Agent skill

verified-information-generator

Verified information generation and validation

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill verified-information-generator --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 40 KB
Bundled scripts: none
Path: skills/analysis/verified-information-generator/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Adaptive verification system that analyzes a user's question and automatically selects the optimal validation level (Quick, Standard, Academic) for fact-checking. It performs cross-source verification across multiple sources, ranks trust with a simple color label, and produces a structured output including core answer, sources, cross-check results, and limitations. It emphasizes Korean context (KRW currency, domestic regulations) and generates a structured document with sources and a verification checklist.

How it works

  • Analyzes the question to choose an appropriate verification level: Quick (2-3 minutes, 2-3 sources), Standard (7-12 minutes, 3-5 sources), or Academic (15-20 minutes, 5-10 sources).
  • Uses a prioritized multi-source verification process: official documents, peer-reviewed papers, official repositories, trusted tech blogs, and community consensus, then extracts core facts from each source.
  • Compares sources for consistency, highlights discrepancies, and makes additional investigations as needed.
  • Visualizes trust with a three-level label: 🟢 Confirmed, 🟡 Partially Verified, 🔴 Unverifiable.
  • Produces a structured document with sections: core answer, sources, cross-check results, limitations, advanced features, and additional context.
  • Applies Korean context automatically: currency conversion, domestic regulations, and market context.

When to use it

  • When fact-checking technical facts (software versions, API specs, feature support).
  • When comparing data from multiple sources (benchmarks, product comparisons, prices).
  • When creating content (blogs, technical docs, FAQs) requiring fact-checking.
  • When conducting scholarly work (literature verification and citations).
  • When business decisions require regulatory or market context (compliance, market research, competitive analysis).
  • When Korean context is needed (domestic pricing, regulations, market conditions).
  • When verifying compliance with GDPR, HIPAA, etc.
  • When comparing tools/products on features, performance, costs, etc.
  • For trend analysis and urgent information checks.

What it can touch

  • References official documents, academic papers, official repositories, and trusted blogs as sources.
  • Outputs a structured document including sources and cross-check tables.

Caveats

  • Outputs depend on the sources selected by the skill's verification logic.
  • The skill emphasizes Korean context; currency conversion and domestic regulations are included where applicable.
  • Time estimates (2-3, 7-12, 15-20 minutes) are stated as part of level definitions and not guarantees of execution time in all environments.
From the SKILL.md

# Verified Information Generator ## Overview **Verified Information Generator**는 사용자 질문의 복잡도와 맥락을 자동 분석하여, 간단한 팩트체크(2분)부터 학술급 심층 검증(20분)까지 **상황에 맞는 최적의 검증 수준을 자동 선택**하는 적응형 검증 엔진입니다. 핵심 특징: - 🎯 **적응형 검증**: 질문 유형에 따라 Quick/Standard/Academic 자동 선택 - 🔍 **다중 출처 교차 검증**: 3-10개 독립 출처 비교 분석 - 🟢🟡🔴 **신뢰도 라벨**: 검증 수준 시각화 - 🇰🇷 **한국 맥락 최적화**: KRW 환산, 국내 규정/시장 반영 - 📊 **구조화된 출력**: 핵심 답변 → 출처 → 교차검증 → 심층분석 - ⏱️ **투명한 검증**: 소요 시간 및 제한사항 명시 ## When to Use This Skill 이 Skill을 다음과 같은 상황에서 사용하세요: - ❓ **기술적 사실 확인**: 소프트웨어 버전, API 사양, 기능 지원 여부 등 - 📊 **다중 출처 비교**: 벤치마크 결과, 제품 비교, 가격 정보 등 - 📝 **콘텐츠 작성**: 블로그, 기술 문서, FAQ 작성 시 팩트체크 - 🔬 **학술 연구**: 논문 작성 시 선행 연구 검증 및 인용 - 💼 **비즈니스 의사결정**: 규정 준수, 시장 조사, 경쟁 분석 - 🇰🇷 **한국 맥락 필요**: 국내 가격, 규제, 시장 상황 반영 필요 시 - ⚖️ **규정 준수 확인**: GDPR, HIPAA, 개인정보보호법 등 - 🆚 **도구/제품 비교**: 기능, 성능, 비용 등 객관적 비교 - 📈 **트렌드 분석**: 시계열 변화, 업계 동향 파악 - 🚨 **긴급 정보**: 회의 중 빠른 팩트체크 ## Core Capabilities ### 1. 적응형 검증 시스템 질문 분석 후 자동으로 최적의 검증 수준 선택: | 수준 | 시간 | 출처 수 | 적합 상황 | 트리거 예시 | |------|------|---------|-----------|-------------| | **Quick** | 2-3분 | 2-3개 | 단순 팩트, 긴급 확인 | "빠르게", Yes/No 질문 | | **Standard** | 7-12분 | 3-5개 | 실무 문서, 블로그 | 기본 선택 (80% 케이스) | | **Academic** | 15-20분 | 5-1

What's inside
Steps it walks through
  1. Overview
  2. When to Use This Skill
  3. Core Capabilities
  4. 1. 적응형 검증 시스템
  5. 2. 다중 출처 교차 검증
  6. 3. 신뢰도 라벨 시스템
  7. 4. 한국 사용자 최적화
  8. 5. 구조화된 문서 생성
  9. Installation
  10. Claude.ai (Web/Desktop)
  11. Claude Code (CLI)
  12. Usage Guide
  13. 기본 사용법
  14. 고급 사용법
Ships with 1 file
  • metadata.json
Commands it runs
mkdir -p ~/.claude/skills/
cp verified-information-generator-SKILL.md ~/.claude/skills/verified-info.md
claude skills list
claude chat "Claude API 비용을 표준 수준으로 검증해줘"
claude skills install verified-info.md --global
cd /path/to/project
claude skills install verified-info.md --local
More from claude-skill-registry
All skills →
About this skill
What does the verified-information-generator skill do?

Verified information generation and validation

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill verified-information-generator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going