plugins/faos-pm/skills/summarize-interview/SKILL.md
<!-- AUTO-GENERATED by export-plugins.py — DO NOT EDIT --> --- name: summarize-interview description: Transform customer interview transcripts or notes into structured summaries with JTBD insights, pain points, and action items. Use when processing interview data after customer discovery sessions. tags: [discovery, customer-research, interviews, synthesis] --- # Summarize Interview Transform raw interview transcripts or notes into structured, actionable summaries that feed directly into Opport
npx skillsauth add frank-luongt/faos-skills-marketplace plugins/faos-pm/skills/summarize-interviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Transform raw interview transcripts or notes into structured, actionable summaries that feed directly into Opportunity Solution Trees, PRDs, and product decisions.
Interview transcripts are long, unstructured, and hard to compare across participants. This skill extracts the signal — jobs, pains, outcomes, and surprises — into a consistent format that enables pattern recognition across interviews.
Provide one of:
For each interview, produce this structured summary:
# Interview Summary
## Metadata
| Field | Value |
| --- | --- |
| Date | [interview date] |
| Participant | [name or ID] |
| Role / Title | [their role] |
| Company / Context | [company, size, industry] |
| Interviewer | [your name] |
| Duration | [minutes] |
---
## Current Situation
**What they do today:**
[1–3 sentences describing how they currently handle the relevant activity]
**Tools / processes used:**
- [tool or process 1]
- [tool or process 2]
**How long they've done it this way:** [duration]
---
## Jobs to Be Done
For each job identified:
| Job | Importance (1–10) | Current Satisfaction (1–10) | Opportunity Score |
| --- | --- | --- | --- |
| [Job description — what they're trying to accomplish] | [rating] | [rating] | [Importance × (1 − Satisfaction/10)] |
---
## Pain Points
| Pain Point | Severity | Frequency | Current Workaround |
| --- | --- | --- | --- |
| [pain description] | High / Medium / Low | Daily / Weekly / Occasionally | [how they cope] |
---
## Desired Outcomes
- [What "success" looks like in their words]
- [Measurable outcome they care about]
---
## What They Like About Current Solution
- [positive aspect] — why it matters to them
- [positive aspect] — why it matters to them
---
## Willingness to Change / Pay
- **Have they searched for alternatives?** [Yes/No — details]
- **Have they spent money on this?** [Yes/No — how much, on what]
- **Priority vs. other problems:** [High / Medium / Low]
- **Switching cost concern:** [what would make switching hard]
---
## Key Insights
- [unexpected finding 1]
- [unexpected finding 2]
---
## Notable Quotes
> "[exact verbatim quote — the most revealing thing they said]"
> "[another important quote]"
---
## Action Items
| Action | Owner | Due |
| --- | --- | --- |
| [follow-up action from this interview] | [who] | [when] |
When processing 3+ interviews, also produce a synthesis table:
## Cross-Interview Patterns (N=[number] interviews)
### Recurring Jobs
| Job | Mentioned By | Avg Importance | Avg Satisfaction | Opportunity Score |
| --- | --- | --- | --- | --- |
| [job] | P1, P3, P5 | 8.3 | 3.2 | 5.6 |
### Recurring Pain Points
| Pain Point | Mentioned By | Severity Consensus |
| --- | --- | --- |
| [pain] | P1, P2, P4, P5 | High |
### Emerging Themes
1. [theme] — supported by [N] participants
2. [theme] — supported by [N] participants
### Contradictions / Segments
- [Group A thinks X, Group B thinks Y — possible segmentation signal]
### Recommended Next Steps
1. [action based on patterns]
2. [action based on patterns]
| Avoid | Why | Instead | | --- | --- | --- | | Editorializing quotes | Loses the participant's voice | Use exact words, even if imperfect | | Confirmation bias in synthesis | Only highlighting data that supports your hypothesis | Include disconfirming evidence prominently | | Skipping "Willingness to Pay" | Leads to building things nobody will buy | Always assess priority and switching signals | | Combining interviews too early | Loses individual nuance | Summarize each individually first, then synthesize | | Ignoring what they like | Understanding satisfaction prevents breaking what works | Always capture positives alongside pains |
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: grpo-rl-training description: GRPO reinforcement learning training with TRL. Use when applying Group Relative Policy Optimization for reasoning and task-specific model training. --- # GRPO/RL Training with TRL Expert-level guidance for implementing Group Relative Policy Optimization (GRPO) using the Transformer Reinforcement Learning (TRL) library. This skill provides battle-tested patterns, critical insights, and production-r
tools
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: graphql-architect description: Master modern GraphQL with federation, performance optimization, --- ## Use this skill when - Working on graphql architect tasks or workflows - Needing guidance, best practices, or checklists for graphql architect ## Do not use this skill when - The task is unrelated to graphql architect - You need a different domain or tool outside this scope ## Instructions - Clarify goals, constraints, and
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: grafana-dashboards description: Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces. --- # Grafana Dashboards Create and manage production-ready Grafana dashboards for comprehensive system observability. ## Do not use this skill when - The task is unrelated
development
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT --> --- name: gptq description: GPTQ post-training quantization for generative models. Use when quantizing large models to 4-bit with calibration-based weight compression. --- # GPTQ (Generative Pre-trained Transformer Quantization) Post-training quantization method that compresses LLMs to 4-bit with minimal accuracy loss using group-wise quantization. ## When to use GPTQ **Use GPTQ when:** - Need to fit large models (70B+) on limited GPU