Help us improve
Share bugs, ideas, or general feedback.
From ai-pm
Synthesizes interview transcripts, surveys, and usage logs into actionable insight tables for PM decision-making. Flags low-frequency signals as weak signals without promoting them.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-pm:discovery-synthesizerclaude-opus-4-8The summary Claude sees in its skill listing — used to decide when to auto-load this skill
첨부된 정성/정량 데이터를 합성해 **인사이트 3–7개 + 합성 표 + 한계 절** 을 출력한다.
Share bugs, ideas, or general feedback.
첨부된 정성/정량 데이터를 합성해 인사이트 3–7개 + 합성 표 + 한계 절 을 출력한다.
samples/*.csv|*.json, @<path>, 또는 사용자가 본문에 붙여넣은 트랜스크립트.## 인사이트 1 — <한 문장> — 빈도 / quote 3개 / so-what / 가설.## 합성 표 — 인사이트 vs 우선순위 (5열).## 약한 신호 (참고용) — N<3 패턴들.## 한계 — 표본 편향, 신뢰, 추가 조사 필요.samples/user-survey-results.csv (실습 데이터)~/.claude/guides/evals.md (lazy load)4.1-discovery-user-research.mdgood-examples/synthesis-pm-time.mdbad-examples/vague-themes.mdnpx claudepluginhub kimsanguine/ai_pm --plugin ai-pmSynthesises user signals from multi-research sources (interviews, support tickets, NPS, app reviews, sales calls) into a weighted insight brief with confidence ratings, divergence analysis, and research gaps.
Synthesizes user research from interviews, surveys, feedback into themes, prioritized findings by frequency/impact, and roadmap recommendations.
Synthesizes user research interviews into actionable insights, patterns, and recommendations. Use after conducting user interviews, customer calls, or usability sessions.