skills

Name: skills
Author: firecrawl

byfirecrawl· 3 MCP servers

Stars

Forks

How to install skills?

firecrawl/skills

$git clone https://github.com/firecrawl/skills

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install skills by running `git clone https://github.com/firecrawl/skills`, then use it for the current task and follow its documentation at https://github.com/firecrawl/skills.

Files · 1

View on GitHub

README.md

1	# Firecrawl Skills
2
3	A collection of skills for AI coding agents following the [Agent Skills](https://agentskills.io) format. Available as a plugin for Claude Code, Cursor, and OpenAI Codex.
4
5	This repo is the app-integration counterpart to [`firecrawl/cli`](https://github.com/firecrawl/cli).
6
7	- Use this repo when an agent is building a product that calls Firecrawl APIs.
8	- Use `firecrawl/cli` when an agent needs better web access during its own work: search the web, scrape pages, crawl docs, or interact with live sites from the terminal.
9
10	## Install
11
12	One command installs both the CLI skills and these build skills:
13
14	```bash
15	npx -y firecrawl-cli@latest init --all --browser
16	```
17
18	Or install just this repo's skills directly:
19
20	```bash
21	npx skills add firecrawl/skills
22	```
23
24	## Available Skills
25
26	\| Skill \| Description \| Source \|
27	\| ------------------------------------------------------------------- \| ----------------------------------------------------------------------- \| ------------- \|
28	\| [`firecrawl-build`](./skills/firecrawl-build) \| Firecrawl application API umbrella skill \| Authored here \|
29	\| [`firecrawl-build-onboarding`](./skills/firecrawl-build-onboarding) \| Get `FIRECRAWL_API_KEY` into a project and choose the right SDK/docs \| Authored here \|
30	\| [`firecrawl-build-scrape`](./skills/firecrawl-build-scrape) \| Integrate `/scrape` for single-page extraction \| Authored here \|
31	\| [`firecrawl-build-search`](./skills/firecrawl-build-search) \| Integrate `/search` for discovery-first workflows \| Authored here \|
32	\| [`firecrawl-build-interact`](./skills/firecrawl-build-interact) \| Integrate `/interact` for clicks, forms, and dynamic flows after scrape \| Authored here \|
33
34	## MCP Server
35
36	The plugin includes Firecrawl MCP configuration for the official [Firecrawl MCP server](https://github.com/firecrawl/firecrawl-mcp-server), so editors that support bundled MCP metadata can wire Firecrawl tools with `FIRECRAWL_API_KEY`.
37
38	## Plugins
39
40	This repo serves as a plugin for multiple platforms:
41
42	- Claude Code - `.claude-plugin/`
43	- Cursor - `.cursor-plugin/`
44	- OpenAI Codex - `.codex-plugin/`
45
46	## Editing Skills
47
48	All current skills in this repo are authored here and can be edited directly in this repo.
49
50	If Firecrawl later syncs skills from other repos, that distinction should be documented here and in `AGENTS.md`.
51
52	## Prerequisites
53
54	- A Firecrawl account or self-hosted Firecrawl deployment
55	- API key stored in `FIRECRAWL_API_KEY` for cloud usage
56
57	Get your API key at [firecrawl.dev/app](https://www.firecrawl.dev/app).
58
59	If you do not already have an API key, use [`firecrawl-build-onboarding`](./skills/firecrawl-build-onboarding) in this repo. It includes the browser authorization flow directly and does not require the website onboarding skill.
60
61	## Relationship To The CLI Repo
62
63	Both repos are installed by the same command:
64
65	```bash
66	npx -y firecrawl-cli@latest init --all --browser
67	```
68
69	This installs the Firecrawl CLI, the CLI skills (for live web work), and these build skills (for app integration) together. The difference is what you use after install:
70
71	- CLI skills (`firecrawl/cli`) — for searching the web, scraping pages, interacting with live sites during the current session
72	- Build skills (this repo) — for integrating Firecrawl into application code
73
74	The build skills here focus on:
75
76	- getting an API key into `.env`
77	- choosing fresh project vs existing project flow
78	- choosing the right endpoint
79	- asking what Firecrawl should do in the product
80	- wiring SDKs or REST calls into code
81	- inspecting an existing repo before integrating
82	- running a smoke test so the integration is proven, not just written
83	- avoiding CLI-only guidance when the real task is product integration
84
85	Default build flow:
86
87	1. decide whether the project is fresh or existing
88	2. ask what Firecrawl should do in the product
89	3. route to `/scrape`, `/search`, or `/interact`
90	4. integrate using the project's existing conventions
91	5. verify one real Firecrawl request succeeds
92
93	## Source Of Truth
94
95	This repo follows the same two usage paths described in Firecrawl's onboarding skill (same install, different use cases):
96
97	- Path A: live web tools during the current session (CLI skills)
98	- Path B: integrate Firecrawl into application code (build skills)
99
100	The onboarding source lives at:
101
102	- [`firecrawl-web/public/agent-onboarding/SKILL.md`](https://www.firecrawl.dev/agent-onboarding/SKILL.md)
103
104	## Docs (Source of Truth)
105
106	Read the source-of-truth page for your project language:
107
108	- Node / TypeScript: [docs.firecrawl.dev/agent-source-of-truth/node](https://docs.firecrawl.dev/agent-source-of-truth/node)
109	- Python: [docs.firecrawl.dev/agent-source-of-truth/python](https://docs.firecrawl.dev/agent-source-of-truth/python)
110	- Rust: [

6 picks

Type

skills

byfirecrawl· 3 MCP servers

Stars

Forks

How to install skills?

firecrawl/skills

$git clone https://github.com/firecrawl/skills

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install skills by running `git clone https://github.com/firecrawl/skills`, then use it for the current task and follow its documentation at https://github.com/firecrawl/skills.

Files · 1

View on GitHub

README.md

1	# Firecrawl Skills
2
3	A collection of skills for AI coding agents following the [Agent Skills](https://agentskills.io) format. Available as a plugin for Claude Code, Cursor, and OpenAI Codex.
4
5	This repo is the app-integration counterpart to [`firecrawl/cli`](https://github.com/firecrawl/cli).
6
7	- Use this repo when an agent is building a product that calls Firecrawl APIs.
8	- Use `firecrawl/cli` when an agent needs better web access during its own work: search the web, scrape pages, crawl docs, or interact with live sites from the terminal.
9
10	## Install
11
12	One command installs both the CLI skills and these build skills:
13
14	```bash
15	npx -y firecrawl-cli@latest init --all --browser
16	```
17
18	Or install just this repo's skills directly:
19
20	```bash
21	npx skills add firecrawl/skills
22	```
23
24	## Available Skills
25
26	\| Skill \| Description \| Source \|
27	\| ------------------------------------------------------------------- \| ----------------------------------------------------------------------- \| ------------- \|
28	\| [`firecrawl-build`](./skills/firecrawl-build) \| Firecrawl application API umbrella skill \| Authored here \|
29	\| [`firecrawl-build-onboarding`](./skills/firecrawl-build-onboarding) \| Get `FIRECRAWL_API_KEY` into a project and choose the right SDK/docs \| Authored here \|
30	\| [`firecrawl-build-scrape`](./skills/firecrawl-build-scrape) \| Integrate `/scrape` for single-page extraction \| Authored here \|
31	\| [`firecrawl-build-search`](./skills/firecrawl-build-search) \| Integrate `/search` for discovery-first workflows \| Authored here \|
32	\| [`firecrawl-build-interact`](./skills/firecrawl-build-interact) \| Integrate `/interact` for clicks, forms, and dynamic flows after scrape \| Authored here \|
33
34	## MCP Server
35
36	The plugin includes Firecrawl MCP configuration for the official [Firecrawl MCP server](https://github.com/firecrawl/firecrawl-mcp-server), so editors that support bundled MCP metadata can wire Firecrawl tools with `FIRECRAWL_API_KEY`.
37
38	## Plugins
39
40	This repo serves as a plugin for multiple platforms:
41
42	- Claude Code - `.claude-plugin/`
43	- Cursor - `.cursor-plugin/`
44	- OpenAI Codex - `.codex-plugin/`
45
46	## Editing Skills
47
48	All current skills in this repo are authored here and can be edited directly in this repo.
49
50	If Firecrawl later syncs skills from other repos, that distinction should be documented here and in `AGENTS.md`.
51
52	## Prerequisites
53
54	- A Firecrawl account or self-hosted Firecrawl deployment
55	- API key stored in `FIRECRAWL_API_KEY` for cloud usage
56
57	Get your API key at [firecrawl.dev/app](https://www.firecrawl.dev/app).
58
59	If you do not already have an API key, use [`firecrawl-build-onboarding`](./skills/firecrawl-build-onboarding) in this repo. It includes the browser authorization flow directly and does not require the website onboarding skill.
60
61	## Relationship To The CLI Repo
62
63	Both repos are installed by the same command:
64
65	```bash
66	npx -y firecrawl-cli@latest init --all --browser
67	```
68
69	This installs the Firecrawl CLI, the CLI skills (for live web work), and these build skills (for app integration) together. The difference is what you use after install:
70
71	- CLI skills (`firecrawl/cli`) — for searching the web, scraping pages, interacting with live sites during the current session
72	- Build skills (this repo) — for integrating Firecrawl into application code
73
74	The build skills here focus on:
75
76	- getting an API key into `.env`
77	- choosing fresh project vs existing project flow
78	- choosing the right endpoint
79	- asking what Firecrawl should do in the product
80	- wiring SDKs or REST calls into code
81	- inspecting an existing repo before integrating
82	- running a smoke test so the integration is proven, not just written
83	- avoiding CLI-only guidance when the real task is product integration
84
85	Default build flow:
86
87	1. decide whether the project is fresh or existing
88	2. ask what Firecrawl should do in the product
89	3. route to `/scrape`, `/search`, or `/interact`
90	4. integrate using the project's existing conventions
91	5. verify one real Firecrawl request succeeds
92
93	## Source Of Truth
94
95	This repo follows the same two usage paths described in Firecrawl's onboarding skill (same install, different use cases):
96
97	- Path A: live web tools during the current session (CLI skills)
98	- Path B: integrate Firecrawl into application code (build skills)
99
100	The onboarding source lives at:
101
102	- [`firecrawl-web/public/agent-onboarding/SKILL.md`](https://www.firecrawl.dev/agent-onboarding/SKILL.md)
103
104	## Docs (Source of Truth)
105
106	Read the source-of-truth page for your project language:
107
108	- Node / TypeScript: [docs.firecrawl.dev/agent-source-of-truth/node](https://docs.firecrawl.dev/agent-source-of-truth/node)
109	- Python: [docs.firecrawl.dev/agent-source-of-truth/python](https://docs.firecrawl.dev/agent-source-of-truth/python)
110	- Rust: [

6 picks

Type

skills

How to install skills?

Related

skills

How to install skills?

Related