firecrawl-research-papers

Name: firecrawl-research-papers
Author: firecrawl

30kinstalls19forks

How to install firecrawl-research-papers?

firecrawl/firecrawl-workflows/firecrawl-research-papers

$npx -y skills add firecrawl/firecrawl-workflows --skill firecrawl-research-papers

Installs into the current project.

Summary

Find and synthesize research papers, whitepapers, PDFs, technical reports, and academic sources with Firecrawl Research, using semantic paper search, related-paper expansion, and in-body verification. Use when the user wants a literature review, paper summary, research landscape,

Files · 1

View on GitHub

SKILL.md

1	# Firecrawl Research Papers
2
3	Use this to create a sourced literature review.
4
5	## Onboarding Interview
6
7	Infer the topic, source constraints, target count, and output format from context. If the topic is clear, proceed immediately.
8
9	Ask at most 1-3 concise questions only if blocked, such as the topic, target paper count, or required venue/date/method constraints.
10
11	## Firecrawl Collection Plan
12
13	Use Firecrawl Research through the CLI, MCP, or equivalent Firecrawl tool
14	surface as the primary path for paper discovery and verification. Fall back to
15	general Firecrawl search and scrape for whitepapers, technical reports,
16	research blogs, leaderboards, or facts outside the paper corpus.
17
18	Core tools:
19
20	- MCP: `firecrawl_research_search_papers(query, k?)`
21	CLI: `firecrawl research search-papers <query> [--k <number>]`
22	Semantic search over paper abstracts. Start here for most paper-finding
23	queries, and retry with alternate framing when results are thin or too
24	narrow.
25	- MCP: `firecrawl_research_related_papers(seed_ids, intent, mode?, k?)`
26	CLI: `firecrawl research related-papers <seedIds...> --intent <intent> [--mode <similar\|citers\|references>] [--k <number>]`
27	Expand from strong seed papers into similar work, citing papers, or
28	references. Use this to find the relevant paper family, not just the first
29	matching result.
30	- MCP: `firecrawl_research_inspect_paper(id)`
31	CLI: `firecrawl research inspect-paper <id>`
32	Fetch canonical metadata for a candidate paper: title, abstract, authors,
33	categories, source ids, and dates.
34	- MCP: `firecrawl_research_read_paper(id, question)`
35	CLI: `firecrawl research read-paper <id> --question <question>`
36	Verify a specific claim or constraint inside one paper, such as method,
37	reported score, benchmark, affiliation, comparison, or limitation.
38	- MCP: `firecrawl_search(query)` / `firecrawl_scrape(url)`
39	CLI: `firecrawl search <query>` / `firecrawl scrape <url>`
40	Use for web-only context: benchmark leaderboards, rankings, reports,
41	whitepapers, research blogs, and source pages outside the paper index.
42
43	Match the approach to the query:
44
45	- Single named paper: run one paper search, then inspect or read the paper if
46	metadata or body verification is needed.
47	- Paper by description, method, or topic family: search for strong anchors,
48	then expand with related papers and keep close neighbors.
49	- Enumeration queries, such as papers that do a task or benchmark a method:
50	search multiple framings, expand several strong anchors, and re-seed from
51	newly found relevant papers.
52	- Papers that use or exhibit a property: start from the defining paper or
53	strongest anchor, expand via similar, citers, or references, and use
54	read-paper to verify the property.
55	- Superlatives and leaderboards: use general web search or scrape to find the
56	ranking, then map top entries back to papers with paper search.
57	- Author, organization, venue, date, or methodology constraints: verify with
58	inspect-paper metadata or read-paper before keeping a candidate.
59
60	Target source types:
61
62	- academic papers from arXiv, university sites, ACM/IEEE pages where accessible
63	- industry reports and whitepapers
64	- company research blogs
65	- technical articles and conference summaries
66
67	Principles:
68
69	- When in doubt, include the relevant paper family rather than only the single
70	best result.
71	- Use related-paper expansion to avoid stopping at one strong hit.
72	- Use read-paper to verify load-bearing constraints, not to summarize every
73	candidate.
74	- Drop only clearly off-topic papers.
75
76	## Parallel Work
77
78	If appropriate, use sub-agents or equivalent parallel task runners:
79
80	- Academic Papers researcher
81	- Industry Reports researcher
82	- Technical Articles researcher
83	- Synthesis and citation reviewer
84
85	## Final Deliverable
86
87	```markdown
88	# Literature Review: [Topic]
89
90	## Abstract
91	[2-3 paragraph summary]
92
93	## Key Papers
94	[Title, authors, source URL, key findings, methodology, relevance]
95
96	## Themes And Consensus
97	[What sources agree on]
98
99	## Open Questions And Debates
100	[Disagreements and unresolved questions]
101
102	## Emerging Trends
103	[Recent developments]
104
105	## Sources
106	[Organized by paper/report/article]
107
108	## Rerun Inputs
109	workflow: firecrawl-research-papers
110	topic: [topic]
111	target_count: [number]
112	output: [markdown/brief]
113	```
114
115	## Quality Bar
116
117	- Every

People who liked this also viewed

6 picks

Type

firecrawl-research-papers

30kinstalls19forks

View on GitHub

How to install firecrawl-research-papers?

firecrawl/firecrawl-workflows/firecrawl-research-papers

$npx -y skills add firecrawl/firecrawl-workflows --skill firecrawl-research-papers

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Firecrawl Research Papers
2
3	Use this to create a sourced literature review.
4
5	## Onboarding Interview
6
7	Infer the topic, source constraints, target count, and output format from context. If the topic is clear, proceed immediately.
8
9	Ask at most 1-3 concise questions only if blocked, such as the topic, target paper count, or required venue/date/method constraints.
10
11	## Firecrawl Collection Plan
12
13	Use Firecrawl Research through the CLI, MCP, or equivalent Firecrawl tool
14	surface as the primary path for paper discovery and verification. Fall back to
15	general Firecrawl search and scrape for whitepapers, technical reports,
16	research blogs, leaderboards, or facts outside the paper corpus.
17
18	Core tools:
19
20	- MCP: `firecrawl_research_search_papers(query, k?)`
21	CLI: `firecrawl research search-papers <query> [--k <number>]`
22	Semantic search over paper abstracts. Start here for most paper-finding
23	queries, and retry with alternate framing when results are thin or too
24	narrow.
25	- MCP: `firecrawl_research_related_papers(seed_ids, intent, mode?, k?)`
26	CLI: `firecrawl research related-papers <seedIds...> --intent <intent> [--mode <similar\|citers\|references>] [--k <number>]`
27	Expand from strong seed papers into similar work, citing papers, or
28	references. Use this to find the relevant paper family, not just the first
29	matching result.
30	- MCP: `firecrawl_research_inspect_paper(id)`
31	CLI: `firecrawl research inspect-paper <id>`
32	Fetch canonical metadata for a candidate paper: title, abstract, authors,
33	categories, source ids, and dates.
34	- MCP: `firecrawl_research_read_paper(id, question)`
35	CLI: `firecrawl research read-paper <id> --question <question>`
36	Verify a specific claim or constraint inside one paper, such as method,
37	reported score, benchmark, affiliation, comparison, or limitation.
38	- MCP: `firecrawl_search(query)` / `firecrawl_scrape(url)`
39	CLI: `firecrawl search <query>` / `firecrawl scrape <url>`
40	Use for web-only context: benchmark leaderboards, rankings, reports,
41	whitepapers, research blogs, and source pages outside the paper index.
42
43	Match the approach to the query:
44
45	- Single named paper: run one paper search, then inspect or read the paper if
46	metadata or body verification is needed.
47	- Paper by description, method, or topic family: search for strong anchors,
48	then expand with related papers and keep close neighbors.
49	- Enumeration queries, such as papers that do a task or benchmark a method:
50	search multiple framings, expand several strong anchors, and re-seed from
51	newly found relevant papers.
52	- Papers that use or exhibit a property: start from the defining paper or
53	strongest anchor, expand via similar, citers, or references, and use
54	read-paper to verify the property.
55	- Superlatives and leaderboards: use general web search or scrape to find the
56	ranking, then map top entries back to papers with paper search.
57	- Author, organization, venue, date, or methodology constraints: verify with
58	inspect-paper metadata or read-paper before keeping a candidate.
59
60	Target source types:
61
62	- academic papers from arXiv, university sites, ACM/IEEE pages where accessible
63	- industry reports and whitepapers
64	- company research blogs
65	- technical articles and conference summaries
66
67	Principles:
68
69	- When in doubt, include the relevant paper family rather than only the single
70	best result.
71	- Use related-paper expansion to avoid stopping at one strong hit.
72	- Use read-paper to verify load-bearing constraints, not to summarize every
73	candidate.
74	- Drop only clearly off-topic papers.
75
76	## Parallel Work
77
78	If appropriate, use sub-agents or equivalent parallel task runners:
79
80	- Academic Papers researcher
81	- Industry Reports researcher
82	- Technical Articles researcher
83	- Synthesis and citation reviewer
84
85	## Final Deliverable
86
87	```markdown
88	# Literature Review: [Topic]
89
90	## Abstract
91	[2-3 paragraph summary]
92
93	## Key Papers
94	[Title, authors, source URL, key findings, methodology, relevance]
95
96	## Themes And Consensus
97	[What sources agree on]
98
99	## Open Questions And Debates
100	[Disagreements and unresolved questions]
101
102	## Emerging Trends
103	[Recent developments]
104
105	## Sources
106	[Organized by paper/report/article]
107
108	## Rerun Inputs
109	workflow: firecrawl-research-papers
110	topic: [topic]
111	target_count: [number]
112	output: [markdown/brief]
113	```
114
115	## Quality Bar
116
117	- Every

People who liked this also viewed

6 picks

Type