공식 출처(Tier 1-2)만 검색하여 신뢰도 90점 이상의 정보를 제공하는 전략입니다.
Searches official sources to provide highly reliable technical information with 90+ credibility scores.
/plugin marketplace add inchan/claude-plugins/plugin install icp@inchan-claude-plugin공식 출처(Tier 1-2)만 검색하여 신뢰도 90점 이상의 정보를 제공하는 전략입니다.
허용: Tier 1-2만 제외: Tier 3-4 (커뮤니티, 개인 블로그)
도메인 패턴:
*.org (python.org, reactjs.org)docs.* (docs.python.org, docs.rs)*.dev (react.dev, web.dev)기술별 공식 도메인 예시:
상세 목록: skills/search-core/resources/source-filters.md#Tier-1-공식-문서 참조
GitHub 공식 조직:
공식 블로그:
blog.{공식도메인} (blog.cloudflare.com){공식도메인}/blog (react.dev/blog)사용자: "Next.js data fetching"
최적화: "Next.js data fetching site:nextjs.org OR site:github.com/vercel/next.js"
WebSearch({
query: "{쿼리} site:{공식도메인}",
allowed_domains: ["{공식도메인1}", "{공식도메인2}"]
})
total_score = domain_score + content_score + relevance_score
IF total_score >= 90:
RETURN result
ELSE:
FILTER OUT
참고: skills/search-core/resources/output-formats.md#1
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>