Interview Me
Interview Me is an agent skill (a SKILL.md file) from addyosmani/agent-skills. Extracts what the user actually wants instead of what they think they should want. It works with Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode and has 110,586 GitHub stars across a repository of 13 listed skills.
github.com/addyosmani/agent-skills/skills/interview-me (opens in a new tab)
Data as of from the GitHub API and skills.sh; description from the skill's SKILL.md. Report an error
- Multi-skill repo
- Plugin marketplace
- Testing & QA
- Active
Add this skill
Claude
This repository is a Claude Code plugin marketplace. In Claude Code:
/plugin marketplace add addyosmani/agent-skills
/plugin install agent-skills@addy-agent-skillsIn the Claude apps, zip the interview-me folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).
ChatGPT / Codex
Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:
git clone --depth 1 https://github.com/addyosmani/agent-skills.git
cp -r agent-skills/skills/interview-me .agents/skills/interview-me # repo; ~/.agents/skills for all projectsStandalone skills also load in the ChatGPT desktop app.
Cursor
Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:
git clone --depth 1 https://github.com/addyosmani/agent-skills.git
cp -r agent-skills/skills/interview-me .cursor/skills/interview-me # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)
What this skill 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.
When it triggers
- 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 ambig
- "build me X"
- "for whom"
- "why now"
- "interview me"
- "grill me"
- "are we sure?"
- "stress-test my thinking"
More skills in addyosmani/agent-skills
13 skills are listed from this repository.
Code Review And Qualityaddyosmani/agent-skills
Security And Hardeningaddyosmani/agent-skills
Frontend UI Engineeringaddyosmani/agent-skills
Performance Optimizationaddyosmani/agent-skills
Documentation And Adrsaddyosmani/agent-skills
Debugging And Error Recoveryaddyosmani/agent-skills
Code Simplificationaddyosmani/agent-skills
API And Interface Designaddyosmani/agent-skills
Test Driven Developmentaddyosmani/agent-skills
Incremental Implementationaddyosmani/agent-skills
Context Engineeringaddyosmani/agent-skills
Idea Refineaddyosmani/agent-skills
Similar skills
More testing & qa skills
Browser Screenshot Diff
ruvnet/ruflo
Visual + DOM diff between two recorded sessions at matching trajectory step ids; used for visual regression and replay verification.
Active · last commit Oct 26, 2026
Testing & QATypeScriptFinishing A Development Branch
obra/superpowers
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
Active · last commit Oct 21, 2026
Testing & QAShellRuview Hardware Setup
ruvnet/RuView
ESP32-S3 / ESP32-C6 firmware build, flash, WiFi provisioning, and serial monitoring for RuView CSI sensing nodes.
Active · last commit Oct 22, 2026
Testing & QARustScaffold Exercises
mattpocock/skills
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting.
Active · last commit Oct 19, 2026
Testing & QAShellQA Acceptance
paperclipai/paperclip
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
Active · last commit Oct 26, 2026
Testing & QATypeScriptVersion Bump
thedotmack/claude-mem
Automated semantic versioning and release workflow for Claude Code plugins.
Active · last commit Oct 25, 2026
Testing & QATypeScript
How do I install the Interview Me skill?
In Claude Code, run /plugin marketplace add addyosmani/agent-skills and then /plugin install agent-skills@addy-agent-skills. For Codex or Cursor, copy the interview-me folder into .agents/skills/ or .cursor/skills/.
Is the Interview Me skill free?
Yes. The repository is open source under the MIT license.
Is Interview Me maintained?
The repository's most recent commit was on Oct 13, 2026. Its latest release is 0.6.13. appsgit only lists skills from repositories with a commit in the last six months.