Token导航 LogoToken导航

Agent Skill · 研究检索

medical-newsletter-writer(医学通讯作家)

medical-newsletter-writer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

medical-newsletter-writer 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 41,189。

总安装 1,211周安装 52GitHub Stars 3下载 424核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:medical-newsletter-writer(医学通讯作家)
来源仓库:https://github.com/drshailesh88/integrated_content_os
仓库路径:skills/medical-newsletter-writer
安装命令:
npx skills add https://github.com/drshailesh88/integrated_content_os --skill medical-newsletter-writer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/drshailesh88/integrated_content_os --skill medical-newsletter-writer

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

medical-newsletter-writer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景定位候选结果。适用于需要快速获取信息或线索的场景,如医学通讯撰写或内容策划。通过关键词、来源仓库或任务描述触发检索,返回结构化候选列表。

安装前需确认权限范围,注意是否会触发联网或文件操作,建议检查维护状态。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/medical-newsletter-writer

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/drshailesh88/integrated_content_os --skill med…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

medical-newsletter-writer 怎么安装?

在终端执行 npx skills add https://github.com/drshailesh88/integrated_content_os --skill medical-newsl…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

medical-newsletter-writer 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

medical-newsletter-writer 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

medical-newsletter-writer 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

medical-newsletter-writer 用的人多吗?

公开数据是累计安装 1,211 次,近一周安装 52 次,下载 424 次,GitHub 3 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

medical-newsletter-writer 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
medical-newsletter-writer

医学通讯作家 · 本页

1,2113只读MIT有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Medical Newsletter Writer

Create high-quality, evidence-based medical newsletters in the style of Eric Topol's Ground Truths. This skill guides the complete newsletter creation process: from analyzing your PDF of topic ideas, to deep PubMed research, to writing in Topol's distinctive authoritative-yet-accessible voice.

Quick Start

Simple 3-Step Process:

  1. Upload PDF - Upload your PDF with topic ideas in the chat
  2. Select Topic - Review engagement predictions and pick one topic
  3. Get Newsletter - Receive complete, publication-ready newsletter (~3,000 words with 20-30 PubMed citations)

The skill handles everything: PDF extraction, trend analysis, PubMed research, and writing in Eric Topol's exact voice.

Complete Workflow

The newsletter creation process has 5 phases:

  1. Extract Topics from PDF - Read user's uploaded PDF of topic ideas
  2. Trend Analysis - Analyze each topic for engagement potential
  3. Topic Selection - User approves topics based on data-driven predictions
  4. Deep Research - Comprehensive PubMed literature review
  5. Newsletter Writing - Write complete newsletter in Topol's style

Phase 1: Extract Topics from PDF

PDF Upload

User will upload a PDF containing potential newsletter topic ideas in the chat.

Extract Topics

  • Read the PDF using available tools
  • Extract all topic ideas mentioned
  • Clean and organize the list
  • If PDF contains notes/context about topics, capture that too

Phase 2: Trend Analysis & Engagement Prediction

Analyze Each Topic (Automatically)

For each topic extracted from the PDF, conduct comprehensive trend analysis:

1. News Coverage (Google News, medical news sites)

  • Search past 30 days
  • Note which outlets covering
  • Identify breaking developments
  • Count article frequency

2. Search Interest

  • Use web_search to assess current discussion
  • Look for rising interest signals
  • Note if topic is trending

3. Social Media Signals

  • YouTube: Search for videos, note view counts
  • Check if medical professionals are discussing
  • Assess virality potential

4. Academic Momentum (PubMed)

  • Count recent publications (6 months)
  • Check for major journal coverage
  • Identify ongoing trials
  • Note if field is active

Engagement Prediction Scoring

For each topic, score 1-10 on:

  1. Readability: Can this be explained clearly to physicians?
  2. Controversy: Is there debate/opposing views?
  3. Clinical Relevance: Will this affect patient care?
  4. Timeliness: How current is this? Breaking news?
  5. Share Potential: Will physicians share with colleagues?

Overall Engagement Score = Average of 5 metrics

Present Analysis

Create comparison table with:

  • Topic name
  • Brief trend summary (2-3 sentences)
  • Individual scores (1-10)
  • Overall engagement score
  • Priority recommendation (High/Medium/Low)

Sort by overall score, present top 5-10 topics to user.

Phase 3: Topic Selection

Present findings to user with:

  • Top topics by engagement prediction
  • Rationale for scores
  • Notable timeliness factors

User selects ONE topic - then the skill automatically proceeds to research and writing.

Phase 4: Deep Research (Automatic)

PubMed Search Strategy

Before searching, read workflow.md for detailed research guidance.

Initial searches:

  1. Broad topic overview
  2. Recent findings (<1 year)
  3. Systematic reviews/meta-analyses
  4. Major clinical trials

Paper Prioritization:

  • Tier 1: Large RCTs in NEJM, Lancet, JAMA, Science, Nature
  • Tier 2: Meta-analyses and systematic reviews
  • Tier 3: Large observational studies
  • Tier 4: Mechanistic studies in high-impact journals
  • Tier 5: Pre-clinical (use sparingly)

Target: 15-30 highly relevant papers

Extract Key Information

For each major paper:

  • Study design and sample size
  • Key findings (quantitative)
  • Limitations
  • How it fits the narrative
  • Potential quotes/figures

Find Related Work

  • Use PubMed related articles
  • Check major paper citations
  • Look for responses/commentary
  • Identify consensus vs. controversy

Phase 5: Newsletter Writing (Automatic)

Before Writing

CRITICAL: Read topol-style-guide.md first - This contains essential voice patterns, phrases, and stylistic requirements.

Structure

Opening (1-2 paragraphs)

  • Hook using Topol's opening patterns (see style guide)
  • Why this matters NOW
  • What will be covered

Background/Context (optional)

  • Define key terms: "To review: [term] is..."
  • Historical perspective if relevant
  • Current state of field

Main Content (3-5 sections with clear headers)

  • Each section = one major subtopic
  • Build logically
  • Include data/studies in each
  • Use tables to compare studies/treatments
  • Reference figures from papers

Implications/Future Directions

  • What this means for practice
  • Research gaps
  • What's next

Bottom Line (required)

  • Synthesize key takeaways
  • Clear conclusions based on evidence
  • Call for more evidence if needed

Standard Closing (required)

Thanks for reading and subscribing to Ground Truths.

If you found this interesting PLEASE share it!

That makes the work involved in putting these together especially worthwhile.

All content on Ground Truths—its newsletters, analyses, and podcasts, are free, open-access.

Paid subscriptions are voluntary and all proceeds from them go to support Scripps Research. They do allow for posting comments and questions, which I do my best to respond to. Please don't hesitate to post comments and give me feedback. Let me know topics that you would like to see covered.

Writing Requirements

Voice & Style:

  • First person engaged ("I recently fielded questions...")
  • Authoritative but accessible
  • Critical and evidence-based
  • Use Topol's signature phrases (see style guide)

Citations:

  • EVERY factual claim needs a PubMed citation with hyperlink
  • Format: link text embedded in prose
  • Cite original studies, not news articles
  • Include author names for major findings: "Professor X and colleagues at Y University published in Z..."

Critical Analysis:

  • Always discuss study limitations
  • Note conflicts of interest if relevant
  • Present alternative interpretations
  • Flag when evidence is preliminary
  • Call out hype vs. data

Length: 2,000-3,500 words

Visual Elements:

  • Create tables comparing studies/treatments
  • Describe figures from papers
  • Use clear section headers

Quality Checks

Before finalizing:

  • Engaging opening hook?
  • Clear why-this-matters framing?
  • Every claim cited?
  • Limitations discussed?
  • Topol's voice consistent?
  • Tables/figures included?
  • Logical flow?
  • "Bottom Line" section?
  • Standard closing?
  • 2,000-3,500 words?

Delivery

Final Format

  • Complete newsletter in Markdown
  • All hyperlinked citations to PubMed
  • 2,000-3,500 words
  • Ready for user's newsletter platform

Customization Note

User may want to change "Scripps Research" in the standard closing to their own institution/practice name.

Essential References

ALWAYS READ BEFORE WRITING:

  • topol-style-guide.md - Complete guide to Topol's voice, phrases, patterns
  • workflow.md - Detailed research and writing process

Key Success Factors

  1. Evidence-based: Every claim must be cited
  2. Critical thinking: Discuss limitations, not just positives
  3. Voice consistency: Sound like Topol throughout
  4. Comprehensive: Cover topic thoroughly with multiple studies
  5. Accessible: Technical accuracy without excessive jargon
  6. Timely: Focus on recent developments
  7. Visual: Include tables/figures to enhance understanding
  8. Engaging: Hook readers immediately, maintain interest

Example Opening Lines (Topol Style)

  • "In fielding questions recently from patients and colleagues about [topic], I was prompted to look into the field at more depth."
  • "[Term] was coined in the late [year]. Now, about [X] years later, we've yet to achieve [goal]."
  • "This week [major development] was published in [journal]. Several important reports have since been published. I've incorporated them in this updated version."
  • "There's no question that the use of [intervention] has surged, in part because of [claims], along with endorsements by [influencers]."

Common Pitfalls to Avoid

  • Don't rely on single studies - use multiple sources
  • Don't ignore study limitations - they're critical
  • Don't cherry-pick data - present full picture
  • Don't get too technical - stay accessible
  • Don't use bullet points excessively - prefer prose
  • Don't skip the critical analysis - it's essential
  • Don't forget visual elements - tables enhance understanding
  • Don't deviate from Topol's voice - consistency matters

平台分布

Claude Code

26.25%
按下载量换算111

Antigravity

21.79%
按下载量换算92

OpenCode

16.43%
按下载量换算70

Gemini CLI

13.58%
按下载量换算58

windsurf

7.73%
按下载量换算33

Codex

3.23%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills