discovery-synthesis
Skill25 starsChanged 10 days agoMITView on GitHub
archive.sqlite / customers.md / memory ledger 에서 JTBD / 문제 신호 / 사용자 패턴 추출. 사용자와 Q&A 안 함 (데이터 분석기). interview transcript 가 업로드되면 분석 포함.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Nomanriaz786/claude-consulting-teamtheir own version, first seen Nov 1, 2026
- andreaskelm/pm-braintheir own version, first seen Oct 17, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- andreaskelm/pm-brain★ 235same name
- Nomanriaz786/claude-consulting-team★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- build-testSkill
- trend-trackerSkill
- typecheckSkill
- agent-managerSkill
- cron-managerSkill
- design-systemSkill
- docsSkill
- experiment-designSkill
- goal-managerSkill
- hypothesis-designSkill
- interview-scriptSkill
- jobs-storiesSkill
- lean-canvasSkill
- market-researchSkill
- meceSkill
- okrSkill
- opportunity-treeSkill
- policySkill
- prdSkill
- premortemSkill
- primitive-reviewSkill
- prioritizationSkill
- retrospectiveSkill
- skill-managerSkill
- skill-refinementSkill
- triageSkill
- wbsSkill
- workflow-managerSkill
- workflow-refinementSkill
- xyz-hypothesisSkill
The file
Files
Discovery Synthesis Skill
데이터 분석기, 챗봇 아님. 사용자 메시지 archive / customers.md / memory ledger / interview transcript 에서 JTBD 신호 추출. 사용자에게 직접 인터뷰하지 않는다.
입력 소스
<org>/memory/archive.sqlite— 사용자 대화 FTS5 아카이브<org>/domain/customers.md— 누적된 customer 가설<org>/memory/ledger/<task-id>.jsonl— 과거 task 결과<org>/memory/interview-transcripts/— (선택) Chief 가 인터뷰 스크립트 받아 사용자가 실제 고객과 진행한 transcript 업로드- team KNOWLEDGE.md — 팀 도메인 지식
산출물
{
"jtbd_signals": [
{
"when": "...",
"i_want": "...",
"so_i_can": "...",
"evidence_refs": ["archive#123", "customers.md#L42"],
"frequency": 1
}
],
"problem_patterns": [
{
"pattern": "string",
"occurrences": 5,
"evidence_refs": ["..."]
}
],
"gaps": [
"string" // 데이터로 풀 수 없는 영역 → open_question 으로 escalate
]
}JTBD 형식
Mom Test + Ulwick 표준:
- "사용자는 [상황] 일 때, [고용하는 job] 을 통해, [기대 결과] 를 얻고 싶다"
- "When [situation], I want to [job], so I can [outcome]"
Anti-Sycophancy
JTBD 신호 진술은 evidence 명시:
- ❌ "사용자는 X 를 원할 것입니다"
- ✅ "archive 5건, customers.md 2건이 X 패턴을 시사합니다. Y 신호가 추가로 발견되면 이 가설 강화/약화 됩니다."
Gaps → open_questions
데이터 부족 영역은 problem-definition.P1 의 open_question 으로 escalate:
{
"stage": "discovery-synthesis",
"type": "data_request",
"question": "[segment X] 의 frustration 데이터가 부족합니다. 사용자가 최근 X 와 관련해 어떤 경험을 했는지 알 수 있을까요?",
"blocking": false
}Reference
- Mom Test (Rob Fitzpatrick)
- JTBD theory (Clayton Christensen, Tony Ulwick)
- phuryn/pm-skills/pm-product-discovery/summarize-interview
- v1.1 PRD §6.2 (PM 자율 작동 흐름)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

