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.
npx skills add Kokxi/qa-test-skills --skill qa-ai-prompt-strategygit clone --depth 1 https://github.com/Kokxi/qa-test-skillsWrote 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.
[](https://agentmods.dev/skills/kokxi/qa-test-skills/qa-ai-prompt-strategy)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-ai-prompt-strategy"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-ai-prompt-strategy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-ai-prompt-strategy"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-ai-prompt-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00119 | $0.03111 |
| Opus 5 | $0.00060 | $0.01555 |
| Sonnet 5 | $0.00024 | $0.00622 |
| Haiku 4.5 | $0.00012 | $0.00311 |
Grade A, and why
qa-ai-prompt-strategy 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 提示词策略
核心原则
不同的测试目标，需要不同的提问模式。
提示词优化要求
关键指标：提示词必须包含以下要素
1. 角色定义：你是[领域]资深测试专家
2. 输出数量：生成[N]条测试用例（N = 需求数量 × 5）
3. 覆盖维度：必须覆盖以下维度
- 功能测试：[具体功能点]
- 异常测试：[异常场景类型]
- 边界测试：[边界条件类型]
- 并发测试：[并发场景]
- 安全测试：[安全风险点]
- 性能测试：[性能指标]
4. 输出格式：Markdown表格，包含需求ID和风险ID
5. 质量要求：每条用例必须可执行、可验证
六大提示词模式
模式1：结构化输出模式
适用场景：需要标准化、可对比的测试用例
请按以下框架输出测试用例：
1. 用例编号：TC_{模块缩写}_{功能缩写}_{序号}（如 TC_API_LOGIN_001）
2. 用例标题：[动作] + [对象] + [条件]
3. 前置条件：[测试前需要满足的条件]
4. 测试步骤：[1. 2. 3. ...]
5. 预期结果：[具体可验证的预期]
6. 优先级：P0/P1/P2/P3
7. 风险等级：高/中/低
输出格式：Markdown表格
测试范围：[功能描述]
测试深度：覆盖正常/异常/边界/安全
模式2：角色扮演模式
适用场景：需要从特定视角深入测试
你现在是一位[角色]，正在使用[功能]。
你的背景：
- 使用频率：[每天/每周/偶尔]
- 技术水平：[新手/普通/专家]
- 核心诉求：[你最关心什么]
- 常见操作：[你通常怎么用]
请从这个角色的视角，列出：
1. 你会怎么用这个功能？
2. 你会遇到什么问题？
3. 什么会让你不满意？
4. 你会怎么误用这个功能？
模式3：分步引导模式
适用场景：复杂功能需要深度分析
请按以下步骤分析这个功能：
第1步：需求解构
- 列出所有显性需求
- 挖掘隐含假设
- 识别潜在矛盾
第2步：场景构建
- 主路径场景
- 分支路径场景
- 异常恢复场景
第3步：深度设计
- 边界条件分析
- 组合测试策略
- 状态转换覆盖
第4步：风险评估
- 高风险区域
- 建议测试深度
功能描述：[具体描述]
模式4：反向质疑模式
适用场景：AI输出后需要查漏补缺
以上是你生成的测试用例。现在请：
1. 假设挖掘
- 你在输出中做了哪些假设？
- 这些假设合理吗？
- 如果假设不成立会怎样？
2. 盲区检查
- 哪些场景你可能遗漏了？
- 哪些边界你没有覆盖？
- 并发、时序、资源竞争考虑了吗？
3. 改进建议
- 最需要补充的3个场景是什么？
- 从哪个方向迭代最有效？
模式5：多视角模式
适用场景：需要全面覆盖不同角度
请从以下三个视角分别分析这个功能：
【用户视角】
- 核心诉求：
- 操作路径：
- 痛点预测：
【开发视角】
- 技术实现风险：
- 边界条件：
- 异常处理：
【运维视角】
- 监控需求：
- 故障场景：
- 恢复方案：
功能描述：[具体描述]
模式6：对抗模式
适用场景：挑战AI的输出，逼出深层思考
我对你的输出有以下质疑：
1. [具体质疑点1]：你考虑过[特定场景]吗？
2. [具体质疑点2]：如果[极端情况]发生会怎样？
3. [具体质疑点3]：这个假设[具体假设]成立吗？
请针对每个质疑：
- 承认或反驳
- 补充你的分析
- 如果确实遗漏，补充测试场景
模式选择指南
| 测试目标 | 推荐模式 | 优势 | 局限 | 复杂度 |
|---|---|---|---|---|
| 快速生成用例 | 结构化输出 | 标准化、高效、易对比 | 深度不足、缺乏个性 | ★★ |
| 深入理解用户 | 角色扮演 | 贴近真实场景、发现UX问题 | 依赖角色设定准确性 | ★★★ |
| 复杂功能分析 | 分步引导 | 系统化、不遗漏深度 | 耗时长、需要迭代 | ★★★★ |
| 质量评审 | 反向质疑 | 查漏补缺、打破盲区 | 需要已有输出为基础 | ★★★ |
| 全面覆盖 | 多视角 | 多维度、无死角 | 输出量大、需筛选 | ★★★★ |
| 挑战假设 | 对抗 | 逼出深层思考、验证假设 | 需要专业对抗经验 | ★★★★★ |
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.
- 7d ago Changed 3e727b71b7c8
- 12d ago First seen · 283 lines · 119 tokens per session scan A fd92a7c1e9b2
qa-ai-prompt-strategy is a skill published in the GitHub repository Kokxi/qa-test-skills (27 stars, last pushed 9d ago), licensed MIT. It adds 119 tokens to every session and 3,111 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.
Other skills, from other repositories
code-review
Reviews Spec Kit code changes for positive and negative test coverage, regression evidence for bug fixes, and consistent repository terminology. Use when reviewing a diff or pull request. Do not use for implementing changes or posting GitHub review actions.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
octocode-benchmark
Use when planning, running, grading, or reporting the by-hand Octocode research benchmark — pairwise matchups (Octocode anchor vs one baseline: gh+RTK, gh+Headroom, or plain gh) over markdown questions, with a fresh isolated runner agent per (question, arm, pass), one blind judge per question grading two answers X/Y…
octocode-graph-eval
Use when you need a measurable keep/discard loop — goal→KPI, baseline vs target, held-out checks, eval suites, or don't-stop-till-done against a runnable sensor. Not for ordinary ship checks where 'tests passed' is enough.
plugin-test
A testing guide for Zhin.js plugins using Vitest, a JavaScript and TypeScript testing framework. It focuses on checking command and tool behavior, ordinary business logic, and the plugin package’s required structure.
modernize-test-starter
Modernize QUnit unit tests and OPA5 integration tests to the UI5 Test Starter concept. Use this skill when: The linter reports prefer-test-starter for .qunit.html or .qunit.js files Test HTML files use manual sap-ui-core.js bootstrapping instead of Test Starter's runTest.js/createSuite.js Test JS files use…