interview-me

Stress-test plans through round-by-round interviews that lock every open decision branch.

3|Updated Apr 11, 2026
One-click install
npx skills add https://github.com/bravros/bravros --skill interview-me-bravros
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: interview-me
Source: https://github.com/bravros/bravros/tree/main/plugins/sdlc/skills/interview-me
Command: npx skills add https://github.com/bravros/bravros --skill interview-me-bravros

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Plans and designs often look complete while hiding unresolved decisions several layers deep, leading to wrong assumptions baked into implementation. This Skill closes the gap between "the agent thinks it understands" and "the agent actually understands" by systematically interviewing the user until every decision branch is locked. ## Core Features & Use Cases - Design tree mapping: Converts a plan or conversation into a tree of unresolved decisions and works the current frontier round by round, batching up to 4 independent questions per ask. - Recommendation-driven questions: Every question ships with a recommended option marked first, so the user can confirm quickly instead of deciding from scratch. - Fact resolution before asking: Structural code questions are resolved silently via graphify queries and direct file reads, so only genuine intent and preference questions reach the user. - Incremental decision capture: Locked decisions are recorded after each round into .planning/decisions/ or a plan folder's decisions.md, so a crashed session loses at most one round. - Use Case: After drafting an implementation plan with /recon, run this Skill to surface hidden choices (naming, error handling, data shape), lock each one with a rationale, and update the plan before writing any code. ## Quick Start Ask the agent to interview you about the current plan, for example: "Interview me on this plan and lock down every open decision before we start coding."

Frequently Asked Questions about interview-me

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

FAQPage Schema
How do I stress-test an implementation plan before coding?▼

Run an interview session that maps the plan into a design tree of unresolved decisions, then asks the current frontier of independent questions round by round. Each answer recomputes the frontier until no open branches remain, and locked decisions are written to a decisions file.

How does the interview decide which questions to ask the user?▼

Questions are classified first: intent and preference questions go to the user, while factual questions about how the code behaves are resolved silently using graphify queries and direct file reads. Only genuine decisions ever reach the ask_question prompt.

Can I use this without an existing plan file?▼

Yes, standalone mode works against whatever is in the conversation. The same design-tree and frontier logic applies, and at close the locked decisions are written to a topic file under .planning/decisions/.

What happens to decisions if the interview session crashes?▼

Decisions are captured incrementally as each round closes rather than batched at the end, so a crashed session loses at most one round of answers. Locked decisions live in decisions.md inside the plan folder or a dated decisions file.

When should I not use a round-by-round interview for a plan?▼

Skip it when the plan is small, fully specified, or the decisions are purely mechanical with obvious answers. The interview adds the most value for plans with layered, interdependent choices where silent assumptions would be costly.