CCM
/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

Claude Code Marketplaces

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

Daangn Realty Search

nomadamas/k-skill
1.3k installs6.2k stars
Summary

A read-only search wrapper for Daangn (Karrot) real estate listings in Korea. It resolves region names to internal IDs, scrapes public Remix `_data` JSON routes for search results, and pulls details from JSON-LD and HTML meta tags. You can query by natural language ("find Hapjeong-dong jeonse") or run the Python helper directly with filters for sales type, trade type, and price. It handles duplicate region names with sensible fallbacks (Seoul dong-level preferred, then first match) and always shows you which region actually got applied. No auth, no favoriting, no booking automation, just listings with source URLs. Fails gracefully when Daangn changes their route structure or throws up a login wall.

Install to Claude Code

npx -y skills add nomadamas/k-skill --skill daangn-realty-search --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download 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 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download 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 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Files
SKILL.mdView on GitHub

Daangn Realty Search

What this skill does

당근부동산 지도 페이지(realty.daangn.com/map/{name1}/{name2}/{name3})의 SSR window.RELAY_STORE(Relay 정규화 스토어)를 파싱해 매물 후보를 정리한다. 제목·주소·층수는 상세 페이지의 JSON-LD에서 보강한다. 외부 패키지 없이 Python 표준 라이브러리만 사용한다.

When to use

  • "당근부동산 매교동 월세 찾아봐"
  • "수원 팔달구 상가 매물 봐줘" (--expand로 인접 동까지)
  • "이 당근부동산 URL 상세 요약해줘"

When not to use

  • 당근 계정 로그인이 필요한 작업
  • 채팅, 찜, 거래 제안, 문의, 예약, 계약, 구매처럼 상대방/계정에 영향을 주는 작업
  • CAPTCHA/봇 차단/로그인벽 우회가 필요한 작업

Prerequisites

  • 인터넷 연결, Python 3.9+

Data surfaces (2026-06 도메인 이전 대응)

  • Region resolver: https://www.daangn.com/kr/api/v1/regions/keyword?keyword=<지역명> → {"locations":[{id,name1,name2,name3,name*Id,depth}]}
  • 매물 목록: https://realty.daangn.com/map/{name1}/{name2}/{name3} 의 window.RELAY_STORE
  • 상세: https://realty.daangn.com/articles/<id> 의 application/ld+json

⚠️ 구버전(www.daangn.com/kr/realty/?_data=routes/kr.realty._index)은 2026-06부터 HTTP 204(빈 응답)로 폐기됨. 절대 사용 금지.

RELAY_STORE 파싱 경로 (검증됨)

ArticleFeedConnection.edges → ArticleFeedEdge.node → ArticleFeedCard.article → Article
  • 스토어에 ArticleFeedCard가 직접 다 들어있어, Card를 순회 → article ref 디레퍼런스가 가장 견고하다.
  • Article: originalId, area(㎡, 문자열일 수 있어 float 변환 필수), salesTypeV3(→*SalesTypeV2.type), trades(→ Month/Buy/BorrowTrade)
  • 가격 단위 = 만원: deposit(보증금), monthlyPay(월세), price(매매가). 예: deposit 2000 = 2천만원, price 28700 = 2억8,700만.
  • window.RELAY_STORE는 JS 문자열로 이스케이프돼 있다 → json.loads(json.loads('"'+raw+'"')) 2단 디코드.

Trade 유형 & 평당 단가

거래유형typename가격 필드평당 단가
월세(MONTH)MonthTradedeposit + monthlyPaymonthlyPay / 평
매매(BUY)BuyTradepriceprice / 평
전세(BORROW)BorrowTradedepositdeposit / 평

평 = ㎡ / 3.305785.

salesType enum

APART, OFFICETEL, STORE, OPEN_ONE_ROOM, SPLIT_ONE_ROOM, TWO_ROOM, HOUSE 등.

층수 (상세 JSON-LD)

목록엔 층수가 없다. 상세 페이지 Product.additionalProperty 배열에서:

  • floor(예 "8.0") / topFloor(예 "10") → floor_label = "8층/10층"
  • nearbySubwayStation 도 함께 추출. 제목은 Product.name, 주소는 Place.name.

Commands

# 기본 검색 (상위 5개 제목·층수 보강)
python3 daangn-realty-search/scripts/daangn_realty.py search --region "매교동" --limit 20

# 거래/용도 필터
python3 ... search --region "매교동" --trade-type BUY            # 매매만
python3 ... search --region "매교동" --sales-type STORE,OFFICETEL # 용도 콤마구분

# 인접 동까지 확장 (같은 구/시)
python3 ... search --region "매교동" --expand --expand-max 6

# 상세
python3 ... search --region "매교동" --titles 0   # 제목 보강 끄기(빠름)
python3 ... detail "https://realty.daangn.com/articles/2947028"

옵션: --limit(기본 20), --titles N(상세로 제목·층수 보강할 상위 N, 기본 5, 0=끔), --expand/--expand-max(기본 6). 기존 CLI 호환 옵션인 --keyword는 반환 매물의 공개 필드 텍스트를 필터링한다. --only-verified는 공개 피드에서 별도 인증 필드를 제공하지 않아 호환 목적으로만 허용한다.

Output fields

매물: article_id, salesType, area_sqm, area_pyeong, trades[{type,label,deposit_manwon,monthly_manwon,price_manwon,per_pyeong_manwon}], url, region, title, address, floor_label, nearby_subway, release_date

release_date는 상세 페이지 JSON-LD의 Product.releaseDate(ISO 8601, UTC)이며 --titles 보강 대상 매물에만 채워진다. 최초 등록일인지 최근 끌어올리기/수정일인지는 당근 쪽 명세에 없어 확정할 수 없다.

Region handling

지역명 → region API로 내부 id 해석. 동명이 여럿이면 정확일치 → 서울 depth=3 → 첫 후보 순. 응답에 effective_region 포함. --expand는 같은 name2Id(구/시) 인접 동을 모은다.

Safety and scope

  • 읽기 전용 검색/상세만. 로그인·채팅·거래·예약·계약 자동화 없음.
  • 공개 표면이 바뀌거나 빈 응답/봇 차단이면 실패 모드로 보고하고 우회하지 않는다.
  • 결과는 실시간 호가라 실거래와 다를 수 있으므로 source URL을 함께 제시.

Failure modes

  • RELAY_STORE 없음 (sources note) → 페이지 구조 재변경 또는 봇 차단. HTML 구조 재확인 필요.
  • 시군구(name2) 랜딩 URL은 매물이 없다 — 반드시 동(name3)까지 있어야 articleFeed가 SSR로 채워진다.
  • 동명이 넓거나 중복되면 다른 행정동 선택 가능.
  • 상세는 삭제/비공개 글에서 실패할 수 있다.

Done when

  • 지역 id 해석 → map URL의 RELAY_STORE에서 매물 추출 → source URL·effective_region 포함.
  • 인증/거래성 액션은 수행하지 않았다.

Notes

  • Windows stdout 한글 깨짐 방지: 지원 런타임에서는 sys.stdout.reconfigure(encoding='utf-8')를 적용한다.
  • area·가격 필드가 문자열로 오는 케이스가 있어 모든 수치 연산 전 float 변환 가드.
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download 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 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
First SeenJun 3, 2026
View on GitHub

Recommended

caveman

juliusbrussee/caveman

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
348.3k
88.9k
grill-me

mattpocock/skills

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.
546.6k
168.9k
improve

shadcn/improve

improve
23.2k
8.1k
systematic-debugging

obra/superpowers

Structured debugging methodology that mandates root cause investigation before attempting any fixes.
185.7k
253.9k
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
17.9k
191.7k
find-skills

vercel-labs/skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.
2.5M
26k