pubmed-linker

pubmed-linker is a skill for Claude Code from samqin123/Claude_skill_pool. It costs 67 tokens per session (1,488 once invoked), scanned A, original, Apache-2.0.

A skill for finding and checking PubMed links for medical and life-science references. PubMed is a database of biomedical research papers, and the skill also covers full-text and related-paper queries.

In plain words
What is it for?
Use it to search PubMed, retrieve paper details and identifiers, update reference links, check full-text availability, download papers, and find cited, citing, or similar studies.
Why use it?
It reduces errors when matching a reference to the correct paper and link. It provides a defined process for searching, verifying authors and titles, checking open access, and downloading available full text.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to search PubMed, retrieve paper details and identifiers, update reference links, check full-text availability, download papers, and find cited, citing, or similar studies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/samqin123/claude_skill_pool/pubmed-linker
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add samqin123/Claude_skill_pool --skill pubmed-linker
Clone the repo
git clone --depth 1 https://github.com/samqin123/Claude_skill_pool

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pubmed-linker

README.md
[![agentmods](https://agentmods.dev/badge/skills/samqin123/claude_skill_pool/pubmed-linker/github.svg)](https://agentmods.dev/skills/samqin123/claude_skill_pool/pubmed-linker)
Your own site
<a href="https://agentmods.dev/skills/samqin123/claude_skill_pool/pubmed-linker"><img src="https://agentmods.dev/badge/skills/samqin123/claude_skill_pool/pubmed-linker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pubmed-linker

Your own site · 80×15
<a href="https://agentmods.dev/skills/samqin123/claude_skill_pool/pubmed-linker"><img src="https://agentmods.dev/badge/skills/samqin123/claude_skill_pool/pubmed-linker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.01488
Opus 5 $0.00034 $0.00744
Sonnet 5 $0.00013 $0.00298
Haiku 4.5 $0.00007 $0.00149

Measured 9d ago against content hash 3d03813a65a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pubmed-linker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills.claude/ref-pubmed-linker/.claude/skills/pubmed-linker/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PubMed 文献链接查询技能

这个技能提供了一套系统化的方法来使用 MCP PubMed 工具查询文献信息并更新参考文献列表的链接。

技能概述

当用户需要:

  • 查询参考文献的 PubMed 链接
  • 更新 Reference_list.md 中的文献链接
  • 下载论文全文
  • 检查文献的开放获取状态

使用此技能来准确调用 MCP PubMed 工具,避免幻觉。

可用的 MCP PubMed 工具

搜索工具

  • pubmed_search - 高级搜索,支持布尔逻辑和 MeSH 术语
  • pubmed_quick_search - 快速搜索,返回精简结果

查询工具

  • pubmed_get_details - 获取完整文献信息(包括 PMID、DOI、全文链接)
  • pubmed_batch_query - 批量查询多个 PMIDs
  • pubmed_extract_key_info - 提取关键信息摘要

下载工具

  • pubmed_download_fulltext - 下载指定文献的 PDF 全文
  • pubmed_batch_download - 批量下载多个文献
  • pubmed_detect_fulltext - 检测开放获取状态

其他工具

  • pubmed_cross_reference - 查找相关文献(引用/被引用/相似文献)
  • pubmed_cache_info - 缓存管理
  • pubmed_system_check - 系统环境检查

文献引用格式解析

Reference_list.md 中的引用格式为:

[序号] 作者. 题目[J]. 期刊名, 年份, 卷(期): 页码.

提取关键信息用于 PubMed 搜索:

  1. 作者姓氏 - 取第一作者姓氏
  2. 关键词 - 从题目中选择 2-3 个核心关键词
  3. 期刊名 - 可选,用于精确匹配
  4. 发表年份 - 用于过滤结果

搜索策略

优先级搜索策略

策略 1:作者 + 题目关键词

作者姓氏 AND 题目关键词1 AND 题目关键词2

例如:Langevin AND Relationship AND Acupuncture

策略 2:期刊 + 年份 + 题目关键词

期刊名[ta] AND 年份[dp] AND 题目关键词

例如:Anat Rec[ta] AND 2002[dp] AND acupuncture

策略 3:精确题目匹配 使用完整题目(去除特殊字符)进行搜索

搜索结果验证

匹配成功需要满足:

  • PMID 存在
  • 作者姓名匹配
  • 题目高度相似(>80%)
  • 发表年份一致
  • 期刊名匹配

链接格式

PubMed 链接

https://pubmed.ncbi.nlm.nih.gov/{PMID}/

DOI 链接(如果存在)

https://doi.org/{DOI}

全文下载链接

  • 如果是开放获取,直接提供 PDF 链接
  • 否则标注 "Subscription required"

更新文档格式

在原始引用后添加链接信息:

[序号] 作者. 题目[J]. 期刊名, 年份, 卷(期): 页码.
- **PMID**: {PMID}
- **PubMed**: https://pubmed.ncbi.nlm.nih.gov/{PMID}/
- **DOI**: https://doi.org/{DOI} (如果存在)
- **Fulltext**: {下载链接或状态}

批量处理流程

当处理大量文献时:

  1. 初始化检查 - 使用 pubmed_system_check 验证环境
  2. 分组处理 - 每次处理 5-10 篇文献,避免超时
  3. 使用批量查询 - 优先使用 pubmed_batch_query 提高效率
  4. 缓存管理 - 定期使用 pubmed_cache_info 查看缓存状态
  5. 进度记录 - 维护处理进度,支持断点续传

错误处理

未找到匹配文献

  • 尝试不同的搜索策略
  • 检查是否有拼写错误
  • 考虑期刊名称缩写变化
  • 在文档中标注 ⚠️ 未找到匹配

多个匹配结果

  • 选择作者、年份、期刊最匹配的结果
  • 如果仍有歧义,标注 ⚠️ 多个匹配,需人工确认

Read the full file on GitHub · 176 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 176 lines · 67 tokens per session scan A 3d03813a65a9

Subscribe to this mod's changes

pubmed-linker is a skill published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,488 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens