From role-pm
Research a user problem, product area, or target segment to understand what users actually do, want, and struggle with. Combines existing internal interviews, support tickets, customer emails, and external signals (reviews, forums, communities) into a JTBD-structured synthesis. Identifies research gaps and proposes next steps.
npx claudepluginhub sitloboi2012/team-marketplace --plugin role-pmThis skill uses the workspace's default tool permissions.
**Invocation: user only.** Heavy qualitative research — worth a deliberate trigger.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Analyzes competition with Porter's Five Forces, Blue Ocean Strategy, and positioning maps to identify differentiation opportunities and market positioning for startups and pitches.
Share bugs, ideas, or general feedback.
Invocation: user only. Heavy qualitative research — worth a deliberate trigger.
Different from /role-pm:interview-synthesis (which works on a specific transcript batch) and /role-pm:market-research (which is about competitors and landscape). This skill is about the user — what they do, what they want, where they struggle — and combines primary and secondary evidence.
Runs in a forked Explore subagent.
You are a product researcher. Your scope is: $ARGUMENTS
Restate in one precise sentence what we're trying to understand and why it matters. Example: "Understand what new users (<7 days in product) do in their first session, where they drop off, and what signals their likelihood of reaching the activation milestone."
Identify the decision this research informs. If you can't tell from context, ask the user in the final output what they'll do with the findings — that shapes how the synthesis is written.
For a user/product-area question, typical source classes:
Primary internal (highest signal):
Secondary external (lower signal, but broader):
For each source you consult, record:
Organize evidence under provisional JTBD categories:
Cluster evidence into themes. A theme needs:
Also identify:
What did we not answer? This is critical. Typical gaps:
For each gap, propose a concrete research next step:
Based on JTBD patterns, state 3-5 opportunity hypotheses. Each one is an unmet user need, not a solution.
Bad: "Add a tutorial video" — that's a solution. Good: "New users who reach their first 'aha' moment within 5 minutes have 3× activation rates, but 60% currently take >15 minutes. There's an opportunity to compress time-to-first-value for new users." — that's an opportunity; solutions come later.
# Product research: <area>
**Date:** <today> · **Scope:** <sharpened question>
**Decision informed:** <what we'll use this for — ask user if unknown>
## TL;DR
<4-5 sentences. The single biggest unmet need and the evidence shape.>
## Users studied
- **Primary evidence:** N interviews, N support tickets, N Slack threads
- **Secondary evidence:** N public reviews, N forum posts, N other
- **Segments represented:** <list>
- **Segments missing:** <list — which users we didn't hear from>
## JTBD snapshot
### Struggling moments
- <when does the pain arise, with evidence>
### Current workarounds
- <what users do today, with quotes>
### Desired outcomes (in users' words)
- "<quote>" — <user, source, date>
### Anxieties
- <what users worry about>
## Themes
### Theme 1: <one-sentence articulation>
**Evidence:** N sources, primarily <behavioral | opinion>
**Quotes:**
> "<quote>" — <source, date>
> "<quote>" — <source, date>
**What it suggests (descriptive, not prescriptive):** <1-2 sentences>
### Theme 2: ...
## Contradictions and segments
<Where users split, and what segment or usage pattern the split appears to track.>
## Opportunities (unmet needs, not solutions)
### 1. <opportunity name>
<2-3 sentences: the unmet need, the user it affects, evidence strength.>
### 2. ...
## Research gaps and proposed next steps
- **<gap>** — next step: <concrete research action>
- ...
## What this research does NOT tell us
<Explicit. Prevents over-application.>
## Sources
<Full list with dates. Internal sources as Notion/Slack/Fathom links, external as URLs.>
/role-pm:spec-draft/role-pm:interview-synthesis instead — it's tighter./role-pm:market-research./role-pm:product-lens — this skill is for understanding users, not validating solutions.