Skip to content
Agentmart
Submit a tool

deep-interview

Clarify an underspecified product or engineering request through one focused question at a time before planning or implementation.

Skill by Rafcin

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/rafcin-deep-interview

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Clarify an underspecified product or engineering request through one focused question at a time before planning or implementation.

Use cases: agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/deep-interview

What's inside

Skill name
deep-interview
Description
Clarify an underspecified product or engineering request through one focused question at a time before planning or implementation.
License
MIT
Instructions
28 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Deep Interview

## Entry conditions

Use only when outcome, boundaries, or acceptance criteria are genuinely unclear. Skip execution-ready work or an explicit request to proceed with stated assumptions. Inspect discoverable facts first and do not ask the user for repository facts that can be established safely.

## Scope limit

Ask one high-leverage question at a time: outcome before implementation detail, then scope, exclusions, constraints, success criteria, and approval decisions. If sources conflict, state the conflict precisely. Do not continue to reach a fixed round count or begin planning or implementation inside this interview.

## Exit evidence

When ready, summarize:

- the problem and observable outcome;
- in-scope behavior and explicit non-goals;
- acceptance criteria;
- constraints and supporting evidence;
- what Codex may decide and what still requires confirmation;
- relevant technical context without prematurely choosing an implementation.

End at the handoff boundary.

## Next gate

After clarified intent is accepted, use `context` for a durable constraint, `codebase-design` for a seam decision, or `plan` for execution planning.

From Rafcin/oh-my-codex-slim, MIT.

More from Rafcin/oh-my-codex-slim

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 26, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/Rafcin/oh-my-codex-slim
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Rafcin

Cite this page

deep-interview skill. Agent Mart. https://agentmart.dev/skills/rafcin-deep-interview (last updated 2026-10-24)