interview-me

An agent skill by addyosmani, from addyosmani/agent-skills. Tags: design, documents.

What it does

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add addyosmani/agent-skills --skill interview-me

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/addyosmani/agent-skills
cp -r agent-skills/skills/interview-me ~/.claude/skills/interview-me

Safety box score

Grade A, minimal risk: 4 of 100 risk points, rated 2026-09-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a conversational clarification skill, not an execution skill: it asks one question at a time, keeps a confidence estimate, and only optionally writes a confirmed intent note. It does not ship scripts, download code, or access secrets; the main practical effect is slowing down ambiguous requests to reduce misalignment.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No scripts, shell commands, code evaluation, or native binaries are included; the skill is only markdown guidance for conversation.
Network access	0 (none)	The file contains no downloading, API calls, or remote data transmission instructions.
Filesystem reach	1 (low)	It may optionally save a confirmed intent document to `docs/intent/[topic].md`, which is a bounded write inside the project tree.
Secrets & credentials	0 (none)	It does not ask for tokens, passwords, `.env` files, keychains, or browser sessions.
Privilege & persistence	0 (none)	No sudo, global installs, services, shell startup changes, or OS setting changes are described.
Instruction hijack surface	0 (none)	The instructions are about structured questioning and confirmation; there is no prompt-injection content, instruction to ignore rules, or hidden text.
Irreversible actions	0 (none)	It does not perform external actions like posting, paying, deploying, or deleting; it only narrows intent and may draft a note after explicit confirmation.
Transparency	0 (none)	The skill is fully readable markdown with no binaries, obfuscated blobs, or runtime-downloaded content.

Before installing

Confirm you’re okay with a skill that intentionally slows ambiguous requests by asking one question at a time.
Check that optional notes under `docs/intent/[topic].md` are acceptable in your repository.
If you use autonomous or non-interactive runs, verify this skill will be blocked there rather than guessing.

Rated 2026-09-20 by an automated review of 1 file from the skill's repository.

Source

Repository: addyosmani/agent-skills (all skills from this repository)
Path: skills/interview-me/SKILL.md
Branch: main
Updated: 2026-09-19

design-md — Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files
stitch::extract-static-html — Extract self-contained static HTML from a built web application or React components by inlining CSS and images.
stitch::manage-design-system — Manage design systems in Stitch using MCP tools. Includes retrieval of assets, creating/updating design systems in Stitch, and applying them to screens.
api-and-interface-design — Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface.
idea-refine — Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking.
spec-driven-development — Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet.