deanpeters/Product-Manager-Skills / skills/research-synthesis
research-synthesis
VerifiedTurn 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.7 KB |
| examples/sample-industrial.md | markdown | 2.3 KB |
| examples/sample.md | markdown | 2.5 KB |
| template.md | markdown | 1.8 KB |
examples/sample.md
View on GitHub# Research Synthesis Example: SaaS
**Research:** 8 dispatcher interviews at Fieldlight customers (service companies, 50-300 technicians)
**Question:** why do rescheduled days still go wrong?
**Hypothesis going in:** "Dispatchers need smarter auto-scheduling" (the team's belief)
**Why this example exists:** the hypothesis was a solution. The synthesis shows the need underneath
it, and one contradiction that changed the insight.
---
```markdown
## Research frame
Participants: 8 dispatchers, recruited from customer accounts by CS (so possibly friendlier than
average). Hypothesis held: smarter auto-scheduling is the answer. [FROM YOU]
## Coded observations (excerpt)
| # | P | Observation | Unprompted | Contradicts hypothesis |
|---|---|---|---|---|
| 14 | P3 | "I print the schedule and rebuild it in a spreadsheet at 2 p.m." | Yes | No |
| 22 | P5 | "The auto-schedule is fine. I can't tell which jobs I'm allowed to move." | Yes | **Yes** |
| 31 | P7 | "I don't trust the board once a rush call lands." | Yes | No |
## Themes
| Theme | Participants | N |
|---|---|---|
| The 2 p.m. rebuild | P1, P3, P4, P5, P7, P8 | 6 of 8 |
| Can't see what's movable | P2, P5, P6, P7 | 4 of 8 |
| Calling customers to renegotiate | P1, P4, P6 | 3 of 8 |
## Insights
| # | Insight | Evidence | N | Confidence |
|---|---|---|---|---|
| 1 | Dispatchers rebuild the day by hand not because the schedule is poor, but because they can't see which jobs are safe to move | Obs 14, 22, 31 | 4-6 of 8 | Suggestive (CS-recruited sample) |
## Opportunity statements
| # | "I need to..." | From | Ideas heard |
|---|---|---|---|
| 1 | "...know which jobs I can move without calling the customer." | 1 | "Color-code flexible jobs" (P2) |
| 2 | "...trust the plan after a rush call lands." | 1 | none |
## Contradictions
Obs 22 (P5): the auto-schedule is fine. It cuts against the hypothesis that scheduling quality is
the problem. It **changed** the insight from "better scheduling" to "visibility of flexibility."
## What the research does not show
- No dispatchers from companies under 50 technicians
- Recruited by CS, so likely engaged customers; unhappy accounts missing
- "Movable" job rules rest on P5 and P7 only; ask others what makes a job movable
```
## What to learn from this
- **The contradiction was the finding.** P5's remark turned a scheduling story into a visibility story.
- **Counts, not percentages.** "6 of 8" says what was true of these eight people.
- **The solution (P2's color-coding) was kept, not buried,** and kept out of the opportunity.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |