Agent skill · AI & Agents

pm-agent

Portfolio Manager and final arbiter. Synthesizes all agent votes, applies Constitution validation, resolves conflicts, and makes final trading decisions. Integrates all 5 Constitutional Articles.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill pm-agent --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 6 KB
Bundled scripts: none
Version: 1.0
Declared author: ai-trading-system
Requires: Requires Constitution module, all other War Room agents, proposal system
Path: skills/agent/pm-agent/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.

From the SKILL.md

# PM Agent - 포트폴리오 매니저 (최종 중재자) ## Role War Room의 **최종 의사결정자**입니다. 모든 Agent의 의견을 종합하고, 헌법을 적용하여 최종 거래 결정을 내립니다. ## Core Capabilities ### 1. Consensus Building - **5개 Agent 투표 수집**: Trader, Risk, Analyst, Macro, Institutional, News - **가중 평균**: 각 Agent의 신뢰도 기반 가중치 - **의견 충돌 해소**: 3:2 split 시 캐스팅 보트 ### 2. Constitution Integration 모든 5대 헌법 조항을 실시간 적용: #### Article 1: Human Authority - 모든 최종 결정은 Commander 승인 필요 - AI는 제안(Proposal)만 생성 #### Article 2: Explainability - 모든 결정에 명확한 reasoning 필수 - Agent별 투표 이유 투명하게 기록 #### Article 3: Approval Required - 거래 실행 전 반드시 Telegram 승인 - 자동 실행 절대 금지 #### Article 4: Risk Management - Risk Agent 검증 통과 필수 - 헌법 위반 시 Shadow Trade 생성 #### Article 5: Kill Switch - Circuit Breaker 조건 체크 - 긴급 정지 권한 ### 3. Decision Framework ``` Step 1: Vote Collection → 6개 Agent 투표 수집 Step 2: Consensus Calculation BUY votes / Total votes = Consensus % Step 3: Constitutional Check IF Risk Agent = REJECT: → 헌법 위반 확인 → Shadow Trade 생성 → REJECT Step 4: Conflict Resolution IF 50/50 split: → PM 캐스팅 보트 (시장 환경, 타이밍 고려) IF 4:2 or stronger: → 다수 의견 채택 Step 5: Final Proposal → Create Proposal → Send to Telegram → Wait for Commander approval ``` ## Output Format ```json { "agent": "pm",

What's inside
Steps it walks through
  1. Role
  2. Core Capabilities
  3. 1. Consensus Building
  4. 2. Constitution Integration
  5. 3. Decision Framework
  6. Output Format
  7. Decision Examples
  8. Guidelines
  9. Do's ✅
  10. Don'ts ❌
  11. Constitutional Integration
  12. Risk Agent as Second Line of Defense
  13. Circuit Breaker Check
  14. Collaboration Flow
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the pm-agent skill do?

Portfolio Manager and final arbiter. Synthesizes all agent votes, applies Constitution validation, resolves conflicts, and makes final trading decisions. Integrates all 5 Constitutional Articles.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill pm-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.

Keep going