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-team-coachinggit 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-team-coaching)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-team-coaching"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-team-coaching/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-team-coaching"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-team-coaching.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 | $0.00098 | $0.02295 |
| Opus 5 | $0.00049 | $0.01148 |
| Sonnet 5 | $0.00020 | $0.00459 |
| Haiku 4.5 | $0.00010 | $0.00230 |
Grade A, and why
qa-team-coaching 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 — 267 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发布检查清单和评审流程的培训材料。 这些是培训示例不是直接操作;请勿未经授权即变更团队流程或发布标准。 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。
团队赋能
核心原则
授人以渔——把经验做成checklist、把案例做成模板、把评判标准量化。
四种赋能方式
方式1:Checklist式
适用场景:
├─ 常见测试点整理
├─ 评审检查清单
├─ 发布检查清单
└─ 质量检查清单
Checklist设计原则:
├─ 完整性:覆盖所有关键点
├─ 可执行:每项可直接执行
├─ 可量化:有明确标准
└─ 可维护:定期更新
示例:
登录功能测试Checklist
├─ [ ] 正常登录验证
├─ [ ] 密码错误验证
├─ [ ] 用户名不存在验证
├─ [ ] 账号锁定验证
├─ [ ] 验证码验证
├─ [ ] 记住我功能验证
├─ [ ] 第三方登录验证
└─ [ ] 多设备登录验证
方式2:模板式
适用场景:
├─ 用例模板
├─ Bug报告模板
├─ 测试报告模板
└─ 测试计划模板
模板设计原则:
├─ 标准化:统一格式
├─ 完整性:包含必要字段
├─ 可填充:方便填写
└─ 可复用:可多次使用
示例:
测试用例模板
├─ 用例编号:TC_{模块缩写}_{功能缩写}_{序号}
├─ 用例标题:[动作]+[对象]+[条件]
├─ 前置条件:[测试前需要满足的条件]
├─ 测试步骤:[1. 2. 3. ...]
├─ 预期结果:[具体可验证的预期]
├─ 优先级:P0/P1/P2/P3
└─ 风险等级:高/中/低
方式3:Review式
适用场景:
├─ 用例评审
├─ Bug评审
├─ 代码评审
└─ 测试报告评审
Review设计原则:
├─ 结构化:有明确的评审维度
├─ 量化:有明确的评判标准
├─ 教学式:评审过程即学习过程
└─ 可改进:有明确的改进方向
示例:
用例评审维度
├─ 完整性:是否覆盖所有场景?
├─ 准确性:步骤/预期是否准确?
├─ 可执行:用例能否直接执行?
├─ 效率性:是否有冗余用例?
└─ 风险覆盖:高风险区域是否深测?
方式4:Pair式
适用场景:
├─ 结对测试
├─ 新人带教
├─ 复杂场景测试
└─ 探索测试
Pair设计原则:
├─ 角色分工:Driver/Navigator
├─ 实时交流:边做边讲
├─ 知识传递:经验分享
└─ 及时反馈:发现问题立即讨论
示例:
结对测试流程
├─ 准备:明确测试目标和分工
├─ 执行:Driver操作,Navigator观察
├─ 交流:实时讨论发现的问题
├─ 总结:回顾测试过程和收获
└─ 改进:制定改进措施
培训材料设计
新人培训大纲
第1周:基础认知
├─ 测试基础概念
├─ 公司测试流程
├─ 测试工具使用
└─ 常用Checklist
第2周:技能提升
├─ 用例设计方法
├─ 缺陷管理流程
├─ 测试执行技巧
└─ 常见问题处理
第3周:实战演练
├─ 参与实际项目
├─ 结对测试
├─ 用例评审
└─ Bug评审
第4周:独立工作
├─ 独立负责模块
├─ 定期Review
├─ 问题解答
└─ 能力评估
培训练习设计
练习类型:
├─ 案例分析:分析真实Bug案例
├─ 用例设计:设计测试用例
├─ Bug报告:编写Bug报告
└─ 场景模拟:模拟测试执行
练习设计原则:
├─ 真实性:基于真实场景
├─ 渐进性:从简单到复杂
├─ 可衡量:有明确评判标准
└─ 可反馈:及时给予反馈
能力评估体系
评估维度
评估维度:
├─ 测试设计能力:用例设计质量
├─ 测试执行能力:执行效率和质量
├─ 缺陷发现能力:Bug发现数量和质量
├─ 沟通协作能力:团队协作效果
└─ 问题解决能力:问题分析和解决
评估标准:
├─ 初级:能完成基础测试任务
├─ 中级:能独立负责模块测试
├─ 高级:能指导新人、优化流程
└─ 专家:能制定策略、推动改进
评估方法
评估方法:
├─ 日常观察:工作表现观察
├─ 产出评审:用例/Bug报告评审
├─ 能力测试:技能测试
├─ 360度评估:多维度反馈
└─ 成长记录:成长轨迹记录
应用场景
新入职的测试同学不知道怎么写测试用例 → Checklist式赋能:提供测试用例设计checklist,逐项check即可完成 → 模板式赋能:提供标准测试用例模板,填空即用 → Review式赋能:Review他的输出,给出改进建议 → Pair式赋能:Pair设计一个模块,示范思路
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 e932602d3f0c
- 12d ago First seen · 267 lines · 98 tokens per session scan A bede5e887819
qa-team-coaching is a skill published in the GitHub repository Kokxi/qa-test-skills (27 stars, last pushed 10d ago), licensed MIT. It adds 98 tokens to every session and 2,295 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.
Other skills, from other repositories
introspect
Capture corrections and lessons from this testing session into introspection.md at the feature demo path.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
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.
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.