qa-input-validation

qa-input-validation is a skill for Claude Code from Kokxi/qa-test-skills. It costs 99 tokens per session (2,492 once invoked), scanned A, original, MIT.

A check that verifies whether a testing request contains enough detail to begin, such as the feature, users, expected result and relevant documents.

In plain words
What is it for?
Use it at the start of a testing workflow to identify missing requirements, context, files or links and ask the requester for the information needed.
Why use it?
A request like “test this” does not provide enough information to design useful tests and can lead to unsupported assumptions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the qa-test-skills plugin — 49 skills shipped together

Good fit Use it at the start of a testing workflow to identify missing…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kokxi/qa-test-skills/qa-input-validation
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.

Any agent
npx skills add Kokxi/qa-test-skills --skill qa-input-validation
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-input-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-input-validation.svg)](https://agentmods.dev/skills/kokxi/qa-test-skills/qa-input-validation)
Your own site
<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-input-validation"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-input-validation.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,492 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00099 $0.02492
Opus 5 $0.00049 $0.01246
Sonnet 5 $0.00020 $0.00498
Haiku 4.5 $0.00010 $0.00249

Measured yesterday against content hash 72ac2f97007e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa-input-validation 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-input-validation/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 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。

输入验证

核心原则

垃圾进,垃圾出——输入质量决定输出质量。 本技能是整个QA Test Skills工作流的第一步,在需求评审之前执行,验证输入是否满足生成高质量测试用例的基本要求。

验证维度

维度1:需求明确性

检查点:
├─ 是否有明确的功能描述?
├─ 是否有业务目标?
├─ 是否有用户角色?
└─ 是否有成功标准?

评分标准:
- 10分:需求完整清晰,包含所有必要信息
- 7分:需求基本清晰,缺少少量信息
- 4分:需求模糊,缺少关键信息
- 1分:需求不明,无法理解

维度2:上下文充分性

检查点:
├─ 是否有业务背景?
├─ 是否有技术架构?
├─ 是否有历史缺陷?
├─ 是否有约束条件?
└─ 是否有参考文档?

评分标准:
- 10分:上下文完整,可直接生成
- 7分:上下文基本充分,可补充少量信息
- 4分:上下文不足,需要补充
- 1分:上下文缺失,无法生成

维度3:输入类型识别

输入类型:
├─ 直接描述:文字描述需求
├─ 上传文件:附件/文件路径
├─ URL链接:http/https开头
└─ 混合输入:多种类型组合

验证规则:
- 直接描述:检查是否包含功能关键词
- 上传文件:检查文件是否可读取
- URL链接:检查URL是否可访问
- 混合输入:检查各部分是否完整

验证流程

步骤1:解析用户输入

解析内容:
├─ 提取需求描述
├─ 识别输入类型
├─ 检查是否有附件/URL
└─ 提取关键词

步骤2:评估输入质量

评估维度:
├─ 需求明确性(0-10分)
├─ 上下文充分性(0-10分)
├─ 信息完整性(0-10分)
└─ 可测试性(0-10分)

综合评分 = (需求明确性 + 上下文充分性 + 信息完整性 + 可测试性) / 4

步骤3:生成验证结果

结果类型:
├─ pass(通过):综合评分≥7分
├─ need_more_info(需要更多信息):综合评分4-6分
└─ fail(失败):综合评分<4分

输出格式

通过(pass)

{
  "validation_result": "pass",
  "input_quality_score": 8,
  "missing_info": [],
  "recommendation": "输入质量良好,可以继续执行"
}

需要更多信息(need_more_info)

{
  "validation_result": "need_more_info",
  "input_quality_score": 5,
  "missing_info": [
    "缺少业务背景描述",
    "缺少用户角色说明",
    "缺少约束条件"
  ],
  "clarification_questions": [
    "这个功能的业务目标是什么?",
    "主要用户有哪些角色?",
    "有什么技术约束或业务规则?"
  ],
  "recommendation": "请补充以上信息后再生成"
}

失败(fail)

{
  "validation_result": "fail",
  "input_quality_score": 2,
  "missing_info": [
    "缺少功能描述",
    "缺少业务背景",
    "缺少所有必要信息"
  ],
  "clarification_questions": [
    "请描述需要测试的功能是什么",
    "这个功能的业务背景是什么",
    "主要用户是谁,核心流程是什么"
  ],
  "recommendation": "输入信息严重不足,无法生成有效测试用例"
}

输入类型速查表

输入类型 示例 验证重点 典型评分区间
功能名称 "测试登录" 缺业务目标、用户角色、约束 4-6分
场景描述 "用户输入密码错误3次锁定" 缺边界条件、非功能需求 6-8分
PRD文档 上传完整需求文档 检查可读性、覆盖度、歧义 7-10分
URL链接 需求文档链接 检查可访问性、内容完整性 5-9分
截图/图片 功能截图 缺完整上下文、业务规则 3-6分
Bug描述 "XX功能报错了" 缺复现步骤、环境、数据 3-5分
混合输入 描述+附件+URL 各部分一致性、互补性 6-9分

Read the full file on GitHub · 257 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 72ac2f97007e
  2. 6d ago First seen · 257 lines · 99 tokens per session scan A 25e47aae3606

Subscribe to this mod's changes

qa-input-validation is a skill published in the GitHub repository Kokxi/qa-test-skills (24 stars, last pushed 4d ago), licensed MIT. It adds 99 tokens to every session and 2,492 once invoked, about $0.0005 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