med-paper-assistant: Skill for Claude Code

.claude/skills/pubmed-quick-search/SKILL.md

pubmed-quick-search is a skill for Claude Code from u9401066/med-paper-assistant. It costs 40 tokens per session (1,214 once invoked), scanned A, original, Apache-2.0.

A quick research-paper search workflow using PubMed and other scholarly databases. PubMed is a database of biomedical and health research; the workflow can combine results, remove duplicates, and rank them by balance, impact, recency, or quality.

In plain words
What is it for?
Use it to find papers on a topic, check whether research exists, identify representative or recent studies, and limit searches to sources such as PubMed, OpenAlex, Semantic Scholar, Europe PMC, or Crossref.
Why use it?
It removes the need to search several research sources separately during an initial literature check. Filters can narrow results by dates, human studies, or clinical purpose.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is u9401066/med-paper-assistant's own configuration. It tells Claude Code how to work on med-paper-assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything med-paper-assistant configures →

Reuse

Borrowing it

Nothing to install: this file belongs to u9401066/med-paper-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/u9401066/med-paper-assistant/master/.claude/skills/pubmed-quick-search/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/u9401066/med-paper-assistant

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-quick-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/pubmed-quick-search/github.svg)](https://agentmods.dev/skills/u9401066/med-paper-assistant/pubmed-quick-search)
Your own site
<a href="https://agentmods.dev/skills/u9401066/med-paper-assistant/pubmed-quick-search"><img src="https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/pubmed-quick-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.

agentmods 80×15 button for pubmed-quick-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/u9401066/med-paper-assistant/pubmed-quick-search"><img src="https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/pubmed-quick-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,214 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00040 $0.01214
Opus 5 $0.00020 $0.00607
Sonnet 5 $0.00008 $0.00243
Haiku 4.5 $0.00004 $0.00121

Measured 11d ago against content hash 0305ee8d85a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pubmed-quick-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 11d 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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

.claude/skills/pubmed-quick-search/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

快速文獻搜尋

描述

用 unified_search 做第一輪文獻探索。它會自動分析查詢、選擇來源、合併去重,適合快速確認某個主題是否有研究、有哪些代表性文章,以及是否值得進一步做系統性搜尋。

觸發條件

  • 「幫我找...的論文」
  • 「有沒有關於...的文章」
  • 「先快速搜尋一下...」
  • 「search papers about...」
  • 「find articles on...」

核心工具

unified_search(
    query="remimazolam ICU sedation",
    limit=10,
    ranking="balanced",
    output_format="markdown"
)

參數重點

  • query: 自然語言、Boolean 查詢、或包含 ICD 代碼的查詢都可以
  • limit: 每個來源最多取回幾篇
  • sources: 可指定 pubmed,openalex,semantic_scholar,europe_pmc,crossref
  • ranking: balanced, impact, recency, quality
  • filters: 以逗號分隔的篩選條件
  • options: 額外旗標,例如預印本、是否深搜等

快速搜尋時,優先使用自然語言 + filters。只有在需要精細組裝查詢時,才切到系統性搜尋 skill。


最常用範例

1. 一般主題搜尋

unified_search(query="remimazolam ICU sedation", limit=10)

2. 最近幾年的臨床研究

unified_search(
    query="diabetes treatment",
    limit=20,
    ranking="quality",
    filters="year:2020-2025, species:humans, clinical:therapy"
)

3. 看最新研究

unified_search(
    query="lung cancer liquid biopsy",
    limit=15,
    ranking="recency"
)

4. 看高影響力文獻

unified_search(
    query="CAR-T therapy lymphoma",
    limit=15,
    ranking="impact"
)

5. 限定來源

unified_search(
    query="CRISPR gene therapy",
    sources="pubmed,openalex,europe_pmc",
    limit=20
)

6. 納入預印本

unified_search(
    query="COVID-19 vaccine efficacy",
    limit=20,
    options="preprints"
)

filters 速查

filters="year:2020-2025, age:aged, sex:female, species:humans, lang:english, clinical:therapy"

可用欄位

  • year: 2020-2025, 2020-, -2025, 2024
  • age: newborn, infant, preschool, child, adolescent, young_adult, adult, middle_aged, aged, aged_80
  • sex: male, female
  • species: humans, animals
  • lang: english, chinese
  • clinical: therapy, therapy_narrow, diagnosis, diagnosis_narrow, prognosis, etiology

options 速查

options="preprints, shallow"

Read the full file on GitHub · 173 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. 11d ago First seen · 173 lines · 40 tokens per session scan A 0305ee8d85a0

Subscribe to this mod's changes

pubmed-quick-search is a skill published in the GitHub repository u9401066/med-paper-assistant (12 stars, last pushed 10d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,214 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

thesis-control

Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.

yha9806/academic-writing-toolkit · 57 tokens

manuscript-reframe

Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.

yha9806/academic-writing-toolkit · 53 tokens

tikz-figure-review

Review and fix alignment, label collision, clipping, legend-over-data, overlap, and layout issues in TikZ and pgfplots figures inside LaTeX documents. Use when the user wants to review figures in a paper, tutorial, lecture notes, or thesis before submission; when a reviewer flags figure problems; when a rendered…

shubham0704/claude-skills · 177 tokens

animating-computational-mechanics

Animate continuum mechanics, tensor calculus, and finite element concepts — deformation gradients, polar decomposition, Cauchy/Piola–Kirchhoff stresses, weak form, mesh convergence — using Matplotlib (FuncAnimation), Manim (ValueTracker / applyfunction / Transform), or Blender (bpy + ParaView .obj pipeline). Use when…

shubham0704/claude-skills · 185 tokens

refining-ml-papers

Refines ML/scientific LaTeX papers based on reviewer or advisor feedback. Handles structural reorganization (moving problem statements, merging sections), concrete instantiations of abstract tables, cross-file deduplication, and compilation verification. Use when the user requests paper revisions, addresses reviewer…

shubham0704/claude-skills · 75 tokens

rigorous-paper-reviewer

Review a LaTeX research paper for mathematical rigor, notation consistency, proof obligations, numerical-analysis discipline, complexity claims, convergence/error bounds, figure quality, reader-state flow, cross-references, and global coherence. Use when the user wants a deep technical review or verification pass on a…

shubham0704/claude-skills · 128 tokens