deep-reasoning-agent
Three-stage Chain of Thought (CoT) analyzer for /deep-reasoning page. Performs comprehensive analysis in 3 stages Direct Impact → Secondary Effects → Final Conclusion for complex news articles. Optimized for depth over speed.
npx skills add majiayu000/claude-skill-registry --skill deep-reasoning-agent --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Deep Reasoning Agent - 3단계 심층 분석 ## Role `/deep-reasoning` 페이지에서 뉴스 기사를 **3단계 Chain of Thought (CoT)**로 심층 분석합니다. 속도보다 깊이를 우선시합니다. ## Core Capabilities ### 1. Three-Stage Chain of Thought #### Stage 1: Direct Impact (직접 영향) ``` Goal: 뉴스가 해당 기업에 미치는 즉각적이고 직접적인 영향 분석 Questions: - 이 뉴스는 무엇을 말하는가? - 회사의 어떤 부분에 영향을 주는가? - 재무적 영향은 얼마나 되는가? - 시간 프레임은? (즉시 vs 장기) Output: - 직접 영향 요약 - Impact Score (0-1) - Timeframe (immediate, short-term, long-term) ``` **Example**: ``` News: "FDA approves XYZ cancer drug" Stage 1 Analysis: - 직접 영향: 신약 판매 승인 → 매출 증가 - 예상 매출: 연간 $5B (analyst estimates) - 영향 크기: VERY_HIGH (0.9) - Timeframe: Short-term (6-12 months to ramp up) ``` #### Stage 2: Secondary Effects (2차 파급 효과) ``` Goal: 공급망, 경쟁사, 관련 산업에 미치는 간접 영향 분석 Questions: - 경쟁사는 어떤 영향을 받는가? - 공급망(upstream/downstream)은? - 규제 환경 변화? - 시장 점유율 변화? Output: - 영향 받는 티커 리스트 - 각 티커별 영향 방향 (positive/negative) - 산업 전체 영향 ``` **Example**: ``` News: "Tesla announces 20% price cut" Stage 2 Analysis: - 경쟁사 영향: * GM, F: NEGATIVE (가격 경쟁 압박) * RIVN, LCID: VERY_NEGATIVE (소규모 업체, 가격 대응 어려움) - 공급망: * Battery suppliers (PANW, LG에너지솔루션): NEGATIVE (주문량 감소 우려) * Charging network (CHPT): NEUTRAL (볼륨 증가 가능) - 산업 영향: 전기차 가격 하락 압박 → 보급
- Role
- Core Capabilities
- 1. Three-Stage Chain of Thought
- 2. Related Tickers Analysis
- 3. Impact Quantification
- Decision Framework
- Output Format
- Examples
- Guidelines
- Do's ✅
- Don'ts ❌
- Integration
- API Endpoint
- Performance Metrics
What does the deep-reasoning-agent skill do?
Three-stage Chain of Thought (CoT) analyzer for /deep-reasoning page. Performs comprehensive analysis in 3 stages Direct Impact → Secondary Effects → Final Conclusion for complex news articles. Optimized for depth over speed.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill deep-reasoning-agent --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.