interview
Topic: $0
If topic is a file path, read it first. Otherwise, use topic as context.
Before asking the user anything, explore the codebase for answers yourself. Only ask what code can't tell you.
Interview the user relentlessly using AskUserQuestion or request_user_input tool. Walk each branch of the topic systematically — resolve dependencies between decisions before moving to dependent questions.
For each question:
- Provide your recommended answer based on codebase exploration and context
- Let the user confirm, adjust, or reject
Adapt questions to topic type:
Codebase exploration: Architecture decisions, patterns used, why certain approaches Issue investigation: Symptoms, reproduction steps, what changed, when started New feature: Requirements, constraints, affected systems, acceptance criteria Plan/spec review: Implementation details, UI/UX, tradeoffs, edge cases, dependencies
Guidelines:
- Ask non-obvious questions only — don't ask what you can find in code
- One question at a time, with your recommended answer
- Go deep on answers before moving to the next branch
- Challenge assumptions and vague answers — push for specifics
- Uncover hidden complexity and dependencies between decisions
After each answer, either:
- Ask a deeper follow-up or move to the next branch
- If all branches exhausted, summarize findings and ask what to do with them (write spec, create tasks, document, etc.)
Continue until user says "done" or all meaningful questions exhausted.
More from benjaming/ai-skills
confluence-cli
Use confluence-cli (NPM package) to manage Confluence content, pages, and spaces from the command line. Ideal for documentation workflows, bulk content operations, page migration, and when users request CLI-based Confluence interactions. Trigger on requests like "use Confluence CLI", "create Confluence pages via CLI", "migrate Confluence content", "automate documentation workflows", or when users want to script Confluence operations.
43atlassian-cli-jira
Use Atlassian CLI (acli) to manage Jira work items, projects, and workflows from the command line. Ideal for bulk operations, automation, scripting, and when users request CLI-based Jira interactions. Trigger on requests like "use Jira CLI", "create Jira issues via CLI", "bulk update Jira tickets", "automate Jira workflows", or when users want to script Jira operations.
29ralph-loop
Create autonomous iterative loops (Ralph Wiggum pattern) for multi-step tasks. Use when setting up automated workflows that iterate over a backlog of tasks with clear acceptance criteria. Triggers on requests like "create a ralph loop", "set up an iterative agent", "automate this migration", or "create an autonomous loop".
21codex-cli
Use OpenAI Codex CLI in non-interactive mode for automated code analysis, review, and programmatic task execution. Trigger on requests like "use Codex to analyze", "run codex exec", "codex code review", or when users want AI-powered code analysis without interactive prompts. Ideal for automation workflows, code quality checks, and generating structured analysis reports.
19daily-standup
Daily standup assistant for Benjamin that compiles work priorities from Jira and Slack into a single prioritized task list. This skill should be used when Benjamin asks for morning standup, daily priorities, what to work on today, or needs to compile work items.
18ui-skills
Opinionated constraints for building better interfaces with agents.
16