interviewer

Interviews users in structured question rounds to surface hidden assumptions and settle design decisions.

Updated Sep 13, 2026
One-click install
npx skills add https://github.com/petemcw/farseer --skill interviewer-petemcw
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: interviewer
Source: https://github.com/petemcw/farseer/tree/main/skills/interviewer
Command: npx skills add https://github.com/petemcw/farseer --skill interviewer-petemcw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans, decisions, and ideas often contain hidden assumptions, unexamined risks, and edge cases that only surface after costly implementation. This Skill stress-tests your thinking by interviewing you relentlessly until every decision branch is explored and a shared understanding is reached. ## Core Features & Use Cases - Design Tree Mapping: Models your plan as a decision tree where each settled decision unlocks the questions that depend on it. - Frontier Rounds: Asks every currently answerable question in numbered rounds with recommended answers, using the AskUserQuestion tool for one-click responses. - Fact-Finding Sub-Agents: Dispatches sub-agents to look up environmental facts itself instead of burdening you with research questions. - Use Case: Before starting a new feature, say "interview me about my authentication plan" and the Skill will question scope, edge cases, and trade-offs round by round until nothing is left silently assumed. ## Quick Start Ask the AI to interview you about a plan, decision, or idea you want to stress-test before acting on it.

Frequently Asked Questions about interviewer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stress-test a plan or idea with AI?▼

Ask the AI to interview you about your plan using trigger phrases like "interview me". The Skill questions you in structured rounds, mapping decisions as a tree and probing assumptions, risks, and edge cases until a shared understanding is reached.

How does the interviewer skill structure its questions?▼

It works in frontier rounds, asking every question whose prerequisites are already settled. Each round contains up to four numbered questions with recommended answers, delivered through the AskUserQuestion tool for one-click responses.

Can the interviewer look up facts instead of asking me?▼

Yes. When a question requires facts from the environment such as filesystem or tool data, it dispatches a sub-agent to find the answer rather than asking you. Only genuine decisions are put to the user.

When does an interview session end?▼

The session ends when the frontier is empty, meaning every branch of the design tree has been visited and nothing remains silently assumed. The Skill then produces a summary of the discussion and all settled decisions.

What are the limitations of interview-based plan validation?▼

The Skill validates thinking through dialogue, so it depends on the quality of your answers and cannot verify real-world feasibility. It does not act on the conclusions until you explicitly confirm shared understanding.