interview

interview is a skill for Claude Code, Codex from akovalion/paranoid-qa. It costs 52 tokens per session (791 once invoked), scanned A, original, MIT.

A structured interview process for turning an informal software request into clear requirements and acceptance checks.

In plain words
What is it for?
It helps clarify features, bugs, screens, platforms, loading and error states, negative cases, and outside-service integrations before implementation or testing.
Why use it?
It removes uncertainty about scope, expected behavior, edge cases, and the situations that need testing.

Skill for Claude CodeCodex

Part of the paranoid-qa-ru plugin — 5 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/akovalion/paranoid-qa/interview
Any agent
npx skills add akovalion/paranoid-qa --skill interview
Clone the repo
git clone --depth 1 https://github.com/akovalion/paranoid-qa

Made for: Claude Code, Codex.

Or install paranoid-qa-ru, the plugin that ships this one along with the rest of its 5 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for interview

README.md
[![agentmods](https://agentmods.dev/badge/skills/akovalion/paranoid-qa/interview.svg)](https://agentmods.dev/skills/akovalion/paranoid-qa/interview)
Your own site
<a href="https://agentmods.dev/skills/akovalion/paranoid-qa/interview"><img src="https://agentmods.dev/badge/skills/akovalion/paranoid-qa/interview.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 791 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.00791
Opus 5 $0.00026 $0.00396
Sonnet 5 $0.00010 $0.00158
Haiku 4.5 $0.00005 $0.00079

Measured 5d ago against content hash 52f33ee14b14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

ru/skills/interview/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interview: сбор требований через вопросы

Помоги пользователю структурировать неформальное описание задачи в полные требования, готовые к передаче в скиллы test-cases или testing.

Когда применять

  • Задача описана устно или общими словами, без тикета
  • Нет AC, нет макетов, нет чёткого scope
  • Пользователь сам не уверен, что именно тестировать/автоматизировать

Если задача уже из трекера (Jira и т.п.) с полным описанием — этот скилл не нужен: собери контекст прямо из тикета (через MCP трекера: описание, комментарии, вложения, связанные задачи) и передай в test-cases.

Процесс

Раунд 1: scope и контекст. Задай 3-4 вопроса через AskUserQuestion:

  • Что именно проверяем (фича, страница, элемент)
  • Где это живёт (URL, экран, путь в навигации)
  • Тип задачи (новая функциональность / регресс / баг)
  • Платформы (desktop / mobile / оба)

Раунд 2: поведение и AC. На основе ответов 1-го раунда:

  • Happy path — какое поведение считается корректным
  • Edge cases — что важно проверить из негативных сценариев
  • Состояния UI (loading, error, empty, disabled) — если применимо
  • Интеграции — есть ли API / внешние сервисы

Раунд 3: уточнения по оставшимся пробелам. Только если после 1-2 раундов остались критичные пробелы. Группируй связанные вопросы.

Максимум 3 раунда. Если требования всё ещё неполные — зафиксируй пробелы как «Вопросы для аналитика/PM» и работай с тем, что есть.

Формат вывода

После завершения опроса собери структурированный summary:

# Требования: <короткое название задачи>

## Контекст
- Тип: <новая фича / регресс / баг>
- Платформы: <desktop / mobile / оба>
- URL / расположение: <…>

## Scope
<что именно проверяем, кратко>

## Acceptance Criteria
- <AC 1>
- <AC 2>

## Сценарии
**Happy path:** <описание>

**Edge cases:**
- <case 1>
- <case 2>

## Интеграции
<API, внешние сервисы — если есть>

## Открытые вопросы для аналитика/PM
- <вопрос 1>

Сохрани summary в md-файл (например, requirements_<task_name>.md в текущей рабочей директории) и предложи пользователю передать его в test-cases или testing.

Read the full file on GitHub · 78 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 78 lines · 52 tokens per session scan A 52f33ee14b14

Subscribe to this mod's changes

interview is a skill published in the GitHub repository akovalion/paranoid-qa (13 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 791 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

mk:qa

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a…

ngocsangyem/MeowKit · 127 tokens

automated-e2e-testing

将手动测试用例转为 Playwright E2E 测试并执行时使用;含写自动化前的业务熟悉踩点、Page Object/Helper 编写、执行中的 Bug 证据收集与报告条目记录。不用于:纯 API 接口测试(api-testing)、以理解系统为目的的独立探索会话(exploratory-testing)、已确认 Bug 的根因分析(bug-analysis)。.

fishzjp/qa-skills · 100 tokens

qawolf-cli

Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; request automation of…

qawolf/cli · 118 tokens

api-testing

接口级测试时使用——从 OpenAPI/Swagger 文档或用例 Schema 中可自动化的接口用例出发,覆盖参数、边界、鉴权、幂等、并发、错误响应与数据一致性,产出可执行的 API 测试脚本与运行结果;含接口压测承接(k6,类型矩阵轴 1 执行层)。不用于:Web UI 流程(automated-e2e-testing)、手动用例编写(test-case-writing)。.

fishzjp/qa-skills · 117 tokens

test-strategy

回答"这个功能应该怎么测"——把风险翻译成两域测试范围与深度。策略位于"需求 → 风险分析 → 策略 → 测试设计 → 用例"链路中,跳过策略直接写用例是本框架明确反对的。.

fishzjp/qa-skills · 103 tokens

regression-testing

代码变更(diff/Bug 修复/需求变更)后判断应回归哪些测试时使用——沿"改动文件 → 改动函数 → 受影响功能 → 受影响用例"分析链,基于用例 Schema 的追溯映射产出分级回归清单。不用于:用例文件本身的增量修改(test-case-writing)、长期回归策略(test-strategy)。.

fishzjp/qa-skills · 98 tokens