# Interview Framework

Should be used when a Ralph phase must identify critical user decisions, run a layered...

- Repository: https://github.com/tzachbon/smart-ralph (566 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-10-28
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add tzachbon/smart-ralph --skill interview-framework -g -a claude-code -y`
Codex: `npx skills add tzachbon/smart-ralph --skill interview-framework -g -a codex -y`
Cursor: `npx skills add tzachbon/smart-ralph --skill interview-framework -g -a cursor -y`
Gemini CLI: `npx skills add tzachbon/smart-ralph --skill interview-framework -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add tzachbon/smart-ralph`

## Description

This skill should be used when a Ralph phase must identify critical user decisions, run a layered grill, persist partial answers, obtain explicit approval, or resume an interrupted phase interview before delegating artifact work.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Interview Framework

Treat every normal-mode interview governed by this framework as a grill. Run the approval-gated interview for `start`, `triage`, `research`, `requirements`, `design`, and `tasks`. Treat this skill and its references as the single source of truth for interview behavior. Phase commands supply exploration territory and artifact context; they do not redefine the algorithm.

Quick mode bypasses interview questions only. It still requires current discovery, contract loading, bypass receipts, delegation checks, and artifact-agent load parity.

## Entry Contract

Before each new or resumed interview:

1. Complete the applicable skill discovery pass from `${CLAUDE_PLUGIN_ROOT}/references/normal-mode-gates.md`.
2. Reload this entire `SKILL.md`, `references/algorithm.md`, `references/domain-modeling.md`, every selected skill body, and every selected skill resource required for the current work. Load `references/examples.md` only when an example is needed.
3. Record the load manifest with `phase_gate.py record-skill-load`.
4. Begin or resume the interview with the matching phase, interview ID, discovery revision, and context digest.

Block when this skill or the core algorithm reference cannot be loaded. Warn and continue when a domain skill fails to load. Put unresolved material conflicts in the first critical frontier.

## Critical Decision Test

Grill only a decision that meets both conditions:

- The answer cannot be established by inspecting the project, prior artifacts, configuration, or selected skill contracts.
- Different answers would materially change scope, observable behavior, architecture, risk acceptance, delivery sequencing, or the acceptance standard.

The rest: https://github.com/tzachbon/smart-ralph/blob/HEAD/plugins/ralph-specum/skills/interview-framework/SKILL.md