Skip to content
Back to skills

Interview Me

ASecurity

Stress-test a plan or design via a round-by-round interview — ask the whole frontier of independent questions each round until every branch of the decision tree is locked. Use on `/interview-me`, "interview me", or when the user signals doubt about a plan.

  • 3 stars
  • 0 votes
  • 0 copies
  • 26 views
  • Added September 5, 2026
ai-agents

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned September 5, 2026

npx -y skills add bravros/bravros --skill interview-me --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Interview Me?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Interview Me
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bravros-interview-me/badge)](https://www.skillsdirectory.com/skills/bravros-interview-me)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: interview-me
description: Stress-test a plan or design via a round-by-round interview — ask the whole frontier of independent questions each round until every branch of the decision tree is locked. Use on `/interview-me`, "interview me", or when the user signals doubt about a plan.
---

# Interview Me

Read [briefing.md](references/briefing.md) on demand for detailed context and instructions.

Stress-test plans or designs by mapping unresolved choices into a **design tree** and interviewing the user round-by-round over the decision **frontier**.

## Critical Rules

1. **Ask by rounds (max 4 per `ask_question`)**: Only batch independent questions on the current frontier.
2. **Always include a recommendation**: Place recommended option first, append `(Recommended)`, and explain why in 1 sentence.
3. **Recompute frontier every round**: Do not use a static question list; answers alter downstream branches.
4. **No round limit**: Continue until the decision frontier is completely empty or user says stop.
5. **Facts are your job, decisions are theirs**: Resolve structural code questions silently via graphify/code before asking.

## Core Workflow

1. **Map Tree**: Identify unresolved branches in the plan/conversation.
2. **Preview**: Show short bulleted list of open branches to the user.
3. **Interview Loop**:
   - Check code/graphify first for factual questions.
   - Present decision frontier via `ask_question` (with recommendations).
   - Recompute frontier after responses.
   - Record locked decisions incrementally in `.planning/decisions/` or `decisions.md`.
4. **Finalize**: Update plan file or decision log upon complete frontier exhaustion and user confirmation.

Files in this skill

  • SKILL.md1.7 KB
  • references/briefing.md8.8 KB
  • skill.yaml10 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.