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.
npx skills add EthanYoQ/Skill-hub --skill europepmc-searchgit clone --depth 1 https://github.com/EthanYoQ/Skill-hubWrote 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.
[](https://agentmods.dev/skills/ethanyoq/skill-hub/europepmc-search)<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/europepmc-search"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/europepmc-search/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.
<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/europepmc-search"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/europepmc-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00283 | $0.04078 |
| Opus 5.5 | $0.00113 | $0.01631 |
| Sonnet 5.5 | $0.00057 | $0.00816 |
| Haiku 4.5 | $0.00028 | $0.00408 |
Grade A, and why
europepmc-search 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
europepmc-search
Europe PMC RESTful Web Service 的薄封装。一次请求 = 多源召回:PubMed(MED)、PubMed Central(PMC)、AGRICOLA(AGR)、CABI(CBA)、预印本(PPR,涵盖 bioRxiv/medRxiv/ChemRxiv/arXiv 生命科学子集)、专利(PAT)、ETHOS 论文集等。
1. 何时使用本 skill
| 场景 | 用本 skill | 不用本 skill |
|---|---|---|
| RAG 知识库构建,需"撒网"式广召回 | ✅ | |
| 同时要 PubMed + 预印本 | ✅ | |
| 只要 PubMed 官方源 + Clinical Queries | ❌ → pubmed-eutils | |
| 拿 DOI 反查全文 OA 链接 | ✅ | |
| 找特定基金(NIH/NSFC/Wellcome)资助的研究 | ✅(grant_id 检索) |
|
| 抽取已知 PMCID 的全文 XML | ❌ → bioc-fulltext-fetch | |
| 临床试验注册号检索 | ❌ → clinical-trials-v2 | |
| 实体(基因/疾病/化合物)关联 | ❌ → pubtator-entity-search |
与 pubmed-eutils 的差异化(必读):
- pubmed-eutils:PubMed 单源、Clinical Queries 过滤、PubDate 精确范围 → 高精准
- europepmc-search:多源聚合 + 自动去重 + 全文链接 + citations metadata → 高召回
- 推荐编排:RAG 知识库构建用本 skill 广召回 → 拿 PMID 列表喂给 pubmed-eutils 做精准复核
2. 前置准备 / 配置加载
Europe PMC RESTful 是完全开放 API,无需 API key,但服务条款要求传 email 联系方式(礼貌请求,便于 EBI 在大流量异常时联系到使用者)。
配置加载顺序(优先级从高到低):
- 项目级:
.config/europepmc.local.yaml(可选,优先于全局) - 用户级:
~/.config/europepmc.yaml - 环境变量:
EUROPEPMC_EMAIL - 都没有 → 退化为
[email protected]并打印 ⚠️ 警告(建议用户配置)
配置文件示例(~/.config/europepmc.yaml):
email: [email protected]
default_page_size: 100 # 单页条数,1-1000
default_result_type: core # lite | core | idlist
default_format: json # json | xml | dc
timeout_seconds: 30
max_retries: 3
3. API 端点速查
基础 URL:https://www.ebi.ac.uk/europepmc/webservices/rest/
| 端点 | 用途 | 关键参数 |
|---|---|---|
search |
通用检索(本 skill 主力) | query, resultType, pageSize, cursorMark, format, sort |
article/{source}/{id} |
单篇详情 | source∈{MED,PMC,PPR,AGR,CBA,PAT,CTX,ETH,HIR,NBK} |
{source}/{id}/fullTextXML |
全文 XML(仅 OA) | 仅 PMC 子集 |
{source}/{id}/references |
参考文献 | 分页 |
{source}/{id}/citations |
被引列表 | 分页 |
{source}/{id}/supplementaryFiles |
补充材料 | |
grant/search |
资助检索 | query=GR:"R01..." |
4. 核心检索能力(5 个原子函数)
4.1 search_articles(query, source_filter=None, max_results=200, sort=None)
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.
- 1mo ago First seen · 304 lines · 283 tokens per session scan A b19f086bbd66
europepmc-search is a skill published in the GitHub repository EthanYoQ/Skill-hub (11 stars, last pushed yesterday), licensed MIT. It adds 283 tokens to every session and 4,078 once invoked, about $0.0011 per session on Opus 5.5. 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 2026-09-13.
Other skills, from other repositories
preprint-fulltext
Retrieve full text of bioRxiv/medRxiv/arXiv preprints as structured sections to ground scientific reasoning and deep research (methods/results, not just abstracts), or build embedding-ready corpora. Use when a task needs a preprint's full text or sections from a DOI/arXiv id/URL; to verify a claim against a paper's…
hugging-face-trackio
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
molecular-rag
Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
vss-generate-video-calibration
Use this skill when running or tuning AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, or when deploying vss-auto-calibration. Do not use for non-AMC calibration or runtime analytics.
figure-composer
Compose one publication-grade multi-panel figure. Entry from a one-line claim + data files, OR from an existing figure via deriveoutlineprompt (you read the PNG). Runs a per-figure loop: outline (12-col grid, per-panel ask + labelbudget) → render each panel with paneltask (loading figure-style), one at a time or…
paper-narrative
Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. paperbriefprompt(abstract, captions) hands you the prompt to write the brief yourself (pitch/vision/per-figure-claims); then you play a handling editor over the full deck and…