firecrawl-knowledge-ingest

Name: firecrawl-knowledge-ingest
Author: firecrawl

29kinstalls18forks

How to install firecrawl-knowledge-ingest?

firecrawl/firecrawl-workflows/firecrawl-knowledge-ingest

$npx -y skills add firecrawl/firecrawl-workflows --skill firecrawl-knowledge-ingest

Installs into the current project.

Summary

Ingest public or authenticated knowledge bases and docs portals with Firecrawl browser. Use for JS-heavy docs, login-gated portals, paginated help centers, support knowledge bases, or structured JSON/markdown extraction from documentation sites.

Files · 1

View on GitHub

SKILL.md

1	# Firecrawl Knowledge Ingest
2
3	Use this when a docs portal needs browser navigation, auth, pagination, or JS rendering.
4
5	## Onboarding Interview
6
7	Infer the portal URL, output format, auth needs, and page limit from context. If the portal is clear, proceed immediately.
8
9	Ask at most 1-3 concise questions only if blocked, such as the portal URL, whether authentication is required, or the desired output format.
10
11	## Firecrawl Collection Plan
12
13	Use Firecrawl browser to:
14
15	- open the portal and inspect navigation
16	- identify sections, categories, sidebar links, and article URLs
17	- follow sidebar navigation, next links, pagination, load-more controls, or search
18	- scrape article content as markdown
19	- extract metadata such as title, section, last updated date, author, and tags
20
21	Try Firecrawl map as a supplement for public URLs, but use browser navigation for auth-gated or JS-heavy content.
22
23	## Final Deliverable
24
25	```markdown
26	# Knowledge Ingest: [Portal]
27
28	## Summary
29	[Pages extracted, sections covered, limitations]
30
31	## Output
32	[JSON/markdown/merged file path or content]
33
34	## Sections
35	[Section names and article counts]
36
37	## Failed Or Restricted Pages
38	[Any access/loading issues]
39
40	## Sources
41	[URLs extracted]
42
43	## Rerun Inputs
44	workflow: firecrawl-knowledge-ingest
45	url: [portal url]
46	format: [json/markdown/merged]
47	max_pages: [number]
48	```
49
50	## JSON Shape
51
52	Use `source`, `url`, `extractedAt`, `totalArticles`, and `sections[]` with article `title`, `url`, `section`, `content`, and `metadata`.
53
54	## Quality Bar
55
56	- Preserve code examples, tables, and formatting.
57	- Strip nav chrome, headers, and footers.
58	- Track extraction progress and page failures.
59	- Respect authentication boundaries.

People who liked this also viewed

6 picks

Type

firecrawl-knowledge-ingest

29kinstalls18forks

View on GitHub

How to install firecrawl-knowledge-ingest?

firecrawl/firecrawl-workflows/firecrawl-knowledge-ingest

$npx -y skills add firecrawl/firecrawl-workflows --skill firecrawl-knowledge-ingest

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Firecrawl Knowledge Ingest
2
3	Use this when a docs portal needs browser navigation, auth, pagination, or JS rendering.
4
5	## Onboarding Interview
6
7	Infer the portal URL, output format, auth needs, and page limit from context. If the portal is clear, proceed immediately.
8
9	Ask at most 1-3 concise questions only if blocked, such as the portal URL, whether authentication is required, or the desired output format.
10
11	## Firecrawl Collection Plan
12
13	Use Firecrawl browser to:
14
15	- open the portal and inspect navigation
16	- identify sections, categories, sidebar links, and article URLs
17	- follow sidebar navigation, next links, pagination, load-more controls, or search
18	- scrape article content as markdown
19	- extract metadata such as title, section, last updated date, author, and tags
20
21	Try Firecrawl map as a supplement for public URLs, but use browser navigation for auth-gated or JS-heavy content.
22
23	## Final Deliverable
24
25	```markdown
26	# Knowledge Ingest: [Portal]
27
28	## Summary
29	[Pages extracted, sections covered, limitations]
30
31	## Output
32	[JSON/markdown/merged file path or content]
33
34	## Sections
35	[Section names and article counts]
36
37	## Failed Or Restricted Pages
38	[Any access/loading issues]
39
40	## Sources
41	[URLs extracted]
42
43	## Rerun Inputs
44	workflow: firecrawl-knowledge-ingest
45	url: [portal url]
46	format: [json/markdown/merged]
47	max_pages: [number]
48	```
49
50	## JSON Shape
51
52	Use `source`, `url`, `extractedAt`, `totalArticles`, and `sections[]` with article `title`, `url`, `section`, `content`, and `metadata`.
53
54	## Quality Bar
55
56	- Preserve code examples, tables, and formatting.
57	- Strip nav chrome, headers, and footers.
58	- Track extraction progress and page failures.
59	- Respect authentication boundaries.

People who liked this also viewed

6 picks

Type