npx skills add majiayu000/claude-skill-registry --skill ax-scorecard --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.
# AX Scorecard Skill Signal을 정량 평가하여 Go/Pivot/Hold/No-Go를 판정합니다. ## 입력 - Signal JSON (`signal.schema.json` 준수) ## 출력 - Scorecard JSON (`scorecard.schema.json` 준수) ## 평가 기준 (100점 만점) | 차원 | 배점 | 평가 항목 | |------|------|----------| | **Problem Severity** | 20점 | 고객 Pain 심각도, 빈도, 비용 | | **Willingness to Pay** | 20점 | 예산 존재 여부, Buyer 명확성 | | **Data Availability** | 20점 | 데이터 접근성, 품질, 보안 허들 | | **Feasibility** | 20점 | 기술 난이도, PoC 기간, 리소스 | | **Strategic Fit** | 20점 | AX BD 전략 정합성, 확장성 | ## Red Flags (자동 감점/경고) 다음 조건 중 하나라도 해당 시 Red Flag 표시: - 데이터 접근 불가 (내부 정책/보안) - Buyer/예산 오너 부재 - 규제/법무 이슈 확인됨 - 경쟁사 선점 (6개월 이상 앞섬) - KT DS 역량 외 영역 ## Recommendation 로직 ``` IF total_score >= 70 AND red_flags == 0: decision = "GO" next_step = "BRIEF" ELIF total_score >= 50 AND red_flags <= 1: decision = "PIVOT" next_step = "NEED_MORE_EVIDENCE" ELIF total_score >= 30: decision = "HOLD" next_step = "NEED_MORE_EVIDENCE" ELSE: decision = "NO_GO" next_step = "DROP" ``` ## 출력 예시 ```json { "signal_id": "SIG-2025-001", "total_score": 75, "dimension_scores": { "problem_severity": 18, "willingness_to_pay": 15, "data_availability": 14, "feasibility": 16, "strategic_fit": 12 }, "red_flags": [], "recommendation": { "dec
- 입력
- 출력
- 평가 기준 (100점 만점)
- Red Flags (자동 감점/경고)
- Recommendation 로직
- 출력 예시
- 사용법
What does the ax-scorecard skill do?
Signal 정량 평가 — Scorecard JSON (100점 만점, 5개 차원)
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ax-scorecard --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.