CAT
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Mfds Drug Safety

nomadamas/k-skill
1.6k installs5.3k stars
Summary

This is a Korean drug safety checker that deliberately slows you down before handing back API results from the Ministry of Food and Drug Safety. When someone asks "can I take Tylenol with Pancol?" it doesn't answer immediately. It interviews first: who's taking it, existing medications, symptoms, allergies, red flags like breathing trouble or severe rash. If there's a red flag, it skips the API entirely and routes to emergency services. Otherwise it proxies through k-skill-proxy to pull official drug monographs and interaction data, then summarizes without diagnosing or prescribing. The mandatory interview pattern is the interesting bit here. Most health API wrappers race to show data; this one forces context collection first, which is probably the right call for anything touching medication decisions.

Install to Claude Code

npx -y skills add nomadamas/k-skill --skill mfds-drug-safety --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Files
SKILL.mdView on GitHub

의약품 안전 체크

What this skill does

식약처 공식 OpenAPI를 k-skill-proxy 경유로 조회해 의약품개요정보(e약은요) 와 안전상비의약품 정보를 확인한다.

하지만 사용자가 증상이나 복용 상황을 말하면 바로 단정하지 말고 먼저 되묻는다.

  • 본인/아이/임산부/고령자 여부
  • 어떤 약을 이미 먹었는지 / 지금 먹으려는지
  • 언제부터 얼마나 복용했는지
  • 현재 증상, 기저질환, 알레르기, 복용 중인 다른 약
  • red flag (호흡곤란, 의식저하, 심한 발진, 지속되는 구토/흉통)

red flag 가 있으면 API 조회보다 즉시 119·응급실·의료진 연결을 우선한다.

When to use

  • "이 약이랑 이 약 같이 먹어도 되니?"
  • "타이레놀 먹는 중인데 판콜 같이 먹어도 돼?"
  • "두드러기가 있는데 이 약 계속 먹어도 되나?"
  • "식약처 공식 약 정보로 효능/주의사항 확인해줘"

Prerequisites

  • 인터넷 연결
  • python3
  • 설치된 skill payload 안에 scripts/mfds_drug_safety.py helper 포함
  • k-skill-proxy의 /v1/mfds/drug-safety/lookup route가 있는 hosted/self-host 프록시에 접근 가능할 것

Credential requirements

  • 사용자 측 필수 시크릿 없음.
  • KSKILL_PROXY_BASE_URL — self-host·별도 프록시를 쓸 때만 설정. 비우면 기본 hosted https://k-skill-proxy.nomadamas.org 를 사용한다.
  • DATA_GO_KR_API_KEY 는 프록시 운영 서버 환경에만 둔다.

Mandatory interview first

증상/복용상황이 언급되면 바로 결론을 말하지 말고 먼저 되묻는다.

권장 첫 질문 예시:

  • 누가 복용하려는지(본인/아이/임산부/고령자), 이미 먹은 약 이름, 언제 얼마나 복용했는지, 지금 있는 증상을 먼저 알려주세요.
  • 호흡곤란, 의식저하, 입술·혀 붓기, 심한 전신 발진이 있으면 즉시 119 또는 응급실로 가야 합니다.

Official surfaces

  • 공공데이터포털 문서: https://www.data.go.kr/data/15075057/openapi.do
  • e약은요 endpoint: https://apis.data.go.kr/1471000/DrbEasyDrugInfoService/getDrbEasyDrugList
  • 공공데이터포털 문서: https://www.data.go.kr/data/15097208/openapi.do
  • 안전상비의약품 endpoint: https://apis.data.go.kr/1471000/SafeStadDrugService/getSafeStadDrugInq
  • 프록시 route: GET /v1/mfds/drug-safety/lookup

Workflow

  1. 증상/복용상황이 있으면 인터뷰를 먼저 진행한다.
  2. red flag 가 하나라도 있으면 즉시 응급 안내로 전환한다.
  3. 약 이름이 확인되면 k-skill-proxy의 /v1/mfds/drug-safety/lookup 으로 공식 정보를 조회한다.
  4. 효능, 사용법, 주의사항, 상호작용, 이상반응, 보관법을 짧게 정리한다.
  5. 같이 먹어도 되나? 질문에는 공식 상호작용 문구만 근거로 제시하고, 최종 판단은 약사·의료진 확인이 필요하다고 명시한다.

CLI examples

python3 scripts/mfds_drug_safety.py interview \
  --question "타이레놀이랑 판콜 같이 먹어도 되나요?" \
  --symptoms "두드러기와 어지러움"
python3 scripts/mfds_drug_safety.py lookup --item-name "타이레놀" --item-name "판콜"

Response policy

  • 이 스킬은 진단/처방/복용 지시를 하지 않는다.
  • 공식 문서에 있는 효능/주의/상호작용 문구만 근거로 요약한다.
  • 상호작용 문구가 모호하거나 red flag 가 있으면 약사·의사 상담으로 넘긴다.
  • 증상이 있는 질문은 인터뷰 없이 바로 답하지 않는다.

Done when

  • 증상 또는 복용상황을 먼저 되물었다.
  • red flag 여부를 확인했다.
  • 프록시 route를 통해 공식 endpoint 조회 결과를 JSON으로 정리했다.
  • 최소한 제품명, 업체명, 효능/주의/상호작용이 포함된 요약을 제공했다.
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
First SeenMay 16, 2026
View on GitHub

Recommended

caveman

juliusbrussee/caveman

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
203.4k
67.8k
grill-me

mattpocock/skills

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.
250.9k
114.5k
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for other models/agents to execute.
10
205
systematic-debugging

obra/superpowers

Structured debugging methodology that mandates root cause investigation before attempting any fixes.
124.6k
215.9k
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
13.9k
165.4k
find-skills

vercel-labs/skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.
1.8M
21.1k