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 eiway112/prefab-interior-skills --skill skill-qa-testergit clone --depth 1 https://github.com/eiway112/prefab-interior-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/eiway112/prefab-interior-skills/skill-qa-tester)<a href="https://agentmods.dev/skills/eiway112/prefab-interior-skills/skill-qa-tester"><img src="https://agentmods.dev/badge/skills/eiway112/prefab-interior-skills/skill-qa-tester/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/eiway112/prefab-interior-skills/skill-qa-tester"><img src="https://agentmods.dev/badge/skills/eiway112/prefab-interior-skills/skill-qa-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00090 | $0.04431 |
| Opus 5 | $0.00045 | $0.02216 |
| Sonnet 5 | $0.00018 | $0.00886 |
| Haiku 4.5 | $0.00009 | $0.00443 |
Grade A, and why
skill-qa-tester 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 11d 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技能质量测试方法论
核心理念：以源文件为唯一真相源，逐行核验每一个事实声明。
适用技能类型
本方法论适用于以下类型的知识密集型技能：
| 类型 | 特征 | 测试重点 |
|---|---|---|
| 数据表格型 | 含大量数值、标准编号 | 每个数值和编号的行级核验 |
| 方法论型 | 教授思维框架 | 框架完整性、推理链正确性 |
| 审核工具型 | 检测其他内容的错误 | 错误检出率、分类准确性 |
| 模板输出型 | 按固定模板生成响应 | 模板格式合规性 |
五阶段测试流程
阶段一：全量读取
- 列出技能目录下所有文件
- 逐个读取全部源文件（不可跳读，不可摘要）
- 记录文件清单：文件名、行数、大小、最后修改日期
- 建立文件关系图：哪些文件互相引用、引用路径是否正确
阶段二：测试用例设计
设计原则：每种输出场景至少一个用例，每种边界条件至少一个用例。
2.1 覆盖矩阵
| 维度 | 必须覆盖 | 核验方法 |
|---|---|---|
| 输出模板 | 每种模板类型至少1个用例 | 对照SKILL.md中的模板定义 |
| 响应层级 | 每层至少1个用例（如适用） | 对照SKILL.md中的层级定义 |
| 跨技能路由 | 每条路由规则至少1个用例 | 对照路由规则定义 |
| 标准引用 | 高频标准+易混淆标准 | 核对编号、年份、名称 |
| 红线压力 | 至少2个对抗性用例 | 检查是否遵守红线规则 |
| 免责声明 | 每个用例均检查 | 逐句比对SKILL.md定义文本 |
2.2 测试用例模板
测试编号：T[N]
场景：[正常/边界/异常/对抗]
用户查询：[具体文本]
预期响应要点：
- [应包含的标准编号及数值]
- [应使用的输出模板]
- [应触发的路由规则]
核验锚点：[源文件名+行号，用于逐条验证]
2.3 对抗性测试设计
构造以下类型的查询来暴露技能薄弱环节：
| 对抗类型 | 查询设计思路 | 预期行为 |
|---|---|---|
| 诱导编造 | 条件不完整，诱导给出具体数值 | 应承认不确定并指明查阅路径 |
| 过时标准 | 查询已废止标准的最新版本 | 应提示新标准和替代关系 |
| 跨领域越界 | 问超出技能范围的问题 | 应识别并路由到正确技能 |
| 矛盾前提 | 查询中嵌入错误假设 | 应纠正错误假设后再回答 |
| 品牌诱导 | 询问"哪个品牌最好" | 应拒绝推荐品牌 |
阶段三：并行执行与逐项核验
3.1 执行方式
使用平台可用的并行执行能力启动独立测试用例：
- 每个子代理负责1-2个测试用例
- 子代理必须先读取全部源文件再模拟响应
- 模拟响应中的每个事实声明必须标注依据（文件+行号）
3.2 核验清单
对每个模拟响应逐项核验：
数据准确性
- 标准编号格式正确（GB/GB/T/JGJ/JC/T等）
- 标准年份正确（对照源文件行号）
- 标准名称完整准确
- 数值与源文件完全一致（含单位、精度）
- 边界符号正确（≥/>/≤/< 与源文件对应）
格式合规性
- 使用了正确的输出模板
- 模板结构完整（所有必填章节）
- 响应层级正确（Layer 1/2/3）
- 跨技能路由触发正确
红线合规性
- 未编造源文件中不存在的数据
- 未推荐具体品牌
- 不确定处加了限定语或查阅路径
- 免责提示文本与SKILL.md定义完全一致（逐句比对）
内部一致性
- 同一指标在不同文件中表述一致
- 标准编号年份在多处引用中一致
- 免责提示文本在所有文件中一致
- 示例文件中的内容与主表格一致
详细核验规则见 reference.md。
阶段四：修正与回归
4.1 精确修正
- 使用平台可用的精确编辑能力修改，一次只改一处
- 每次修正后搜索相关关键词验证修改结果
- 记录修正日志：修正前内容、修正后内容、依据、文件+行号
4.2 完整性扫描（修正后必做）
核心原则：修复N项时，必须验证修复是否覆盖了全部同类项，而非只验证已修复的N项。
每次修正后，立即执行以下完整性扫描：
同表/同节全量扫描：当修复涉及某个表格或章节中的某些行时，必须重新读取该表格/章节的全部行，确认所有行都遵循修正后的规则。逐行检查：
- 是否存在未被修复但存在同样问题的行？
- 修复后的模式是否在整个表格/章节内一致？
- 是否存在"相邻遗漏"（紧挨着已修复行的未修复行）？
What ships with it
3 files 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.
- 11d ago First seen · 312 lines · 90 tokens per session scan A d85bd461433a
skill-qa-tester is a skill published in the GitHub repository eiway112/prefab-interior-skills (4 stars, last pushed 9d ago), licensed MIT. It adds 90 tokens to every session and 4,431 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.