Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Interview

ASecurity

Pre-implementation interview — the model asks the user the questions that turn known unknowns into decisions, biggest blast radius first. Use when the user says "interview me", "ask me questions before implementing", or requirements are incomplete and implementation has not started.

2 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsapisecurityperformance

Works with

api

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add ajitta/know-your-unknowns --skill interview --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Interview?

Add the live security badge to your README — it updates automatically with every re-scan.

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

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: interview
description: >
  Pre-implementation interview — the model asks the user the questions that turn
  known unknowns into decisions, biggest blast radius first. Use when the user says
  "interview me", "ask me questions before implementing",
  or requirements are incomplete and implementation has not started.
argument-hint: "[task/spec description] [priority hint]"
---

# Interview — Pre-Implementation Interview

Requirements incomplete? Don't implement yet — **model interviews user**.
Origin: The Interview — see skills/loop/references/talk-source.md.

## Question Priority (blast radius, fixed)

1. Questions whose answer **changes the whole architecture**
2. Questions that could cause **data loss / security problems**
3. **Compatibility with external APIs / existing code**
4. Questions affecting **performance / operating cost**
5. UI taste, minor implementation details (last)

## Procedure

1. From `$ARGUMENTS` and conversation context, list spec gaps (known unknowns).
   No arguments → the spec under discussion; if none, ask once what to interview about.
   If the user has not yet said what they are sure of and what they are assuming, make
   that the first question of round 1: settled items are not asked again, and stated
   assumptions become questions of their own.
2. Ask **max 4 questions per round** (AskUserQuestion hard cap: 1-4 questions,
   2-4 options each), in priority order. Attach a **one-line reason why it matters**
   to each question.
3. If AskUserQuestion tool available, use it for multiple-choice questions. Give each
   option a short consequence (tradeoff) note.
4. On answers: re-present decisions as an **updated spec summary**; if undecided
   items remain, propose next round.
5. If user wants a deep interview (e.g. "40-question level"), repeat rounds while
   keeping architecture → data → compatibility → performance → taste order.

## Final Deliverables

When interview ends, present two things:

1. **Decision table** — radius (architecture / data / ux / polish) / question /
   decision / rationale / left undecided.
2. **Ready-to-use implementation prompt** — complete instruction with all decisions
   applied. Mark skipped questions "(unanswered — use your judgment)"; declare the
   architecture and data decisions **fixed**, with "if anything later conflicts with
   them, flag it before writing code"; close with "start with a short plan, then
   implement". User copying this to start implementation is the skill's purpose.

Then offer in one AskUserQuestion: proceed with this prompt now / let me edit it /
stop here.

## Never

- Ask questions already answered in conversation/codebase (investigate first).
- Start from priority 5 (taste).
- Start implementing on guesses without the interview.

Attribution

ajittaajitta
View sourceMore from ajitta →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →