firecrawl

Name: firecrawl
Author: MoizIbnYousaf

27stars5forks

How to install firecrawl?

moizibnyousaf/marketing-cli/firecrawl

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

Installs into the current project.

Summary

Web scraping, search, crawling, and browser automation 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, extract data from a website, crawl documen

Files · 1

View on GitHub

SKILL.md

1	# Firecrawl CLI
2
3	Web scraping, search, and browser automation CLI. Returns clean markdown optimized for LLM context windows.
4
5	Run `firecrawl --help` or `firecrawl <command> --help` for full option details.
6
7	## Prerequisites
8
9	Must be installed and authenticated. Check with `firecrawl --status`.
10
11	```
12	🔥 firecrawl cli v1.8.0
13
14	● Authenticated via FIRECRAWL_API_KEY
15	Concurrency: 0/100 jobs (parallel scrape limit)
16	Credits: 500,000 remaining
17	```
18
19	- Concurrency: Max parallel jobs. Run parallel operations up to this limit.
20	- Credits: Remaining API credits. Each scrape/crawl consumes credits.
21
22	If not ready, see [rules/install.md](rules/install.md). For output handling guidelines, see [rules/security.md](rules/security.md).
23
24	```bash
25	firecrawl search "query" --scrape --limit 3
26	```
27
28	## Workflow
29
30	Follow this escalation pattern:
31
32	1. Search - No specific URL yet. Find pages, answer questions, discover sources.
33	2. Scrape - Have a URL. Extract its content directly.
34	3. Map + Scrape - Large site or need a specific subpage. Use `map --search` to find the right URL, then scrape it.
35	4. Crawl - Need bulk content from an entire site section (e.g., all /docs/).
36	5. Browser - Scrape failed because content is behind interaction (pagination, modals, form submissions, multi-step navigation).
37
38	\| Need \| Command \| When \|
39	\| --------------------------- \| ---------- \| --------------------------------------------------------- \|
40	\| Find pages on a topic \| `search` \| No specific URL yet \|
41	\| Get a page's content \| `scrape` \| Have a URL, page is static or JS-rendered \|
42	\| Find URLs within a site \| `map` \| Need to locate a specific subpage \|
43	\| Bulk extract a site section \| `crawl` \| Need many pages (e.g., all /docs/) \|
44	\| AI-powered data extraction \| `agent` \| Need structured data from complex sites \|
45	\| Interact with a page \| `browser` \| Content requires clicks, form fills, pagination, or login \|
46	\| Download a site to files \| `download` \| Save an entire site as local files \|
47
48	For detailed command reference, use the individual skill for each command (e.g., `firecrawl-search`, `firecrawl-browser`) or run `firecrawl <command> --help`.
49
50	Scrape vs browser:
51
52	- Use `scrape` first. It handles static pages and JS-rendered SPAs.
53	- Use `browser` 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.
54	- Never use browser for web searches - use `search` instead.
55
56	Avoid redundant fetches:
57
58	- `search --scrape` already fetches full page content. Don't re-scrape those URLs.
59	- Check `.firecrawl/` for existing data before fetching again.
60
61	## When NOT to use firecrawl
62
63	Firecrawl is the default for public, text-based web content. Route elsewhere when the source is auth-walled, audio/video, or when you already have the text and just need it shorter:
64
65	\| Situation \| Use instead \| Why \|
66	\| --- \| --- \| --- \|
67	\| X / Twitter post, thread, article, or `/bookmarks` \| `mktg-x` skill \| Twitter serves a degraded logged-out page to unauthenticated clients. `mktg-x` uses stored `MKTG_X_AUTH_TOKEN` to fetch the real content. Firecrawl will return a stub. \|
68	\| YouTube / podcast / TikTok / any audio or video URL \| `mktg transcribe <url>` \| Firecrawl returns the page chrome (title, description), not the spoken content. `mktg transcribe` runs the yt-dlp → ffmpeg → whisper.cpp pipeline and returns the full transcript. \|
69	\| Fetched page is too long to ideate on \| Chain into `summarize` after the firecrawl call \| Firecrawl is the fetcher, summarize is the compressor. `firecrawl scrape <url> -o page.md && cat page.md \\| summarize --tldr` is the canonical pattern — don't re-fetch or ask firecrawl to summarize. \|
70
71	Escalation rule of thumb: *if a human would need to log in, press play, or skim-and-condense to get value fr

People who liked this also viewed

6 picks

Type

firecrawl

27stars5forks

View on GitHub

How to install firecrawl?

moizibnyousaf/marketing-cli/firecrawl

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Firecrawl CLI
2
3	Web scraping, search, and browser automation CLI. Returns clean markdown optimized for LLM context windows.
4
5	Run `firecrawl --help` or `firecrawl <command> --help` for full option details.
6
7	## Prerequisites
8
9	Must be installed and authenticated. Check with `firecrawl --status`.
10
11	```
12	🔥 firecrawl cli v1.8.0
13
14	● Authenticated via FIRECRAWL_API_KEY
15	Concurrency: 0/100 jobs (parallel scrape limit)
16	Credits: 500,000 remaining
17	```
18
19	- Concurrency: Max parallel jobs. Run parallel operations up to this limit.
20	- Credits: Remaining API credits. Each scrape/crawl consumes credits.
21
22	If not ready, see [rules/install.md](rules/install.md). For output handling guidelines, see [rules/security.md](rules/security.md).
23
24	```bash
25	firecrawl search "query" --scrape --limit 3
26	```
27
28	## Workflow
29
30	Follow this escalation pattern:
31
32	1. Search - No specific URL yet. Find pages, answer questions, discover sources.
33	2. Scrape - Have a URL. Extract its content directly.
34	3. Map + Scrape - Large site or need a specific subpage. Use `map --search` to find the right URL, then scrape it.
35	4. Crawl - Need bulk content from an entire site section (e.g., all /docs/).
36	5. Browser - Scrape failed because content is behind interaction (pagination, modals, form submissions, multi-step navigation).
37
38	\| Need \| Command \| When \|
39	\| --------------------------- \| ---------- \| --------------------------------------------------------- \|
40	\| Find pages on a topic \| `search` \| No specific URL yet \|
41	\| Get a page's content \| `scrape` \| Have a URL, page is static or JS-rendered \|
42	\| Find URLs within a site \| `map` \| Need to locate a specific subpage \|
43	\| Bulk extract a site section \| `crawl` \| Need many pages (e.g., all /docs/) \|
44	\| AI-powered data extraction \| `agent` \| Need structured data from complex sites \|
45	\| Interact with a page \| `browser` \| Content requires clicks, form fills, pagination, or login \|
46	\| Download a site to files \| `download` \| Save an entire site as local files \|
47
48	For detailed command reference, use the individual skill for each command (e.g., `firecrawl-search`, `firecrawl-browser`) or run `firecrawl <command> --help`.
49
50	Scrape vs browser:
51
52	- Use `scrape` first. It handles static pages and JS-rendered SPAs.
53	- Use `browser` 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.
54	- Never use browser for web searches - use `search` instead.
55
56	Avoid redundant fetches:
57
58	- `search --scrape` already fetches full page content. Don't re-scrape those URLs.
59	- Check `.firecrawl/` for existing data before fetching again.
60
61	## When NOT to use firecrawl
62
63	Firecrawl is the default for public, text-based web content. Route elsewhere when the source is auth-walled, audio/video, or when you already have the text and just need it shorter:
64
65	\| Situation \| Use instead \| Why \|
66	\| --- \| --- \| --- \|
67	\| X / Twitter post, thread, article, or `/bookmarks` \| `mktg-x` skill \| Twitter serves a degraded logged-out page to unauthenticated clients. `mktg-x` uses stored `MKTG_X_AUTH_TOKEN` to fetch the real content. Firecrawl will return a stub. \|
68	\| YouTube / podcast / TikTok / any audio or video URL \| `mktg transcribe <url>` \| Firecrawl returns the page chrome (title, description), not the spoken content. `mktg transcribe` runs the yt-dlp → ffmpeg → whisper.cpp pipeline and returns the full transcript. \|
69	\| Fetched page is too long to ideate on \| Chain into `summarize` after the firecrawl call \| Firecrawl is the fetcher, summarize is the compressor. `firecrawl scrape <url> -o page.md && cat page.md \\| summarize --tldr` is the canonical pattern — don't re-fetch or ask firecrawl to summarize. \|
70
71	Escalation rule of thumb: *if a human would need to log in, press play, or skim-and-condense to get value fr

People who liked this also viewed

6 picks

Type