firecrawl-research

This skill should be used when the user requests to research topics using FireCrawl, enrich notes with web sources, search and scrape information, or write scientific/academic papers. It extracts research topics from markdown files, creates research documents with scraped sources, generates BibTeX bibliographies from research results, and provides Pandoc/MyST templates for academic writing with citation management.

17stars1forksUpdated 2/21/2026

Data Science & ML #research #citation-management #web-scraping #academic-writing #firecrawl #python

Security Assessment

Medium Risk(50/100)

Detected risks:

Secret Exposure([SKILL.md] API_KEY=)

Sensitive File Access([SKILL.md] .env)

Security Score50/100

About firecrawl-research

The 'firecrawl-research' skill is designed to automate the process of researching topics by utilizing the FireCrawl API. It allows users to extract research topics from markdown files, search and scrape information from the web, and generate research documents enriched with scraped sources. This skill is valuable for users who need to perform systematic research or enrich their documents with up-to-date, web-sourced information. It is particularly useful for generating scientific or academic papers with proper citation management, saving users the time and effort of manual research and content gathering.

The skill provides key features such as automatic topic extraction from markdown files using headers and research tags, searching for relevant content on FireCrawl, scraping data from multiple sources, and generating markdown files containing comprehensive research results. Additionally, it supports creating BibTeX bibliographies and offers Pandoc/MyST templates for academic writing. The script also handles rate limiting for the FireCrawl API to ensure smooth operation even on the free tier, making it accessible for users with different needs.

This skill is ideal for researchers, academic writers, students, or anyone in need of an automated tool for gathering research data from the web and integrating it into their written works. It supports workflows like quick research, where users extract topics from notes and generate research content, as well as organized research, where results are saved in dedicated output folders for further use.

FAQ

How do I use the firecrawl-research skill?

You can use the skill by running the command: `python scripts/firecrawl_research.py research.md`, where 'research.md' is the input markdown file containing the topics to research. You can specify an output directory and limit the number of results per topic.

What kind of input file does the skill accept?

The skill accepts markdown files (.md) where research topics can be listed using headers or research tags. Topics are either extracted from headers like '## Topic Name' or from tags like '- [research] Topic Name'.

Are there any rate limits for using the FireCrawl API?

Yes, the script includes automatic rate limiting to prevent exceeding FireCrawl's free tier limit of 5 requests per minute. A 12-second delay is applied between each topic to ensure smooth operation.

Can I specify the number of results I want per topic?

Yes, you can specify the maximum number of results to retrieve for each topic by passing the desired number as a parameter. For example: `python scripts/firecrawl_research.py research.md ./output 3` will limit results to 3 per topic.

How are the research results saved?

Research results are saved in markdown files, with one file per topic. Each file includes the topic title, timestamp, source count, and the full scraped content from the selected sources, along with their URLs.