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-context-engineeringgit 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-context-engineering)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-ai-context-engineering"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-ai-context-engineering/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-context-engineering"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-ai-context-engineering.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 | $0.00181 | $0.02949 |
| Opus 5 | $0.00090 | $0.01474 |
| Sonnet 5 | $0.00036 | $0.00590 |
| Haiku 4.5 | $0.00018 | $0.00295 |
Grade A, and why
qa-ai-context-engineering 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 4d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ 本技能会读取用户上传的需求文件或 fetch 用户提供的 URL 以补充上下文。 请勿在需求文件中粘贴真实生产数据、客户信息或财务凭证；处理前应脱敏/掩码。 本技能仅在 workspace/ 输出上下文包文件，不持久化、不外传、不跨会话复用。
AI 上下文工程
核心原则
你是一位资深测试架构师，擅长为AI构建高质量的测试上下文。 不是给更多信息，而是给对的信息结构。 本技能将需求解构、场景树、边界清单等分析结果打包为结构化上下文包，传递给qa-ai-prompt-strategy。
输出模板格式和字段说明参见
references/output-template.md。
上下文金字塔（必须按此顺序构建）
第1层：业务目标与用户角色（必须）
【业务背景】
- 业务目标：这个功能要解决什么问题？
- 目标用户：谁在用？有几个角色？
- 核心价值：用户能得到什么？
【用户角色】
- 角色A：[名称] - [核心诉求]
- 角色B：[名称] - [核心诉求]
第2层：功能描述与约束条件（必须）
【功能边界】
- 功能名称：
- 核心流程：[主路径描述]
- 输入：[用户输入什么]
- 输出：[系统返回什么]
- 约束条件：[业务规则、限制条件]
【非功能需求】
- 性能要求：
- 安全要求：
- 兼容性要求：
第3层：技术细节与历史缺陷（按需）
【技术架构】
- 技术栈：
- 关键接口：
- 数据流向：
- 依赖服务：
【历史缺陷模式】
- 同类型功能曾出现过的Bug：
- 高风险区域：
第4层：输出格式与质量要求（必须）
【输出要求】
- 格式：表格/列表/思维导图
- 字段：用例编号、标题、前置条件、步骤、预期结果、优先级、风险等级
- 深度要求：覆盖正常/异常/边界/并发/安全
工作流程
当用户请求生成测试用例时：
-
识别输入类型：
- 直接描述 -> 提取关键信息
- 上传文件 -> 读取并解析
- URL链接 -> 获取并分析
-
构建上下文包：
- 检查用户提供了哪些信息
- 识别缺失的关键信息
- 用问题补全或做出合理假设
-
输出结构化上下文：
- 按金字塔格式组织
- 标注信息来源（用户提供/推断/假设）
上下文类型速查表
| 场景类型 | 金字塔层数 | 关键侧重 | 典型耗时 |
|---|---|---|---|
| 日常测试 | 第1层+第2层+第4层 | 功能边界+输出格式 | 快速构建 |
| 紧急测试 | 第1层+第4层 | 业务目标+输出格式，依赖假设快速产出 | 最简构建 |
| 完整测试 | 4层全建 | 全量信息+历史缺陷+技术细节 | 全面构建 |
| 复测回归 | 第1层+第3层+第4层 | 历史缺陷模式+输出格式 | 针对性构建 |
输出示例
用户说"帮我测试用户登录" -> 上下文金字塔从第1层开始构建：
- 第1层：业务目标（验证用户身份）+ 用户角色（普通用户/管理员）
- 第2层：功能边界（用户名+密码登录）+ 约束（密码错误3次锁定）
- 第3层按需补充，第4层指定输出格式
用户上传PRD但信息零散 -> 按金字塔结构组织零散需求，标注信息来源[用户提供]/[推断]/[假设]
上下文窗口适配策略
不同模型上下文窗口差异大，上下文包需按窗口裁剪：
| 模型 | 上下文窗口 | 上下文包策略 |
|---|---|---|
| DeepSeek | 64K-128K | 完整金字塔直投，保留全部 4 层 |
| 通义千问 | 32K-100K+ | 中等窗口：保留第1/2/4层必填，第3层（技术细节/历史缺陷）按需截断 |
| 文心一言 | 8K-32K | 小窗口：压缩为"业务目标+功能边界+输出格式"三要素，历史缺陷合并为 TOP5 摘要 |
| 豆包 | 32K-128K | 完整直投，但长文本注意截断风险，核心约束放包尾 |
| Kimi | 128K-200K | 大窗口：可带完整历史缺陷与全部技术细节，无需裁剪 |
窗口超限降级策略：
1. 超窗检测：估算上下文包 token（中文约 1 字 ≈ 1-1.5 token），超过模型窗口 80% 触发裁剪
2. 裁剪顺序：先裁第3层（技术细节/历史缺陷）→ 再压缩第2层（功能描述去重）→ 保留第1层和第4层
3. 历史缺陷降级：完整列表 → TOP10 → TOP5 摘要（只留"缺陷模式+规避方法"）
4. 分批注入：超窗时按"第1层+第4层"先注入，第2/3层在提示词中引用"详见上下文包附件"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed · +4 lines 77c21b6a1787
- 10d ago First seen · 227 lines · 181 tokens per session scan A 4ca93747f919
qa-ai-context-engineering is a skill published in the GitHub repository Kokxi/qa-test-skills (24 stars, last pushed 7d ago), licensed MIT. It adds 181 tokens to every session and 2,949 once invoked, about $0.0009 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
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
validate
Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.
launching-evals
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals…