菜单
Search the internet for up-to-date information and fetch web page content via Tavily. Use for: 검색해줘, 찾아줘, 최신 정보, 인터넷 검색, 뉴스, 요즘, web search, latest news, current information
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
One-shot import of Google Contacts (People API) into the user's Connect (인맥) list. Pages through every contact, dedupes against existing connections by email then phone, and inserts new rows with category=acquaintance and tags=['google_contacts']. Honors BR-SOCIAL-3 — never writes social_profiles even if Google returns LinkedIn URLs. Use for: 구글 연락처 가져오기, 연락처 동기화, contacts import, import google contacts, sync google contacts, google 연락처, 인맥 가져오기, 주소록 가져오기
Record and sync Connect (인맥) activity timeline entries. Pulls from Google Calendar + Gmail (shares google-workspace OAuth token), or accepts manual entries like '김철수와 어제 점심 먹었어'. Use for: 인맥 활동, 활동 기록, 만남 기록, 미팅 기록, 점심, 저녁, 통화 기록, 일정 동기화, 인맥 동기화, connect sync, connect activity, meeting log, met with, had lunch with
Add or replace Context Memo (context_notes) for a Connect (인맥) entry. Looks up the target connection by exact or fuzzy name when the agent doesn't already know the connection UUID. Use for: 인맥 메모, 인맥 메모 추가, 메모 추가, 메모 수정, 인물 메모, 사람 메모, connect memo, add note, update note, context note
Scan a business card image with Gemini Vision and extract structured contact fields (name, role, company, email, phone, address, etc.) to create a new Connect (인맥) entry. Use for: 명함, 명함 스캔, 명함 등록, 명함 인식, 명함 저장, 명함 추가, 인맥, 인맥 추가, 인맥 등록, 연락처 등록, 연락처 추가, 비즈니스 카드, business card, business card ocr, scan business card, contact card, register contact
"Analyze uploaded images using Gemini Vision, or generate/edit images with Gemini AI. Use for: 이미지 분석, 사진 분석, 이미지 생성, 그려줘, 그림 만들어줘, image generation, photo analysis"
Record notes in the Planner's '노트' section. Use for: 노트, 노트에 기록, 메모, 메모해줘, 노트 저장, 노트 추가, note, memo
| name | websearch |
| display_name | Tavily 검색 |
| description | Search the internet for up-to-date information and fetch web page content via Tavily. Use for: 검색해줘, 찾아줘, 최신 정보, 인터넷 검색, 뉴스, 요즘, web search, latest news, current information |
| version | 1.0.0 |
| emoji | 🔍 |
| category | search |
| enabled_by_default | true |
| requires_api_key | true |
| platforms | web, telegram, api |
| api_key_provider | tavily |
| api_key_label | Tavily API Key |
| uses_provider | false |
| allowed-tools | ["Bash","exec"] |
| triggers | {"keywords":["검색해줘","찾아줘","최신 정보","인터넷에서","웹에서","뉴스","요즘","지금","알려줘","search","look up","find online","latest","current news","web search","internet"],"when_to_use":["User asks for up-to-date information that may have changed recently","User asks to search the internet for news or current events","User asks to fetch or read the content of a specific web page URL","User says \"검색해줘\", \"찾아줘\", or \"최신 정보 알려줘\""],"not_for":["Searching within knowledge base documents (use documents skill)","Korea-specific searches where Naver would be better (use naver-search skill)"]} |
Always pass --user-id {user_id}.
TAVILY_API_KEY is automatically injected as an environment variable when configured in the web UI.
Always attempt to run the script — it will report if credentials are missing.
python3 websearch/scripts/websearch.py \
--user-id {user_id} search \
--query "{검색 키워드나 질문}" \
--max-results 5
python3 websearch/scripts/websearch.py \
--user-id {user_id} search \
--query "{검색 쿼리}" \
--search-depth advanced \
--topic news \
--time-range week \
--include-answer \
--max-results 5
python3 websearch/scripts/websearch.py \
--user-id {user_id} fetch \
--url "{https://...}" \
--max-length 8000
--max-results N: 결과 개수 (기본: 5, 최대: 10)--search-depth basic|advanced: 검색 깊이 (기본: basic)
basic: 빠른 일반 검색advanced: 심층 연구 수준, 가장 관련성 높은 결과--topic general|news|finance: 검색 주제 (기본: general)
news: 최신 뉴스·실시간 업데이트finance: 주식·금융 정보--time-range day|week|month|year: 기간 필터--include-answer: AI 생성 요약 답변 포함--include-domains domain1,domain2: 특정 도메인으로 제한--exclude-domains domain1,domain2: 특정 도메인 제외--max-length N: 최대 텍스트 길이 (기본: 8000, 최대: 50000)search: 결과 목록 (제목, URL, 요약 포함) fetch: 웹페이지 텍스트 내용 (HTML → 가독성 있는 텍스트 변환)
| User intent | Command | Options |
|---|---|---|
| Latest news or current events | search | --topic news --time-range day |
| Fact-checking or general information | search | (default) |
| Deep research with comprehensive results | search | --search-depth advanced --include-answer |
| Summarize or extract content from a specific URL | fetch | — |
| Get full content of a search result | fetch | use URL from search result |
User: "오늘 뉴스 알려줘"
python3 websearch/scripts/websearch.py \
--user-id abc123 search \
--query "오늘 주요 뉴스" \
--topic news \
--time-range day \
--max-results 5
User: "비트코인 현재 가격"
python3 websearch/scripts/websearch.py \
--user-id abc123 search \
--query "bitcoin price today" \
--topic finance \
--max-results 3
User: "이 기사 내용 요약해줘: https://..."
python3 websearch/scripts/websearch.py \
--user-id abc123 fetch \
--url "https://..." \
--max-length 8000
--search-depth advanced와 고급 옵션은 Tavily 키 설정 시에만 유효