用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/lamm-mit/scienceclaw --skill firecrawl-scraper命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | firecrawl-scraper |
| description | Web scraping of JavaScript-rendered scientific websites using Firecrawl API |
| metadata | null |
Web scraping using the Firecrawl API for JavaScript-rendered scientific websites, database pages, and literature sources. Returns clean Markdown content optimized for LLM processing. Handles dynamic content, authentication flows, and complex single-page applications that static scrapers cannot access.
Particularly useful for scraping scientific databases with JavaScript-heavy frontends, preprint servers, supplementary data pages, and research institution websites.
# Scrape a scientific database page as markdown
python3 skills/firecrawl-scraper/scripts/firecrawl_scrape.py --url "https://www.uniprot.org/uniprotkb/P53_HUMAN"
# Scrape and return raw HTML
python3 skills/firecrawl-scraper/scripts/firecrawl_scrape.py --url "https://www.rcsb.org/structure/1TUP" --format html
# Use explicit API key
python3 skills/firecrawl-scraper/scripts/firecrawl_scrape.py \
--url "https://www.biorxiv.org/content/10.1101/2024.01.01.000001" \
--api-key fc-yourkey123 \
--format markdown
{
"url": "https://www.uniprot.org/uniprotkb/P53_HUMAN",
"content": "# Cellular tumor antigen p53\n\n**Organism:** Homo sapiens...",
"format": "markdown",
"title": "P53_HUMAN - Cellular tumor antigen p53",
"links": [
"https://www.uniprot.org/uniprotkb/P04637",
"https://www.rcsb.org/structure/2OCJ"
]
}
Set your Firecrawl API key as an environment variable:
export FIRECRAWL_API_KEY=fc-yourkey123
Or pass it directly via --api-key. Get a key at https://firecrawl.dev.