agentsclimarketplace
Sign in

Customer interview analyzer

Skill sisodiabhumca/agent-skills/skills/customer-interview-analyzer

Use when a PM or UX researcher has interview transcripts (text/Notion/Drive) and needs themes, pain points, JTBD, and verbatim quotes synthesized into a research report.From its SKILL.md

Install
npx -y skills add sisodiabhumca/agent-skills --skill customer-interview-analyzer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.6 KB, 325 tokens by cl100k_base, as published. Nobody here has run it

Customer Interview Analyzer

When to invoke

  • "Synthesize these 12 user interviews."
  • "What are the top pain points across last quarter's research?"
  • "Pull JTBD statements from these transcripts."

Inputs needed

  1. Transcripts — folder of .txt/.md/.vtt files, or Notion/Drive docs.
  2. Research question (optional) — focuses the analysis.
  3. Persona / segment tags (optional).

Workflow

  1. Ingest — load all transcripts; clean speaker labels.
  2. Code — extract candidate themes by frequency + co-occurrence.
  3. Cluster — group similar codes into themes; tag each with a verbatim quote.
  4. Report — produce: research question, methodology, themes (with frequency), JTBD statements, surprises, recommendations.

Output format

## Research question
## Methodology (n, recruit, dates)
## Themes (ranked)
  Theme — # mentions — verbatim — implication
## JTBD statements
## Surprises / disconfirmations
## Recommendations

Guardrails

  • Always cite a verbatim quote with source file + line for every theme.
  • Distinguish observations (what users said/did) from interpretations.
  • Surface contradictions across interviews.

Reference code

analyze.py does keyword + n-gram extraction with simple clustering. Optional --llm flag uses any chat-completions API for richer themes (provide endpoint + key via env vars).

What ships with it: 2 files

6.6 KB alongside SKILL.md, 1 of them executable

Keep looking

Skills are one crate of 326,679. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.