Skip to content

deanpeters/Product-Manager-Skills / skills/voice-of-customer-miner

voice-of-customer-miner

Verified

Mine public reviews, app stores, and forums for unmet needs, competitor weaknesses, and switching triggers — with quoted evidence. Use when you want customer voice without waiting on interviews.

FileKindSize
SKILL.mdskill md9.7 KB
examples/sample-industrial.mdmarkdown6.0 KB
examples/sample.mdmarkdown5.8 KB
template.mdmarkdown2.3 KB

template.md

View on GitHub
# Voice-of-Customer Snapshot Template

Copy this to record a public-voice mining run. **Verbatims are the product** — short, real, quoted
customer language with URLs. If it has quote marks, it must be a real excerpt at a real URL; never
fabricate quotes, ratings, review counts, or reviewer roles. Theme by **need, not feature**
("I can't get my data where my team works," not "exports are broken"), and remember every theme is
a hypothesis to validate in real interviews, never a verdict.

## Template

```markdown
# Voice-of-Customer Snapshot

## 1. Scope
**Products mined:** [yours, a rival's, or a set]
**Decision supported:** [what this informs]
**Sources swept:** [review sites, app stores, forums — with the bias note each carries]
**As-of date:** [YYYY-MM-DD]

## 2. Need Themes
_Top 3-5 themes. The theme name is solution-free — it names the need, so discovery can explore
solutions the reviews never imagined._

### Theme: [Underlying need, solution-free, 4 to 8 words]
- **Frequency:** [recurring across sources / concentrated in one thread / isolated but vivid — honesty here is the discipline]
- **Verbatim:** "[short real quote]" — [source, URL]
- **Verbatim:** "[short real quote]" — [source, URL]
- **Who says it:** [role/segment, if evident — labeled]
- **Reading:** [Inference — what this suggests]

## 3. Competitor Weak Points
- **[Competitor]:** [weakness in customers' words; frequency; URL]
- [Max 5, strongest evidence only]

## 4. Switching Triggers
- [What pushes customers off a product; what pulls them; labeled, cited]

## 5. So What?
- **Opportunity hypotheses:** [exactly 3 — phrased as problems, not features]
- **Battle-card-ready weaknesses:** [exactly 2 — with evidence quality noted]
- **Assumptions to validate in real interviews:** [exactly 3 — this section is the bridge to discovery]
```

## Quality checks before you call it done

- Every quoted string is a real excerpt with a real URL — paraphrases don't get quote marks
- Every theme name survives the feature test: no product component named, only the need
- Frequency labels are honest — one articulate ranter is "isolated," not a theme
- Each source carries its bias note (reviewers skew negative; vendor communities skew loyal; app stores over-represent update anger)
- The validation handoff is populated — themes ship to interviews, not straight to the roadmap
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 323kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 323kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 323kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 323kUpdated Claude CodeCodexVerifiedInstall