qa-question-framework

qa-question-framework is a skill for Claude Code from Kokxi/qa-test-skills. It costs 116 tokens per session (2,914 once invoked), scanned A, original, MIT.

A question framework for gathering the missing details needed to design or review software tests. It covers goals, users, boundaries, business rules, errors, performance, security, and compatibility.

In plain words
What is it for?
Interviewing product or development teams, clarifying feature scope and edge cases, reviewing test cases, and asking focused questions before reporting a bug.
Why use it?
It turns vague requirements into information that testers and developers can act on, reducing gaps in scenarios and unclear expected results.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the qa-test-skills plugin — 49 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/kokxi/qa-test-skills/qa-question-framework
Any agent
npx skills add Kokxi/qa-test-skills --skill qa-question-framework
Clone the repo
git clone --depth 1 https://github.com/Kokxi/qa-test-skills

Made for: Claude Code.

Or install qa-test-skills, the plugin that ships this one along with the rest of its 49 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 qa-question-framework

README.md
[![agentmods](https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-question-framework.svg)](https://agentmods.dev/skills/kokxi/qa-test-skills/qa-question-framework)
Your own site
<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-question-framework"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-question-framework.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,914 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 5.1 $0.00116 $0.02914
Opus 5 $0.00058 $0.01457
Sonnet 5 $0.00023 $0.00583
Haiku 4.5 $0.00012 $0.00291

Measured yesterday against content hash 3114a39d0182, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa-question-framework 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 yesterday.

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.

skills/qa-question-framework/SKILL.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ 安全警告:本技能的示例可能涉及订单号、支付金额、截图、身份证、手机号等敏感数据。 实际使用时请勿粘贴真实生产数据、客户信息或财务凭证;测试前应脱敏/掩码处理。 本技能仅在 workspace/ 输出评估文件,不持久化、不外传、不跨会话复用。

提问框架

核心原则

专家不是"知道答案",而是"知道该问什么"。

四大提问场景

场景1:拿到需求时的提问链

目标:从模糊需求中挖掘完整信息

第一层:业务目标
├─ 这个功能要解决什么问题?
├─ 目标用户是谁?有几个角色?
├─ 核心价值是什么?用户能得到什么?
└─ 成功标准是什么?怎么衡量做成了?

第二层:功能边界
├─ 功能包含什么?不包含什么?
├─ 核心流程是什么?有几条路径?
├─ 输入是什么?输出是什么?
└─ 约束条件有哪些?限制是什么?

第三层:业务规则
├─ 有哪些业务规则?规则间有什么关系?
├─ 异常情况怎么处理?有降级方案吗?
├─ 状态怎么流转?状态变更条件是什么?
└─ 数据怎么存储?有数据迁移需求吗?

第四层:非功能需求
├─ 性能要求是什么?响应时间、并发量?
├─ 安全要求是什么?权限、数据保护?
├─ 兼容性要求是什么?浏览器、设备、系统?
└─ 可用性要求是什么?容错、恢复?

示例提问

"这个登录功能要解决什么问题?只是验证身份,还是有其他目的?"
"除了用户名密码登录,还有其他登录方式吗?"
"登录失败后怎么处理?有锁定机制吗?"
"登录状态保持多久?需要记住我功能吗?"

场景2:评审用例时的提问链

目标:识别测试用例的不足

第一层:完整性检查
├─ 主路径场景都覆盖了吗?
├─ 分支路径都考虑了吗?
├─ 异常场景都设计了吗?
└─ 边界条件都分析了吗?

第二层:深度检查
├─ 边界分析够深吗?有隐含边界吗?
├─ 并发场景考虑了吗?
├─ 时序依赖分析了吗?
└─ 资源竞争测试了吗?

第三层:风险检查
├─ 高风险区域深挖了吗?
├─ 资金相关场景重点测了吗?
├─ 安全相关场景覆盖了吗?
└─ 数据一致性验证了吗?

第四层:可执行性检查
├─ 测试数据能构造吗?
├─ 测试环境能搭建吗?
├─ 测试步骤能执行吗?
└─ 预期结果能验证吗?

示例提问

"这个用例的前置条件能实现吗?数据从哪来?"
"这个预期结果怎么验证?有具体指标吗?"
"这个场景考虑过并发情况吗?"
"这个边界真的够深吗?还有其他边界吗?"

场景3:报Bug前的提问链

目标:确保Bug报告完整有效

第一层:现象确认
├─ Bug的具体表现是什么?
├─ 在什么条件下出现?
├─ 复现步骤是什么?
└─ 出现频率是多少?

第二层:环境信息
├─ 在什么环境下出现?
├─ 使用什么浏览器/设备?
├─ 网络环境是什么?
└─ 数据状态是什么?

第三层:影响评估
├─ 影响范围有多大?
├─ 影响哪些用户?
├─ 有 workaround 吗?
└─ 优先级是什么?

第四层:根因推测
├─ 可能的原因是什么?
├─ 相关日志/截图有吗?
├─ 之前出现过类似问题吗?
└─ 哪个模块/接口可能有问题?

示例提问

"能详细描述一下Bug现象吗?"
"在什么条件下会出现这个问题?"
"能提供复现步骤吗?从头开始操作一遍"
"这个问题影响多大?有用户受影响吗?"

场景4:复盘时的提问链

目标:从问题中提取改进点

第一层:事实还原
├─ 发生了什么问题?
├─ 什么时候发现的?
├─ 影响范围多大?
└─ 处理过程是怎样的?

第二层:根因分析
├─ 直接原因是什么?
├─ 根本原因是什么?
├─ 为什么没提前发现?
└─ 流程哪里出了问题?

第三层:改进措施
├─ 怎么防止再次发生?
├─ 流程需要怎么优化?
├─ 工具需要怎么改进?
└─ 知识需要怎么沉淀?

第四层:资产沉淀
├─ 这次学到了什么?
├─ 哪些经验可以复用?
├─ checklist需要更新吗?
└─ 培训材料需要补充吗?

示例提问

"这次问题的根本原因是什么?不是表面原因"
"为什么测试没发现这个问题?是覆盖不足还是方法问题?"
"下次怎么防止类似问题?具体措施是什么?"
"这次的经验怎么沉淀?checklist需要更新吗?"

提问技巧

5W1H 质疑法

What:这是什么?做什么用的?
Why:为什么要做?为什么这样做?
Who:谁在用?谁负责?
When:什么时候用?什么时候上线?
Where:在哪里用?数据从哪来?
How:怎么用?怎么实现?

Read the full file on GitHub · 295 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. yesterday Changed 3114a39d0182
  2. 6d ago First seen · 295 lines · 116 tokens per session scan A 5b962c9ffbc3

Subscribe to this mod's changes

qa-question-framework is a skill published in the GitHub repository Kokxi/qa-test-skills (24 stars, last pushed 4d ago), licensed MIT. It adds 116 tokens to every session and 2,914 once invoked, about $0.0006 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.