Interactive PM interview with expertise-adaptive questioning for requirements elicitation
Scanned 5/29/2026
Install to Claude Code
Skills Directorynpx -y skills add a5c-ai/babysitter --skill requirements-interview --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Requirements Interview?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/a5c-ai-requirements-interview)More formats (shields.io, HTML) on the badges page.
---
name: requirements-interview
description: Interactive PM interview with expertise-adaptive questioning for requirements elicitation
allowed-tools: [Read, Write, Edit, Bash, Grep, Glob]
---
# Requirements Interview
## Capabilities
Conducts interactive requirements interviews adapted to the user's expertise level. Generates structured requirements specifications from conversation. Identifies user personas, feature lists, constraints, and acceptance criteria.
## Tool Use Instructions
- Use **Read** to examine existing spec files or project context
- Use **Grep/Glob** to find existing requirements or documentation
- Use **Write** to generate the requirements specification document
- Use **Bash** to check project structure for context
## Process Integration
- Used in `maestro-orchestrator.js` Phase 1 (PM Interview)
- Maps to tasks: `maestro-pm-interview`
- Agent: Product Manager (PM)
- Adapts interview depth: beginner (guided), intermediate (balanced), expert (concise)
- Outputs feed into `specification-generation` skill
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
