Skip to content

ComeOnOliver/skillshub / skills/aakashg/pm-claude-code-setup/user-research

user-research

Verified

User Research Synthesizer

Trigger

Activate on "synthesize research", "analyze interviews", "research findings", "interview synthesis".

Behavior

Step 1: Get Input

Ask:

  1. Paste the research notes or interview transcripts
  2. What was the research question?
  3. How many participants?

Step 2: Synthesize

Key Findings (ranked by evidence strength) For each:

  • Finding (1 sentence)
  • Evidence (how many participants, quotes)
  • Confidence (High/Medium/Low)
  • Product implication

Themes | Theme | Frequency | Representative Quote | Implication |

Surprises

  • What contradicted our assumptions

Gaps

  • Questions not answered, segments not covered

Recommended Actions

  • Prioritized list with supporting evidence

Example

Bad synthesis (no evidence, no confidence levels):

Key Findings:
- Users like the product
- Onboarding could be better
- Some people want more features

Good synthesis:

Key Findings (ranked by evidence strength):

1. Users abandon onboarding at the "connect integrations" step
   Evidence: 7 of 10 participants hesitated or failed here. 4 said
   variants of "I don't want to give access to my data yet."
   Confidence: HIGH
   Implication: Move integrations to post-activation. Let users see
   value before asking for trust.

2. Power users create personal workarounds for batch editing
   Evidence: 3 of 10 participants (all daily users) showed custom
   keyboard shortcuts or browser extensions they built themselves.
   Confidence: MEDIUM (small sample of power users)
   Implication: Batch editing is a retention lever for heaviest users.
   Worth exploring, but validate with usage data first.

Surprises:
- 6 of 10 participants didn't know the search feature existed. It's
  behind a keyboard shortcut (Cmd+K) with no visible UI entry point.
  This contradicts our assumption that search is well-adopted.

Gaps:
- No participants from enterprise segment (>500 employees). Findings
  may not generalize to that tier.
- Research question about pricing sensitivity was not explored — all
  participants were on free plans.

Rules

  • Use actual quotes, never paraphrases. Quotes are evidence. Paraphrases are interpretation.
  • Findings from 1-2 participants are signals, not conclusions. Label them accordingly.
  • Distinguish said vs. did. Behavior always outranks stated preference.
  • Every finding requires a confidence level AND a product implication. A finding without "so what" is trivia.
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