firecrawl-parse

Name: firecrawl-parse
Author: firecrawl

45kinstalls77forks

How to install firecrawl-parse?

firecrawl/cli/firecrawl-parse

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

Installs into the current project.

Summary

Efficiently extract and convert the contents of any local file—such as PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, or HTML—into clean, well-formatted markdown saved to disk. Use this skill whenever the user requests to parse, read, or extract information from a file on their computer, i

Files · 1

View on GitHub

SKILL.md

1	# firecrawl parse
2
3	Turn a local document into clean markdown on disk. Supports PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, HTML/HTM/XHTML.
4
5	## When to use
6
7	- You have a file on disk (not a URL) and want its text as markdown
8	- User drops a PDF/DOCX and asks what it says, or to summarize it
9	- Use `scrape` instead when the source is a URL
10
11	## Quick start
12
13	Always save to `.firecrawl/` with `-o` — parsed docs can be hundreds of KB and blow up context if streamed to stdout. Add `.firecrawl/` to `.gitignore`.
14
15	```bash
16	mkdir -p .firecrawl
17
18	# File → markdown
19	firecrawl parse ./paper.pdf -o .firecrawl/paper.md
20
21	# AI summary
22	firecrawl parse ./paper.pdf -S -o .firecrawl/paper-summary.md
23
24	# Ask a question about the doc
25	firecrawl parse ./paper.pdf -Q "What are the main conclusions?" \
26	-o .firecrawl/paper-qa.md
27	```
28
29	Then `head`, `grep`, `rg` etc., or incrementally read the file - don't load the whole thing at once.
30
31	## Options
32
33	\| Option \| Description \|
34	\| ---------------------- \| --------------------------------------- \|
35	\| `-S, --summary` \| AI-generated summary \|
36	\| `-Q, --query <prompt>` \| Ask a question about the parsed content \|
37	\| `-o, --output <path>` \| Output file path — always use this \|
38	\| `-f, --format <fmt>` \| `markdown` (default), `html`, `summary` \|
39	\| `--timeout <ms>` \| Timeout for the parse job \|
40	\| `--timing` \| Show request duration \|
41
42	## Tips
43
44	- Quote paths with spaces: `firecrawl parse "./My Doc.pdf" -o .firecrawl/mydoc.md`.
45	- Max upload size: 50 MB per file.
46	- Credits: ~1 per PDF page; HTML is 1 flat.
47	- Check `.firecrawl/` before re-parsing the same file.
48	- To check your credit balance (recommended for batch processing and similar workflows), use the `firecrawl credit-usage` command.
49
50	## See also
51
52	- [firecrawl-scrape](../firecrawl-scrape/SKILL.md) — same idea for URLs

People who liked this also viewed

6 picks

Type

firecrawl-parse

45kinstalls77forks

View on GitHub

How to install firecrawl-parse?

firecrawl/cli/firecrawl-parse

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# firecrawl parse
2
3	Turn a local document into clean markdown on disk. Supports PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, HTML/HTM/XHTML.
4
5	## When to use
6
7	- You have a file on disk (not a URL) and want its text as markdown
8	- User drops a PDF/DOCX and asks what it says, or to summarize it
9	- Use `scrape` instead when the source is a URL
10
11	## Quick start
12
13	Always save to `.firecrawl/` with `-o` — parsed docs can be hundreds of KB and blow up context if streamed to stdout. Add `.firecrawl/` to `.gitignore`.
14
15	```bash
16	mkdir -p .firecrawl
17
18	# File → markdown
19	firecrawl parse ./paper.pdf -o .firecrawl/paper.md
20
21	# AI summary
22	firecrawl parse ./paper.pdf -S -o .firecrawl/paper-summary.md
23
24	# Ask a question about the doc
25	firecrawl parse ./paper.pdf -Q "What are the main conclusions?" \
26	-o .firecrawl/paper-qa.md
27	```
28
29	Then `head`, `grep`, `rg` etc., or incrementally read the file - don't load the whole thing at once.
30
31	## Options
32
33	\| Option \| Description \|
34	\| ---------------------- \| --------------------------------------- \|
35	\| `-S, --summary` \| AI-generated summary \|
36	\| `-Q, --query <prompt>` \| Ask a question about the parsed content \|
37	\| `-o, --output <path>` \| Output file path — always use this \|
38	\| `-f, --format <fmt>` \| `markdown` (default), `html`, `summary` \|
39	\| `--timeout <ms>` \| Timeout for the parse job \|
40	\| `--timing` \| Show request duration \|
41
42	## Tips
43
44	- Quote paths with spaces: `firecrawl parse "./My Doc.pdf" -o .firecrawl/mydoc.md`.
45	- Max upload size: 50 MB per file.
46	- Credits: ~1 per PDF page; HTML is 1 flat.
47	- Check `.firecrawl/` before re-parsing the same file.
48	- To check your credit balance (recommended for batch processing and similar workflows), use the `firecrawl credit-usage` command.
49
50	## See also
51
52	- [firecrawl-scrape](../firecrawl-scrape/SKILL.md) — same idea for URLs

People who liked this also viewed

6 picks

Type