← Back to Skills Marketplace
239
Downloads
0
Stars
0
Active Installs
10
Versions
Install in OpenClaw
/install naver-real-estate-search
Description
Search, compare, and monitor 대한민국 property listings from 네이버 부동산 with natural-language queries. Use when the user wants 강남 아파트 전세 시세 찾기, 특정 지역 매매/전세/월세 비교, 조...
Usage Guidance
This skill is coherent with its stated purpose: it scrapes Naver search and Naver Land to find and compare Korean property listings and stores local JSON seed/cache/watch files. Before installing, consider: 1) Network activity — the scripts perform outbound HTTP requests to search.naver.com and new.land.naver.com; ensure your environment allows/consents to that. 2) Rate limits & anti-bot — the code includes backoff and blocked-state handling; repeated automated queries may trigger 403/429 and could violate site terms. 3) Local dependency mention — SKILL.md references a local upstream 'tmp/naverland-scrapper' repo (not packaged); verify whether your deployment needs that upstream code or whether the included search_real_estate.py implements everything required. 4) Review search_real_estate.py's network/request helpers (_request_text, fetch_complex_info) to confirm there are no unexpected external endpoints, cookies, or telemetry being sent. 5) The skill stores watch/seed cache JSON files under the skill directory; confirm you are comfortable with that local data retention. If you want higher assurance, run the provided --self-test and inspect the specific functions that make HTTP requests before enabling autonomous agent invocation.
Capability Analysis
Type: OpenClaw Skill
Name: naver-real-estate-search
Version: 2026.4.16
The naver-real-estate-search skill bundle is a well-structured tool designed to scrape, compare, and monitor property listings from Naver Real Estate. The scripts (search_real_estate.py, build_candidate_seeds.py, watch_real_estate.py) implement legitimate scraping logic using standard libraries like urllib, with robust handling for rate limits and data normalization. The SKILL.md instructions are purely functional, guiding the AI agent on how to use the provided scripts for property-related queries without any signs of prompt injection or malicious intent. No evidence of data exfiltration, unauthorized network access, or suspicious execution patterns was found.
Capability Assessment
Purpose & Capability
The skill's name/description (Naver real-estate search, compare, monitor) align with the included scripts and data (search_real_estate.py, chat_real_estate.py, watch_real_estate.py, seed builders). All declared requirements are minimal (no env vars, no binaries). One notable point: SKILL.md references an external 'tmp/naverland-scrapper' upstream clone; the package also reuses internal helper names (src.core.*) — this indicates the runtime expects or is designed to reuse an external/local repo in some deployments. That dependency is not packaged or declared as a required config; it's plausible for legitimate reuse but you should be aware the skill may expect local upstream code or different runtime layout.
Instruction Scope
The runtime instructions and scripts focus on: natural-language parsing, candidate seed generation, HTML extraction from search.naver.com, fetching complex detail from new.land.naver.com, local seed/caching, generating JSON/stdout for higher layers. They explicitly read and write skill-local files (references/*, data/*) and call network endpoints for Naver search/land. There are no instructions to read arbitrary user home/system files or to exfiltrate data to unknown third-party endpoints. The only reads of non-skill paths are informational (a generated-file source_input path recorded during generation) — not active reads in the provided scripts. The skill does perform scraping and will perform outbound HTTP requests; that is expected for the purpose.
Install Mechanism
No install spec — instruction-only with packaged Python scripts. Nothing downloads or extracts remote archives. The risk surface is limited to the code shipped in the skill executing at runtime and outbound HTTP requests to Naver domains.
Credentials
The skill requests no environment variables, credentials, or privileged config paths. Its network actions target Naver search and Naver Land and it stores local JSON (candidate-cache, watch-rules, seed files). There are no requests for unrelated secrets or tokens.
Persistence & Privilege
always is false, autonomous invocation is allowed (platform default). The skill stores state only in its own data/ and references/ files (candidate-cache.json, watch-rules.json, candidate-seeds.json). It does not modify other skills or system-wide agent settings. No elevated persistence or hidden self-enablement is present.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install naver-real-estate-search - After installation, invoke the skill by name or use
/naver-real-estate-search - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2026.4.16
Handle missing upstream dependency gracefully and ignore local browser session files
v0.6.3
Polish ClawHub-facing description and intro copy for clearer discovery and positioning
v0.6.2
Add generated seed preview/apply workflow and tighten operating docs.
v0.6.1
운영용 candidate seed 검수 기준 정리 및 서울 주요 단지 수동 검수 큐 반영
v0.6.0
네이버 부동산 스킬 seed 자동 생성기 추가: build_candidate_seeds.py, 서울 주요 단지 입력 seed, generated seed/evidence 출력, 관련 문서 보강
v0.5.0
Add candidate cache seeding, alias warm-cache flow, and watch preview/message JSON.
v0.4.0
alias/캐시 강화, 동일 평형 비교, 감시 schema/JSON 개선
v0.3.0
네이버 부동산 스킬 개선: 후보 탐색 점수화, chat 래퍼 추가, 비교 한국어 브리핑 개선, 가격 감시 초안, README/예제 보강
v0.2.0
네이버 부동산 검색 스킬 개선: 자연어 질의 파싱 강화, 단지 후보 탐색 추가, 여러 단지 비교/시세 요약, 429 백오프 전략, README/설계 문서 보강
v0.1.0
Initial release of 네이버 부동산 검색 스킬.
- 대한민국 네이버 부동산 기반 매물(매매/전세/월세) 검색 지원
- 단지 URL, complex ID, 또는 키워드 기반 조회 가능
- 평수 필터 및 매물 목록 요약 기능
- 결과를 한국어 요약 또는 JSON으로 출력
- 429 rate-limit 발생 시 안내 및 fallback 문구 포함
Metadata
Frequently Asked Questions
What is Naver Real Estate Search?
Search, compare, and monitor 대한민국 property listings from 네이버 부동산 with natural-language queries. Use when the user wants 강남 아파트 전세 시세 찾기, 특정 지역 매매/전세/월세 비교, 조... It is an AI Agent Skill for Claude Code / OpenClaw, with 239 downloads so far.
How do I install Naver Real Estate Search?
Run "/install naver-real-estate-search" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Naver Real Estate Search free?
Yes, Naver Real Estate Search is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Naver Real Estate Search support?
Naver Real Estate Search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Naver Real Estate Search?
It is built and maintained by twbeatles (@twbeatles); the current version is v2026.4.16.
More Skills