interview-framework

Automates interview preparation with intent-based depth scaling and a 3-phase algorithm.

2|Updated Jul 13, 2025

Search Tags:#user validation #intent capture #interview preparation #interview framework #question flow

Ready to run

npx skills add https://github.com/krzemienski/shannon --skill interview-framework-krzemienski

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: interview-framework
Source: https://github.com/krzemienski/shannon/tree/main/skills/interview-framework
Command: npx skills add https://github.com/krzemienski/shannon --skill interview-framework-krzemienski

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

The interview-framework skill unit simplifies and optimizes the interview preparation and question flow process, ensuring in-depth understanding and accurate validation of user intent.

Core Features & Use Cases

Adaptive Depth Scaling: Dynamically adjusts question depth based on user intent, allowing for varied complexity.
3-Phase Algorithm: Follows a structured UNDERSTAND, PROPOSE APPROACHES, and CONFIRM & STORE process to comprehensively cover user requirements.
Completion Signal Detection: Detects early completion signals for efficient conversation management.
Context Accumulator Pattern: Persists interview outcomes to a file for continuous improvement.

Quick Start

To use the interview-framework, activate it in your project by running /shannon:enforce on.

Frequently Asked Questions about interview-framework

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

FAQPage Schema

How do I structure interview preparation and question flow for user validation?▼

Interview preparation is structured using a 3-phase algorithm: Understand, Propose Approaches, and Confirm & Store, which systematically captures user intent and validates requirements through adaptive question flow.

What is intent-based depth scaling for intake interviews?▼

Intent-based depth scaling dynamically adjusts interview question complexity based on captured user intent, allowing varied depth during the understanding phase to efficiently match the interview's scope to the user's actual requirements.

How do I capture and persist interview outcomes to a file in Claude Code?▼

Interview outcomes are captured and persisted using a context accumulator pattern that stores confirmed results to a file, enabling continuous improvement and preserving data across research, planning, and design phases.

Can I automate approach synthesis after completing user intent capture?▼

Yes, approach synthesis is automated during the Propose Approaches phase, which processes the captured intent from the initial understanding phase to generate and present validated approaches for user confirmation.

Does the interview framework handle early conversation completion signals?▼

The framework includes completion signal detection to manage conversation efficiency, identifying when a user has provided sufficient information to conclude the interview phase without asking redundant or unnecessary follow-up questions.

What is the best way to prepare questions for product research and planning interviews?▼

The best way to prepare interview questions for product research is using an adaptive 3-phase framework that scales question depth by intent, detects completion signals, and stores outcomes for continuous validation improvement.