Clarity Literature Skill
Search and retrieve research papers from Clarity Protocol's curated literature database, sourced from PubMed and enriched with citation metrics from Semantic Scholar.
Quick Start
List all papers in the database:
CODEBLOCK0
Get details for a specific paper by PMID:
CODEBLOCK1
Get paper details in readable format:
CODEBLOCK2
Paper Fields
Each paper includes:
- -
pmid: PubMed identifier - INLINECODE1 : Digital Object Identifier
- INLINECODE2 : Paper title
- INLINECODE3 : First author name
- INLINECODE4 : Year published
- INLINECODE5 : Journal name
- INLINECODE6 : Paper abstract (when available)
- INLINECODE7 : Number of citations (from Semantic Scholar)
- INLINECODE8 : Number of highly influential citations
- INLINECODE9 : Whether full text is available in PubMed Central
Rate Limits
- - Anonymous (no API key): 10 requests/minute
- With API key: 100 requests/minute
To use an API key, set the CLARITY_API_KEY environment variable:
CODEBLOCK3
Get your API key at https://clarityprotocol.io
Error Handling
404 Not Found: The paper with the specified PMID does not exist in the database.
429 Rate Limit: You've exceeded the rate limit. The script will display how long to wait.
500 Server Error: The API server encountered an error. Try again later.
Timeout: The request took longer than 30 seconds.
Pagination
Paper lists are paginated. The API returns a next_cursor field if more results are available.
Use Cases
- - Find research papers related to protein variants
- Get citation metrics for a specific paper
- Check if a paper has full text available
- Extract abstracts for literature reviews
- Build bibliographies for protein research
Clarity文献技能
从Clarity协议精选文献数据库中搜索和检索研究论文，该数据库源自PubMed，并包含来自Semantic Scholar的引文指标。
快速开始
列出数据库中的所有论文：
bash
python scripts/search_papers.py
通过PMID获取特定论文的详细信息：
bash
python scripts/get_paper.py --pmid 12345678
以可读格式获取论文详细信息：
bash
python scripts/get_paper.py --pmid 12345678 --format summary
论文字段
每篇论文包含：
- - pmid：PubMed标识符
- doi：数字对象标识符
- title：论文标题
- firstauthor：第一作者姓名
- publicationyear：发表年份
- journal：期刊名称
- abstract：论文摘要（如有）
- citationcount：引用次数（来自Semantic Scholar）
- influentialcitations：高影响力引用次数
- has_fulltext：PubMed Central中是否有全文
速率限制
- - 匿名（无API密钥）：每分钟10次请求
- 使用API密钥：每分钟100次请求
要使用API密钥，请设置CLARITYAPIKEY环境变量：
bash
export CLARITYAPIKEY=yourkeyhere
python scripts/search_papers.py
在https://clarityprotocol.io获取您的API密钥
错误处理
404未找到：数据库中不存在指定PMID的论文。
429速率限制：您已超出速率限制。脚本将显示需要等待的时间。
500服务器错误：API服务器遇到错误。请稍后重试。
超时：请求耗时超过30秒。
分页
论文列表采用分页方式。如果还有更多结果，API会返回next_cursor字段。
使用场景
- - 查找与蛋白质变体相关的研究论文
- 获取特定论文的引文指标
- 检查论文是否有全文可用
- 提取文献综述的摘要
- 为蛋白质研究构建参考文献列表
