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-expert-reviewgit 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-expert-review)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-expert-review"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-expert-review/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-expert-review"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-expert-review.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 | $0.00116 | $0.02647 |
| Opus 5 | $0.00058 | $0.01324 |
| Sonnet 5 | $0.00023 | $0.00529 |
| Haiku 4.5 | $0.00012 | $0.00265 |
Grade A, and why
qa-expert-review 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 6d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
专家评审与元学习
核心原则
专家评审不是挑错，而是建立"AI生成→专家校验→持续优化"的正向循环。
评审流程
第1步：抽样策略
抽样方法：
├─ 随机抽样：10-20%的用例
├─ 分层抽样：P0用例100%覆盖，P1抽样50%，P2抽样20%
├─ 风险抽样：高风险用例100%覆盖
└─ 新功能抽样：新功能用例100%覆盖
抽样公式：
总用例数 < 50 → 全量评审
总用例数 50-200 → 20%抽样
总用例数 > 200 → 10%抽样 + P0全量
第2步：评审维度
| 维度 | 检查点 | 权重 |
|---|---|---|
| 完整性 | 是否覆盖所有需求点？ | 30% |
| 准确性 | 测试步骤和预期结果是否正确？ | 25% |
| 可执行性 | 步骤是否清晰可执行？ | 20% |
| 风险覆盖 | 高风险区域是否深测？ | 15% |
| 规范性 | 格式是否符合标准？ | 10% |
第3步：校正标记
校正标记格式：
├─ [C-001] 问题类型：描述问题
├─ [C-002] 问题类型：描述问题
└─ ...
问题类型：
├─ MISSING：缺失场景
├─ WRONG：步骤/预期错误
├─ VAGUE：描述模糊
├─ REDUNDANT：冗余用例
├─ RISK：风险覆盖不足
└─ FORMAT：格式不规范
第4步：输出评审报告
# 专家评审报告
## 评审摘要
- 评审ID：REV-XXXX
- 评审日期：YYYY-MM-DD
- 评审专家：[姓名]
- 用例总数：XX条
- 抽样数量：XX条（抽样比例XX%）
## 评审结果
| 维度 | 评分 | 问题数 |
|------|------|--------|
| 完整性 | X/10 | X个 |
| 准确性 | X/10 | X个 |
| 可执行性 | X/10 | X个 |
| 风险覆盖 | X/10 | X个 |
| 规范性 | X/10 | X个 |
| 综合评分 | X/10 | - |
## 问题清单
| 用例编号 | 问题类型 | 问题描述 | 校正建议 |
|---------|---------|---------|---------|
| TC_XXX_001 | MISSING | 缺少并发场景 | 补充并发测试用例 |
| TC_XXX_002 | VAGUE | 步骤描述模糊 | 明确操作步骤 |
## 学习要点
1. 高频问题：[问题模式]
2. 改进方向：[具体建议]
3. Prompt优化：[优化建议]
## 元学习建议
- 更新checklist：[新增检查项]
- 优化prompt：[提示词调整]
- 补充技能：[需要增强的技能]
评审维度速查
各维度典型问题速查
| 维度 | 常见问题现象 | 重点关注 | 通过标准 |
|---|---|---|---|
| 完整性 | 缺少某个需求点/场景 | 需求追溯ID是否全部覆盖 | 每个需求点≥1条用例 |
| 准确性 | 预期结果与实际不符 | 业务规则是否正确应用 | 预期结果=需求定义 |
| 可执行性 | 步骤模糊/依赖不明确 | 新人能否按步骤执行 | 按步骤可复现 |
| 风险覆盖 | 高风险区域用例不够深 | 资金/安全/并发是否深测 | 高风险区域≥3条用例 |
| 规范性 | 格式不统一/字段缺失 | 是否使用标准模板 | 模板字段完整率100% |
常见问题严重度判定
| 问题类型 | 严重 | 一般 | 轻微 |
|---|---|---|---|
| MISSING | 核心功能缺失 | 非核心功能缺失 | 边缘场景缺失 |
| WRONG | 预期结果方向错误 | 步骤顺序错误 | 步骤表述不精确 |
| VAGUE | 完全无法执行 | 需少量猜测 | 措辞可优化 |
| RISK | 资金/安全未覆盖 | 非功能未覆盖 | 兼容性/体验未覆盖 |
| REDUNDANT | 完全重复且P0 | 场景重叠 | 边界略有重叠 |
| FORMAT | 完全无格式 | 部分字段缺失 | 格式可微调 |
元学习机制
校正数据收集
收集内容：
├─ 问题类型分布
├─ 高频问题模式
├─ 专家校正建议
├─ 用例质量趋势
└─ 改进效果跟踪
存储格式：
{
"review_id": "REV-001",
"date": "2024-01-01",
"issues": [
{
"type": "MISSING",
"count": 5,
"pattern": "缺少并发场景",
"correction": "补充并发测试"
}
],
"learning_points": [...]
}
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.
- 6d ago Changed 63042c6c2f6e
- 11d ago First seen · 262 lines · 116 tokens per session scan A a0d855a8a4fb
qa-expert-review is a skill published in the GitHub repository Kokxi/qa-test-skills (25 stars, last pushed 9d ago), licensed MIT. It adds 116 tokens to every session and 2,647 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
dotnet-best-practices
Ensure .NET/C# code follows maintainable, modern best practices. Use when reviewing or improving C# code, solution structure, async patterns, dependency injection, or testability.
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.
quality-gate
Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, and test updates. Use when running quality checks before a PR.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
plugin-quality
A review guide for checking Zhin.js plugins before release. It covers plugin structure, feature declarations, resource cleanup, message sending, and security.
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.