firecrawl-cli

Name: firecrawl-cli
Author: firecrawl

531stars77forks

How to install firecrawl-cli?

firecrawl/cli/firecrawl-cli

$npx -y skills add firecrawl/cli --skill firecrawl-cli

Installs into the current project.

Summary

Search, scrape, and interact with the web via the Firecrawl CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, scrape a webpage, grab content from a URL, get data from a website, crawl documentation, download

Files · 1

View on GitHub

SKILL.md

1	# Firecrawl CLI
2
3	Search, scrape, and interact with the web. Returns clean markdown optimized for LLM context windows.
4
5	Run `firecrawl --help` or `firecrawl <command> --help` for full option details.
6
7	If the task is to integrate Firecrawl into an application, add `FIRECRAWL_API_KEY` to a project, or choose endpoint usage in product code, use the `firecrawl-build` skills. If the task is an outcome workflow such as deep research, SEO audit, QA, lead generation, knowledge-base creation, dashboard reporting, shopping research, or website design-system extraction, use the `firecrawl-workflows` skills. They are already installed alongside this CLI skill when you run `firecrawl init`.
8
9	## Prerequisites
10
11	Must be installed. Check with `firecrawl --status`.
12
13	```
14	🔥 firecrawl cli v1.8.0
15
16	● Authenticated via FIRECRAWL_API_KEY
17	Concurrency: 0/100 jobs (parallel scrape limit)
18	Credits: 500,000 remaining
19	```
20
21	- Concurrency: Max parallel jobs. Run parallel operations up to this limit.
22	- Credits: Remaining API credits. Each operation consumes credits.
23
24	Authenticating gives the best results. Prefer a free account via `firecrawl init --browser` (browser login) or a `FIRECRAWL_API_KEY` whenever the human can sign up. If you cannot obtain a key and the human cannot sign up, you can still search, scrape, and interact without an API key on the keyless free tier (rate-limited). See [agent onboarding](https://www.firecrawl.dev/agent-onboarding/SKILL.md) for the full set of onboarding paths.
25
26	If not ready, see [rules/install.md](rules/install.md). For output handling guidelines, see [rules/security.md](rules/security.md).
27
28	Before doing real work, verify the setup with one small request:
29
30	```bash
31	mkdir -p .firecrawl
32	firecrawl scrape "https://firecrawl.dev" -o .firecrawl/install-check.md
33	```
34
35	```bash
36	firecrawl search "query" --scrape --limit 3
37	```
38
39	## Workflow
40
41	Follow this escalation pattern:
42
43	1. Search - No specific URL yet. Find pages, answer questions, discover sources.
44	2. Scrape - Have a URL. Extract its content directly.
45	3. Map + Scrape - Large site or need a specific subpage. Use `map --search` to find the right URL, then scrape it.
46	4. Crawl - Need bulk content from an entire site section (e.g., all /docs/).
47	5. Monitor - Need recurring checks or ongoing alerts. Prefer setting a monitor with `--page` plus `--goal` instead of doing repeated one-off scrapes.
48	6. Interact - Scrape first, then interact with the page (pagination, modals, form submissions, multi-step navigation).
49
50	\| Need \| Command \| When \|
51	\| --------------------------- \| --------------------- \| --------------------------------------------------------- \|
52	\| Find pages on a topic \| `search` \| No specific URL yet \|
53	\| Get a page's content \| `scrape` \| Have a URL, page is static or JS-rendered \|
54	\| Find URLs within a site \| `map` \| Need to locate a specific subpage \|
55	\| Bulk extract a site section \| `crawl` \| Need many pages (e.g., all /docs/) \|
56	\| AI-powered data extraction \| `agent` \| Need structured data from complex sites \|
57	\| Interact with a page \| `scrape` + `interact` \| Content requires clicks, form fills, pagination, or login \|
58	\| Download a site to files \| `download` \| Save an entire site as local files \|
59	\| Parse a local file \| `parse` \| File on disk (PDF, DOCX, XLSX, etc.) — not a URL \|
60	\| Watch pages for changes \| `monitor` \| Schedule recurring scrapes/crawls, diff against snapshots \|
61
62	For detailed command reference, run `firecrawl <command> --help`.
63
64	Scrape vs interact:
65
66	- Use `scrape` first. It handles static pages and JS-rendered SPAs.
67	- Use `scrape` + `interact` when you need to interact with a page, such as clicking buttons, filling out forms, navigating through a complex site, infinite scroll, or when scrape fails to grab all the content you need.
68	- Neve

People who liked this also viewed

6 picks

Type

firecrawl-cli

531stars77forks

View on GitHub

How to install firecrawl-cli?

firecrawl/cli/firecrawl-cli

$npx -y skills add firecrawl/cli --skill firecrawl-cli

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Firecrawl CLI
2
3	Search, scrape, and interact with the web. Returns clean markdown optimized for LLM context windows.
4
5	Run `firecrawl --help` or `firecrawl <command> --help` for full option details.
6
7	If the task is to integrate Firecrawl into an application, add `FIRECRAWL_API_KEY` to a project, or choose endpoint usage in product code, use the `firecrawl-build` skills. If the task is an outcome workflow such as deep research, SEO audit, QA, lead generation, knowledge-base creation, dashboard reporting, shopping research, or website design-system extraction, use the `firecrawl-workflows` skills. They are already installed alongside this CLI skill when you run `firecrawl init`.
8
9	## Prerequisites
10
11	Must be installed. Check with `firecrawl --status`.
12
13	```
14	🔥 firecrawl cli v1.8.0
15
16	● Authenticated via FIRECRAWL_API_KEY
17	Concurrency: 0/100 jobs (parallel scrape limit)
18	Credits: 500,000 remaining
19	```
20
21	- Concurrency: Max parallel jobs. Run parallel operations up to this limit.
22	- Credits: Remaining API credits. Each operation consumes credits.
23
24	Authenticating gives the best results. Prefer a free account via `firecrawl init --browser` (browser login) or a `FIRECRAWL_API_KEY` whenever the human can sign up. If you cannot obtain a key and the human cannot sign up, you can still search, scrape, and interact without an API key on the keyless free tier (rate-limited). See [agent onboarding](https://www.firecrawl.dev/agent-onboarding/SKILL.md) for the full set of onboarding paths.
25
26	If not ready, see [rules/install.md](rules/install.md). For output handling guidelines, see [rules/security.md](rules/security.md).
27
28	Before doing real work, verify the setup with one small request:
29
30	```bash
31	mkdir -p .firecrawl
32	firecrawl scrape "https://firecrawl.dev" -o .firecrawl/install-check.md
33	```
34
35	```bash
36	firecrawl search "query" --scrape --limit 3
37	```
38
39	## Workflow
40
41	Follow this escalation pattern:
42
43	1. Search - No specific URL yet. Find pages, answer questions, discover sources.
44	2. Scrape - Have a URL. Extract its content directly.
45	3. Map + Scrape - Large site or need a specific subpage. Use `map --search` to find the right URL, then scrape it.
46	4. Crawl - Need bulk content from an entire site section (e.g., all /docs/).
47	5. Monitor - Need recurring checks or ongoing alerts. Prefer setting a monitor with `--page` plus `--goal` instead of doing repeated one-off scrapes.
48	6. Interact - Scrape first, then interact with the page (pagination, modals, form submissions, multi-step navigation).
49
50	\| Need \| Command \| When \|
51	\| --------------------------- \| --------------------- \| --------------------------------------------------------- \|
52	\| Find pages on a topic \| `search` \| No specific URL yet \|
53	\| Get a page's content \| `scrape` \| Have a URL, page is static or JS-rendered \|
54	\| Find URLs within a site \| `map` \| Need to locate a specific subpage \|
55	\| Bulk extract a site section \| `crawl` \| Need many pages (e.g., all /docs/) \|
56	\| AI-powered data extraction \| `agent` \| Need structured data from complex sites \|
57	\| Interact with a page \| `scrape` + `interact` \| Content requires clicks, form fills, pagination, or login \|
58	\| Download a site to files \| `download` \| Save an entire site as local files \|
59	\| Parse a local file \| `parse` \| File on disk (PDF, DOCX, XLSX, etc.) — not a URL \|
60	\| Watch pages for changes \| `monitor` \| Schedule recurring scrapes/crawls, diff against snapshots \|
61
62	For detailed command reference, run `firecrawl <command> --help`.
63
64	Scrape vs interact:
65
66	- Use `scrape` first. It handles static pages and JS-rendered SPAs.
67	- Use `scrape` + `interact` when you need to interact with a page, such as clicking buttons, filling out forms, navigating through a complex site, infinite scroll, or when scrape fails to grab all the content you need.
68	- Neve

People who liked this also viewed

6 picks

Type