Skip to content
Back to skills

Interview Me

ASecurity

Analyze underspecified requests with a short decision interview. Use this skill when guessing would risk the wrong plan.

  • 9 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added June 1, 2026
ai-agents

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned June 1, 2026

npx -y skills add jscraik/Agent-Skills --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 with every re-scan.

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

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: interview-me
description: Analyze underspecified requests with a short decision interview. Use this skill when guessing would risk the wrong plan.
metadata:
  skill-type: team_automation
---

# Interview Me

## Philosophy
Ask the smallest useful question, reduce uncertainty quickly, and preserve an explicit approval boundary.

## When To Use
- One or two decisions would materially change the work.
- The user needs assumptions, tradeoffs, or approval gates clarified.
- A downstream planning or implementation skill needs a compact handoff.

## Avoid
- Do not use when the request is already implementation-ready.
- Do not run a broad discovery workshop when one decision question will unblock the work.
- Do not prescribe implementation before unresolved decisions are closed or declared as assumptions.

## Inputs
- User request and target repo or artifact.
- Evidence source such as files, diffs, issues, releases, or existing workflow state.
- Any safety, privacy, compliance, or approval constraints.

## Outputs
- Schema-bound outputs include `schema_version`.
- Decision log with assumptions and constraints.
- Approval status.
- Compact handoff for the next skill.

## Workflow
1. Ask one high-impact question with 3-5 choices and one recommended default.
2. Explain briefly why the answer matters.
3. Ask a second question only if a material blocker remains.
4. Maintain a compact decision and assumption log.
5. End with approved, needs-input, or blocked plus the next route.

## Constraints
- Redact secrets and sensitive context by default.
- Do not ask broad exploratory questions without a decision payoff.
- Do not invent constraints or approval.
- Fail fast at the first missing input that would change the outcome.

## Validation
- Run Plugin Eval and strict skill audit after editing this skill.
- Report exact validation commands and pass/fail outcomes.
- Fail fast: stop at the first failed gate, fix it, and rerun before continuing.

## Anti-Patterns
- Do not use when the request is already implementation-ready.
- Do not run a broad discovery workshop when one decision question will unblock the work.
- Do not prescribe implementation before unresolved decisions are closed or declared as assumptions.

## Examples
- "This request is fuzzy; ask the one question that changes the plan."
- "I have no success metric yet; help me decide what to ask."

## Progressive Disclosure
- Archived full context: `Infrastructure/references/deferred-skill-context/product-strategy-interview-me/`.
- Load archived references only when the active workflow needs that exact detail.
- Keep the active path compact; do not remove important context for budget trimming.

## See Also

| Skill | When to use together |
|---|---|
| [[verification-before-completion]] | Confirm gate outcomes and report deterministic pass/fail evidence before closeout |
| [[project-brain]] | Capture durable repo learnings and route updates into the canonical memory surface |

Files in this skill

  • SKILL.md2.9 KB
  • references/contract.yaml742 B
  • references/evals.yaml2.4 KB
  • references/task-profile.json923 B

Attribution

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

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.