requirements-interview
Interactive PM interview with expertise-adaptive questioning for requirements elicitation
npx skills add a5c-ai/babysitter --skill requirements-interview --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# 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
- Capabilities
- Tool Use Instructions
- Process Integration
What does the requirements-interview skill do?
Interactive PM interview with expertise-adaptive questioning for requirements elicitation
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill requirements-interview --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.