Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Interview Me

ASecurity

Conduct exhaustive, structured interviews with the user about any topic, business, product, plan, decision, design, process, strategy, personal context, or knowledge area. Use when the user wants to be interviewed, questioned, interrogated, grilled broadly, walked through a topic, or have their thinking/context extracted into a shared understanding. Always use the AskUserQuestion tool for each interview question.

41 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsgodocumentation

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add mike-coulbourn/claude-vibes --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 automatically with every re-scan.

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

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: interview-me
description: Conduct exhaustive, structured interviews with the user about any topic, business, product, plan, decision, design, process, strategy, personal context, or knowledge area. Use when the user wants to be interviewed, questioned, interrogated, grilled broadly, walked through a topic, or have their thinking/context extracted into a shared understanding. Always use the AskUserQuestion tool for each interview question.
---

# Interview Me

## Core Behavior

Interview the user relentlessly, one question at a time, until the topic is understood well enough to summarize, document, decide, plan, or create the requested follow-on artifact.

Use `AskUserQuestion` for every interview question. Do not ask interview questions as plain chat when `AskUserQuestion` is available.

If `AskUserQuestion` is unavailable, stop and say the skill requires that tool for the interview experience. Do not continue the interview with plain-text questions unless the user explicitly asks to proceed without the tool.

## Question Format

For each interview step:

- Ask exactly one question through `AskUserQuestion`.
- Use a short header, 12 characters or fewer.
- Provide 2-3 mutually exclusive answer options.
- Put the recommended option first and suffix its label with `(Recommended)`.
- Make the recommended option a real proposed answer, not a vague placeholder.
- Let the tool's free-form `Other` path handle nuance when the options do not fit.
- Keep the visible question concise, but include enough context for the user to answer quickly.

## Interview Method

Before asking, decide whether the answer can be discovered from available artifacts, repos, docs, previous messages, diagnostics, or uploaded files. If it can, inspect the source instead of asking the user.

Walk the decision tree branch by branch:

1. Establish the root definition of the topic.
2. Identify the purpose of the interview and the desired end artifact or decision.
3. Capture the audience, stakeholders, users, or affected parties.
4. Surface the user's goals, constraints, preferences, and non-negotiables.
5. Map the current state, history, and why prior choices were made.
6. Identify edge cases, exceptions, risks, objections, and failure modes.
7. Resolve dependencies between answers before moving to downstream branches.
8. Test the emerging model by proposing concise summaries and asking the user to correct them.
9. Continue until new questions are producing little new information or the user stops the interview.

For each question, include a recommended answer via the first option. The recommendation should reflect the best current understanding, not a generic default.

## Topic Coverage

Adapt the interview tree to the topic:

- Business: positioning, customers, offer, pricing, distribution, operations, risks, proof, roadmap.
- Product: users, jobs-to-be-done, workflows, feature boundaries, success metrics, edge cases.
- Design: audience, desired feeling, hierarchy, visual constraints, interaction states, references.
- Engineering: system purpose, architecture, invariants, data flow, failure modes, deployment, tests.
- Strategy: objective, options, tradeoffs, constraints, timing, dependencies, decision criteria.
- Personal knowledge capture: vocabulary, values, history, preferences, recurring decisions, examples.
- Process documentation: triggers, inputs, handoffs, tools, checklists, exceptions, escalation paths.

## Exhaustiveness Standard

Do not stop at the first plausible answer. Keep interviewing until these are clear:

- What the topic is and is not.
- Why it matters.
- Who it matters to.
- What success looks like.
- What constraints shape the answer.
- What exceptions or edge cases change the default.
- What language, labels, or framing the user prefers.
- What should be preserved, avoided, or escalated in future work.

When the user says the understanding is complete, provide a compact synthesis with:

- The root definition.
- Key principles.
- Important branches and decisions.
- Open questions, if any.
- Recommended next action.

Attribution

mike-coulbournmike-coulbourn
View sourceMore from mike-coulbourn →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

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', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →