synthesize-interviews

synthesize-interviews is a skill for Claude Code from mshadmanrahman/pm-pilot. It costs 67 tokens per session (1,480 once invoked), scanned A, original, MIT.

A user-research tool that turns interview transcripts, notes, or feedback into common themes, user problems, and recommendations. It can also create a separate document containing only the problems, without proposed solutions.

In plain words
What is it for?
Use it to analyze customer interviews, research notes, feedback dumps, and findings from several user conversations.
Why use it?
It helps you see patterns across conversations instead of reviewing each interview separately. The findings remain connected to the original interview material when structured snapshots are available.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pm-core plugin — 14 skills, 2 agents shipped together

Good fit Use it to analyze customer interviews, research notes, feedback dumps, and findings from several user conversations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mshadmanrahman/pm-pilot/synthesize-interviews
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mshadmanrahman/pm-pilot --skill synthesize-interviews
Clone the repo
git clone --depth 1 https://github.com/mshadmanrahman/pm-pilot

Made for: Claude Code.

Or install pm-core, the plugin that ships this one along with the rest of its 14 skills, 2 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for synthesize-interviews

README.md
[![agentmods](https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/synthesize-interviews/github.svg)](https://agentmods.dev/skills/mshadmanrahman/pm-pilot/synthesize-interviews)
Your own site
<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/synthesize-interviews"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/synthesize-interviews/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for synthesize-interviews

Your own site · 80×15
<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/synthesize-interviews"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/synthesize-interviews.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.01480
Opus 5 $0.00034 $0.00740
Sonnet 5 $0.00013 $0.00296
Haiku 4.5 $0.00007 $0.00148

Measured 10d ago against content hash d62f07615f74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

synthesize-interviews scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/pm-core/skills/synthesize-interviews/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesize Interviews: User Research Synthesis

Turn raw interview transcripts, notes, or feedback dumps into structured insights. Produces two outputs: a synthesis report (themes + recommendations) and a standalone pain points document (problems only, no solutions).

When to Activate

  • User says "synthesize interviews", "what did users say about X"
  • User provides interview transcripts or notes to analyze
  • User says "analyze this feedback", "research findings"
  • After 3+ customer conversations (suggest proactively)

Input Modes

Accept input three ways:

  1. Pasted content: Raw transcript or notes directly in conversation
  2. File path: Point to a file or directory of transcripts
  3. Workspace reference: "Look at the interview notes in /research"

If input is a single interview, produce per-interview notes. If 3+ interviews, produce a cross-interview synthesis.

Preferred input: interview snapshots

For multi-interview work, the best input is one Interview Snapshot per interview, produced by /pm-discovery:interview-snapshot and tagged synthesis_status: single-interview-complete. Reading structured snapshots instead of raw transcripts is what keeps quotes traceable at synthesis time.

If the user hands over raw transcripts for 3+ interviews, say so once and offer the snapshot pass first:

"I can synthesize these directly, but collapsing per-interview reading into cross-interview synthesis is where quote accuracy degrades. Want me to run /pm-discovery:interview-snapshot on each one first? It takes one pass per interview and every quote comes back verified."

Proceed with raw transcripts if they decline. Do not block.

Hallucination guard (required)

Teresa Torres documented roughly a 30% quote hallucination rate when AI synthesizes interviews. Before delivering any synthesis that contains direct quotes:

  1. For every direct quote in the output, search the source transcript or snapshot for at least 60% of its words (exact match, case-insensitive).
  2. If the match fails, flag the quote inline with [UNVERIFIED - edit before citing] and keep going.
  3. Never silently repair a quote you cannot match. Mark it and move on.
  4. State the verified count in the output footer, for example 12/13 quotes verified against source.

Read the full file on GitHub · 166 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 166 lines · 67 tokens per session scan A d62f07615f74

Subscribe to this mod's changes

synthesize-interviews is a skill published in the GitHub repository mshadmanrahman/pm-pilot (20 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 1,480 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories