Skip to content
SkillModel-led376 tokens in use

summarize-interview

Turn a customer interview transcript into a fixed-format summary with jobs to be done, satisfaction signals and action items.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-product-discovery/skills/summarize-interview
claude plugin install pm-product-discovery@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing summarize-interview costs

46tokens idle
376tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure23/25
  • Examples6/15
  • Output5/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

This skill reads a full interview transcript, supplied as an attached file or pasted text, and fills a fixed summary template: date, participants, background, current solution, what they like, problems, key insights and action items.

Likes and problems are written as a job to be done, a desired outcome, its importance and a satisfaction level. The language is kept simple so anyone can read the summary, and the result is saved as a markdown document.

What You Get

  • A structured summary with a fixed set of fields
  • Jobs to be done with desired outcome, importance and satisfaction for likes and problems
  • Notable quotes and unexpected findings under key insights
  • Action items with date and owner, saved as a markdown file

Common Use Cases

  • Processing a batch of discovery interview recordings
  • Creating comparable summaries across many interviews
  • Handing interview findings to teammates who did not attend

What Makes It Unique

Every summary uses the same template, so interviews can be compared side by side. It captures satisfaction next to each job to be done, which feeds opportunity ranking. It pairs with the interview-script skill that prepares the conversation.

Under The Hood

The skill is a prompt only, with no scripts. It tells the agent to read the transcript file the user attaches or pastes and to save the summary as a markdown document in the user’s workspace, so it writes a file. It makes no web or API calls and runs no commands.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers