interview-me · neeeophytee — Claude Code skill: what it does, how to install
Interviews you one question at a time to clarify requirements before coding starts. It helps when brainstorming is finished but the technical spec still has open gaps.
npx skills add Neeeophytee/finding-unknowns-skills --skill interview-me -a claude-codeWhat interview-me does
The skill organizes task discovery before any code gets touched. First, the agent inspects existing specs, prototypes, and code to avoid asking answered questions. It builds an internal list of unknowns, sorting them by blast radius. High-impact architectural questions come first, followed by edge cases and runtime failures, while cosmetic details are left for last.
Every interaction contains strictly one question with surrounding context, two or three actionable options, and a clear recommendation. The prompt explicitly accepts "you decide" if you prefer delegating the choice. Whenever a new answer collides with an earlier agreement, the agent flags the conflict on the spot instead of silently adopting the change.
Interviews pause periodically to summarize confirmed choices and keep direction aligned. Questioning stops as soon as finding remaining details in code becomes cheaper than debating them. At that point, you receive a clean decision log ready for the implementation plan.
What it helps with
- uncover critical architectural trade-offs prior to coding
- clarify edge cases and failure behaviors step by step
- prevent models from dumping overwhelming walls of questions
- produce a clean, dispute-free log of decisions for the task plan
Example prompts for the agent
- Read the task outline in
spec.mdand interview me with interview-me before writing code - Run interview-me to clarify open requirements for the payment refactor
- Interview me about the new caching layer one question at a time
How to install interview-me
1Skills CLI (Vercel)
npx skills add Neeeophytee/finding-unknowns-skills --skill interview-me -a claude-code2Manually: put the files in place
~/.claude/skills/interview-me/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/interview-me/
1Skills CLI (Vercel)
npx skills add Neeeophytee/finding-unknowns-skills --skill interview-me -a codex2Manually: put the files in place
.agents/skills/interview-me/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Neeeophytee/finding-unknowns-skills --skill interview-me -a cursor2Manually: put the files in place
.cursor/skills/interview-me/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Neeeophytee/finding-unknowns-skills interview-me2Manually: put the files in place
.github/skills/interview-me/SKILL.md1Skills CLI (Vercel)
npx skills add Neeeophytee/finding-unknowns-skills --skill interview-me -a gemini-cli2Platform CLI
gemini skills install https://github.com/Neeeophytee/finding-unknowns-skills --path skills/interview-meManually: put the files in place
.devin/skills/interview-me/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Neeeophytee/finding-unknowns-skills --skill interview-me -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about interview-me
How to install interview-me in Claude Code?
Run npx skills add Neeeophytee/finding-unknowns-skills --skill interview-me -a claude-code. The file will be placed in ~/.claude/skills/interview-me/SKILL.md.
What does interview-me do?
It runs a structured pre-implementation interview, asking one prioritized question per turn. Each question includes background context, options, and a recommended default.
When does the interview stop?
It ends once remaining unknowns are cheaper to uncover during coding than through discussion. The agent states this directly and prints the final decision log.
Source text
SKILL.md · MIT
--- name: interview-me description: Interview the user one question at a time to resolve remaining ambiguity before implementation. Use when planning or brainstorming is done but unknowns remain, or when the user asks to be interviewed about a task or spec. --- # Interview me Brainstorming is over and there are still gaps between the user's map and the territory. Close them by asking, one question at a time, starting with the questions whose answers would change the most. ## Steps 1. Read everything already established: the request, any spec, any prototypes, relevant code. Do not ask about things that are already answered. 2. Build a private list of open ambiguities and sort by blast radius: - **First: architecture-changers** — answers that would alter the data model, the interfaces, or the overall approach. - **Then: behavior definers** — edge cases, failure modes, defaults, permissions. - **Last: polish** — naming, copy, cosmetics. Often not worth asking; propose and move on. 3. Ask exactly one question per turn. For each: give the context that makes it matter, offer 2-3 concrete options with your recommendation, and accept "you decide" as an answer you then own. 4. Every few questions, checkpoint: restate what has been decided so far in one tight list, so drift dies early. 5. Stop when the remaining unknowns are cheaper to discover during implementation than to ask about now, and say that out loud. End with the final decision list, ready to paste into a plan. ## Guardrails - One question at a time means one. No question bundles. - Never ask a question whose answer is discoverable from the codebase; go look instead. - If an answer contradicts an earlier decision, flag the conflict immediately rather than silently taking the newest answer.
© Neeeophytee · MIT · Neeeophytee/finding-unknowns-skills
Similar skills
All skills for Agent setup: memory, context, orchestration →interview-me by other authors comes first.
