Skip to content

deanpeters/Product-Manager-Skills / skills/research-synthesis

research-synthesis

Verified

Turn raw interview notes and feedback into themes, insights, and opportunity statements. Use when you have a pile of research and need to know what it says before deciding anything.

FileKindSize
SKILL.mdskill md13.7 KB
examples/sample-industrial.mdmarkdown2.3 KB
examples/sample.mdmarkdown2.5 KB
template.mdmarkdown1.8 KB

template.md

View on GitHub
# Research Synthesis Template

Every quote, count, and participant traces to the supplied notes, or is `[NEEDS SOURCE]`.
Quality checks at the bottom.

---

## 1. Research frame
**Question:** · **Participants (role, segment, how chosen, N):** · **Sessions / sources:**
**Hypotheses held going in (written before coding):**
1.

## 2. Coded observations (excerpt)
| # | Participant | Observation (their words) | Unprompted? | Contradicts a hypothesis? |
|---|---|---|---|---|

## 3. Themes (affinity groups)
| Theme (customer's words) | Participants | N of total | Strength (unprompted / emotional / only when asked) |
|---|---|---|---|

## 4. Insights
| # | Insight (labeled as interpretation) | Evidence (quotes + participants) | N of total | Confidence (strong / suggestive / thin) |
|---|---|---|---|---|

Insight check: specific · evidenced · decision-relevant · no solution inside.

## 5. Opportunity statements (needs, no solutions)
| # | "I need to..." (customer's words) | From insight # | Ideas heard (kept separate) |
|---|---|---|---|

## 6. Contradictions
| Observation | Cuts against (hypothesis or insight #) | What it changes |
|---|---|---|

## 7. What the research does not show
- Who we did not hear from:
- Questions nobody answered:
- Claims resting on one voice:
- What this sample cannot speak to:

## 8. Next
[Handoff: opportunity tree / more interviews / assumption mapping]

---

## Quality checks
- [ ] Hypotheses were written before coding
- [ ] Every insight traces to quotes and a count
- [ ] Counts are participants (6 of 8), not percentages of a market
- [ ] Observation, interpretation, and opinion are kept apart
- [ ] No solution sits inside an opportunity statement
- [ ] Contradictions are listed and read
- [ ] A gaps list exists
- [ ] Nothing invented: quotes, counts, and participants all trace to the notes
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall