/app (opens in a new tab). If you do not have one yet, firecrawl-build-onboarding (opens in a new tab) includes the browser authorization flow.

Which skills do I need?

“Search/scrape the web for me right now, during this session” → core skills (skills/core/)
“Query published research papers or developer docs indexes” → index skills (skills/core/)
“Add Firecrawl to this codebase” → build skills (skills/build/)
“Run an end-to-end task like lead gen or deep research” → workflow skills (skills/workflows/)

Both usage paths follow Firecrawl’s onboarding skill (same install, different use cases): firecrawl.dev/agent-onboarding/SKILL.md (opens in a new tab).

Docs (Source of Truth)

Read the source-of-truth page for your project language:

Node / TypeScript: docs.firecrawl.dev/agent-source-of-truth/node (opens in a new tab)
Python: docs.firecrawl.dev/agent-source-of-truth/python (opens in a new tab)
Rust: docs.firecrawl.dev/agent-source-of-truth/rust (opens in a new tab)
Java: docs.firecrawl.dev/agent-source-of-truth/java (opens in a new tab)
Elixir: docs.firecrawl.dev/agent-source-of-truth/elixir (opens in a new tab)
cURL / REST: docs.firecrawl.dev/agent-source-of-truth/curl (opens in a new tab)

License

ISC

Colophon

How this issue was made

Source

github.com/firecrawl/skills, branch main, last pushed 22 September 2026.

Licence

ISC — the text of every skill is reproduced unmodified, frontmatter included, under the upstream licence.

Discovery

29 skills found by walking the repository tree for SKILL.md, not by matching a directory convention. 2 distinct layouts observed: skills/core/*/SKILL.md, skills/workflows/*/SKILL.md.

Issue colours

Resolved from the owner’s published design.md — hue 48°, chroma 0.187. Two accent tones are generated per issue and each is proven against its own ground before it ships: a single accent that passes AA on both light and dark paper is arithmetically impossible.

Typefaces

Display: SuisseIntl is not a face we ship; the reader's own choice is used.
Body: SuisseIntl is not a face we ship; the reader's own choice is used.

We never load a typeface at request time from a third-party origin, so a brand face we do not already self-host is substituted rather than fetched.

Heading repairs

1 repair applied to the front matter so the document has one h1 and no skipped levels:

Shifted “14 headings” from h1 to h2 so the skill title is the only h1.

Spec compliance

Every skill satisfies the Agent Skills specification’s frontmatter rules.

Images

Images inside a skill come from the upstream repository. Where the author gave no alternative text we mark the image decorative rather than inventing a description — a plausible caption we made up is worse than none for the reader who depends on it.

Marketplace

A plugin manifest is published at .claude-plugin/marketplace.json by Firecrawl, declaring 1 plugin. It is read for editorial metadata only — never as the skill index, which is always the repository tree.

Signal

Install counts come from skills.sh. They measure downloads, not quality, and an unranked repository is not an unread one.

Agent surfaces

The whole issue is available as one markdown document at /firecrawl/skills.md, and each skill at its own .md URL.

Publication

Set by Skills Docs from the source repository. Body text is Literata at the reader’s chosen size and measure; code is Geist Mono. Nothing on this page was written by us except this paragraph.

Contents