Interview Question Design Coach

Interview Question Design Coach is a skill for Claude Code from BrennanJCollins/UnabatedPM-coaching. It costs 49 tokens per session (3,596 once invoked), scanned A, original, MIT.

A coaching guide for writing customer interview questions that uncover real problems and business conditions. It checks whether questions focus on past behaviour, economics, buyers, users, and problems instead of imagined product interest.

In plain words
What is it for?
Use it to design or review interview guides, research plans, and customer questions, or to assess whether questions are behavioural, open-ended, and economically useful.
Why use it?
It helps avoid leading questions that make people agree with a product idea without proving they need it. It also highlights questions that do not reveal purchasing authority, budgets, or business impact.

Skill for Claude Code

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

Part of the unabatedpm-influence plugin — 8 skills, 1 command shipped together

Good fit Use it to design or review interview guides, research plans, and customer questions, or to assess whether questions are behavioural, open-ended, and economically useful.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brennanjcollins/unabatedpm-coaching/interview-question-design
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 BrennanJCollins/UnabatedPM-coaching --skill interview-question-design
Clone the repo
git clone --depth 1 https://github.com/BrennanJCollins/UnabatedPM-coaching

Made for: Claude Code.

Or install unabatedpm-influence, the plugin that ships this one along with the rest of its 8 skills, 1 command.

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 Interview Question Design Coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/interview-question-design/github.svg)](https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/interview-question-design)
Your own site
<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/interview-question-design"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/interview-question-design/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 Interview Question Design Coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/interview-question-design"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/interview-question-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,596 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.
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 $0.00049 $0.03596
Opus 5 $0.00024 $0.01798
Sonnet 5 $0.00010 $0.00719
Haiku 4.5 $0.00005 $0.00360

Measured 11d ago against content hash 79fd5048cff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Interview Question Design Coach 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 11d 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.

unabatedpm-influence/skills/interview-question-design/SKILL.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operating Modes

This skill operates in two modes:

Conversation mode (default): Coach the PM through interview question design interactively. Triggered by direct invocation or natural conversation.

Evaluate mode: Read a research document silently, score its interview questions, and return structured findings. No conversation, no questions — just assessment. Triggered by the /audit orchestrator.

Evaluate Mode Instructions

When invoked in evaluate mode, you receive a research document, interview guide, or customer research plan. Do NOT coach. Do NOT ask questions. Read and score.

Score each dimension 1-5:

  • 1 = Not present or fundamentally broken
  • 2 = Attempted but significant gaps
  • 3 = Competent but missing key elements
  • 4 = Strong with minor improvements possible
  • 5 = Exemplary — reveals actual behavior and economics

Dimensions to evaluate:

  1. Market & customer intelligence — Are questions behavioral ("Tell me about the last time...") or hypothetical ("Would you use...")? Do they probe for economics (willingness to pay, budget authority)? Do they distinguish buyer from user? Are questions open-ended about problems, not product validation? Does the guide follow the Before/During/After structure?

  2. User behavior & satisfaction insights — Do questions quantify pain ("What % of your week...") instead of just asking about importance? Do they uncover current workarounds? Do they reveal the economic impact to the buyer (not just the user)? Are questions designed to surface real behavior, not desired behavior?

Red flags to check:

  • Leading questions ("Wouldn't it be better if...?")
  • Product-focused questions ("What do you think of our feature?")
  • Hypothetical scenarios ("Would you use a tool that...")
  • No economic discovery or willingness-to-pay questions
  • Summarizing what people SAID they want instead of interpreting patterns
  • Questions about the user but not the buyer/decision-maker
  • No quantification of pain points
  • Missing Before/During/After structure
  • Questions that validate the product idea instead of exploring the problem

Read the full file on GitHub · 352 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. 11d ago First seen · 352 lines · 49 tokens per session scan A 79fd5048cff9

Subscribe to this mod's changes

Interview Question Design Coach is a skill published in the GitHub repository BrennanJCollins/UnabatedPM-coaching (4 stars, last pushed 20d ago), licensed MIT. It adds 49 tokens to every session and 3,596 once invoked, about $0.0002 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 2026-08-31.