agent research skill risk: low
Customer Interview JTBD Summary Generator
Transforms an interview transcript into a structured summary using a template covering date, participants, background, current solution, likes, problems, key insights, and action i…
- External action: low
SKILL 1 file
SKILL.md
--- name: summarize-interview description: "Summarize a customer interview transcript into a structured template with JTBD, satisfaction signals, and action items. Use when processing interview recordings or transcripts, synthesizing discovery interviews, or creating interview summaries." --- ## Summarize Customer Interview Transform an interview transcript into a structured summary focused on Jobs to Be Done, satisfaction, and action items. ### Context You are summarizing a customer interview for the product discovery of **$ARGUMENTS**. The user will provide an interview transcript — either as an attached file (text, PDF, audio transcription) or pasted directly. Read any attached files first. ### Instructions 1. **Read the full transcript** carefully before summarizing. 2. **Fill in the summary template** below. Use "-" if information is unavailable. Replace numeric values with qualitative descriptions if needed (e.g., "not satisfied"). 3. **Use clear, simple language** — a primary school graduate should be able to understand the summary. ### Output Template ``` **Date**: [Date and time of the interview] **Participants**: [Full names and roles] **Background**: [Background information about the customer] **Current Solution**: [What solution they currently use] **What They Like About Current Solution**: - [Job to be done, desired outcome, importance, and satisfaction level] **Problems With Current Solution**: - [Job to be done, desired outcome, importance, and satisfaction level] **Key Insights**: - [Unexpected findings or notable quotes] **Action Items**: - [Date, Owner, Action — e.g., "2025-01-15, Paweł Huryn, Follow up with customer about pricing"] ``` Save the summary as a markdown document in the user's workspace. --- ### Further Reading - [User Interviews: The Ultimate Guide to Research Interviews](https://www.productcompass.pm/p/interviewing-customers-the-ultimate) - [Continuous Product Discovery Masterclass (CPDM)](https://www.productcompass.pm/p/cpdm) (video course)
INPUTS
- $ARGUMENTS REQUIRED
product discovery topic for context
REQUIRED CONTEXT
- interview transcript
OPTIONAL CONTEXT
- product discovery topic
ROLES & RULES
Role assignments
- You are summarizing a customer interview for the product discovery of **$ARGUMENTS**.
- Read the full transcript carefully before summarizing.
- Read any attached files first.
- Fill in the summary template below. Use "-" if information is unavailable.
- Replace numeric values with qualitative descriptions if needed (e.g., "not satisfied").
- Use clear, simple language — a primary school graduate should be able to understand the summary.
EXPECTED OUTPUT
- Format
- markdown
- Schema
- markdown_template · Date, Participants, Background, Current Solution, What They Like About Current Solution, Problems With Current Solution, Key Insights, Action Items
- Constraints
- fill the exact output template provided
- use '-' if information is unavailable
- use clear simple language understandable by a primary school graduate
- save as a markdown document
SUCCESS CRITERIA
- Transform an interview transcript into a structured summary focused on Jobs to Be Done, satisfaction, and action items.
- Fill in the summary template completely.
- Use clear, simple language.
CAVEATS
- Dependencies
- Requires interview transcript (attached file or pasted text).
- Missing context
- Example of a completed output template
- File naming convention for the saved markdown document
- How to handle transcripts with multiple speakers or very long content
- Ambiguities
- Does not specify exact format or structure for embedding 'Job to be done, desired outcome, importance, and satisfaction level' inside bullet points.
- $ARGUMENTS placeholder is referenced but not defined or exemplified in the prompt.
QUALITY
- OVERALL
- 0.77
- CLARITY
- 0.82
- SPECIFICITY
- 0.68
- REUSABILITY
- 0.88
- COMPLETENESS
- 0.72
IMPROVEMENT SUGGESTIONS
- Add a filled example of the output template showing how to populate the JTBD-style bullets.
- Replace $ARGUMENTS with a clearer instruction such as 'the product or feature under discovery'.
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- Creative Thinking Frameworks for CS Researchagentresearch
- Academic Paper Figure Generatoragentresearch
- Deep Investigation Agent for Geopolitics Researchagentresearch
- Customer Research Analyst and Synthesizeragentresearch
- Gemini Research Paper Literature Searchagentresearch
- Research Formula Derivation Package Builderagentresearch
- Research Session Provenance Recorderagentresearch
- BIDS Neuroscience Data Organizeragentresearch
- Research Experiment Plan Roadmap Builderagentresearch
- ARA Research Artifact Compileragentresearch
- Research Proposal Experiment Roadmap Generatoragentresearch
- ML AI Theorem Proof Package Writeragentresearch
- Research Formula Derivation Package Builderagentresearch
- Scientific ML Catalog Assistantagentresearch
- OpenMM MDAnalysis Molecular Dynamics Workflowagentresearch
- Publication-Quality Paper Figure Generatoragentresearch
- ML Research Idea Generator and Rankeragentresearch
- ML Paper Figure and Table Generatoragentresearch
- Competitor Profiling Intelligence Analystagentresearch
- Research Method Novelty Checkeragentresearch
- Research Refine and Experiment Planning Pipelineagentresearch
- ML Ablation Study Planneragentresearch
- Research Agent Validation Best Practicesagentresearch
- AlphaXiv arXiv Paper Lookup Workflowagentresearch
- AlphaXiv Single-Paper Lookup and Summarizeragentresearch