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-test-leadershipgit 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-test-leadership)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-test-leadership"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-test-leadership/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-test-leadership"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-test-leadership.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 | $0.00105 | $0.02826 |
| Opus 5 | $0.00053 | $0.01413 |
| Sonnet 5 | $0.00021 | $0.00565 |
| Haiku 4.5 | $0.00011 | $0.00283 |
Grade A, and why
qa-test-leadership 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
测试领导力
核心原则
测试领导力——从技术专家到团队领袖的转变。
团队组织架构
组织模式
├─ 职能型团队
│ ├─ 结构:按技能分组(功能测试、自动化、性能)
│ ├─ 优点:专业深度、资源共享
│ ├─ 缺点:跨组协作、响应慢
│ └─ 适用:大型团队、稳定项目
│
├─ 项目型团队
│ ├─ 结构:按项目分组
│ ├─ 优点:响应快、责任清晰
│ ├─ 缺点:资源重复、专业深度不足
│ └─ 适用:项目制、快速迭代
│
├─ 矩阵型团队
│ ├─ 结构:职能+项目双重汇报
│ ├─ 优点:平衡专业和效率
│ ├─ 缺点:汇报复杂、权责不清
│ └─ 适用:中型团队、多项目
│
└─ 嵌入型团队
├─ 结构:测试嵌入开发团队
├─ 优点:协作紧密、响应快
├─ 缺点:专业传承弱、归属感低
└─ 适用:敏捷团队、DevOps
角色定义
├─ 测试负责人
│ ├─ 职责:团队管理、策略制定、资源协调
│ ├─ 技能:管理能力、沟通能力、业务理解
│ └─ 产出:测试策略、团队计划、质量报告
│
├─ 测试架构师
│ ├─ 职责:技术决策、架构设计、技术攻关
│ ├─ 技能:技术深度、架构能力、创新能力
│ └─ 产出:技术方案、框架设计、最佳实践
│
├─ 测试专家
│ ├─ 职责:复杂测试、质量把控、团队指导
│ ├─ 技能:测试深度、分析能力、指导能力
│ └─ 产出:测试方案、质量评估、经验分享
│
├─ 测试工程师
│ ├─ 职责:测试设计、测试执行、缺陷管理
│ ├─ 技能:测试设计、工具使用、沟通协作
│ └─ 产出:测试用例、缺陷报告、测试报告
│
└─ 测试开发工程师
├─ 职责:自动化开发、工具开发、框架维护
├─ 技能:开发能力、自动化能力、架构能力
└─ 产出:自动化脚本、测试工具、测试框架
绩效评估
评估维度
├─ 技术能力
│ ├─ 测试设计能力
│ ├─ 缺陷发现能力
│ ├─ 工具使用能力
│ └─ 技术深度
│
├─ 业务能力
│ ├─ 业务理解能力
│ ├─ 需求分析能力
│ ├─ 风险识别能力
│ └─ 质量把控能力
│
├─ 协作能力
│ ├─ 沟通能力
│ ├─ 团队协作
│ ├─ 问题解决
│ └─ 推动能力
│
└─ 成长能力
├─ 学习能力
├─ 创新能力
├─ 总结能力
└─ 影响力
评估方法
├─ KPI考核
│ ├─ 缺陷发现数
│ ├─ 测试覆盖率
│ ├─ 测试效率
│ └─ 质量指标
│
├─ 360度评估
│ ├─ 上级评估
│ ├─ 同事评估
│ ├─ 下级评估
│ └─ 自我评估
│
├─ OKR管理
│ ├─ 目标设定
│ ├─ 关键结果
│ ├─ 进度跟踪
│ └─ 结果评估
│
└─ 能力评估
├─ 技能测试
├─ 项目评审
├─ 知识分享
└─ 成长记录
评估周期
├─ 日常:1对1沟通(每周/双周)
├─ 月度:工作回顾、目标跟踪
├─ 季度:绩效评估、能力评估
└─ 年度:年度总结、晋升评估
招聘面试
面试流程
├─ 简历筛选
│ ├─ 关键词匹配
│ ├─ 经验匹配
│ └─ 技能匹配
│
├─ 电话面试
│ ├─ 基本情况
│ ├─ 技术基础
│ └─ 求职动机
│
├─ 技术面试
│ ├─ 测试知识
│ ├─ 技术深度
│ └─ 实战能力
│
├─ 综合面试
│ ├─ 沟通能力
│ ├─ 团队协作
│ └─ 文化匹配
│
└─ HR面试
├─ 薪资谈判
├─ 职业规划
└─ 背景调查
面试问题库
测试基础:
├─ 什么是测试金字塔?
├─ 如何设计测试用例?
├─ 如何进行需求分析?
└─ 如何进行缺陷管理?
技术深度:
├─ 如何设计自动化框架?
├─ 如何进行性能测试?
├─ 如何进行安全测试?
└─ 如何进行接口测试?
实战能力:
├─ 描述一个你发现的最难的Bug
├─ 描述一个你设计的最复杂的测试方案
├─ 描述一个你推动的改进
└─ 描述一个你解决的冲突
软技能:
├─ 如何与开发沟通?
├─ 如何管理时间?
├─ 如何学习新技术?
└─ 如何处理压力?
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 a4124c2310ea
- 12d ago First seen · 292 lines · 105 tokens per session scan A 933396db764f
qa-test-leadership is a skill published in the GitHub repository Kokxi/qa-test-skills (25 stars, last pushed 9d ago), licensed MIT. It adds 105 tokens to every session and 2,826 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
review-story
QA gate for a story — verdict PASS/CONCERNS/FAIL/WAIVED + lifecycle transition. Use when: review story, qa gate, qa-gate, /review-story.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
scaffold-dotnet-test-project
MUST USE when an existing .NET test project was excluded from a .slnf/CI solution filter, disappeared from .sln/.slnx discovery, or lost its production ProjectReference; also for requests to set up, create, reuse, add, register, include, or repair a test project. Handles "tests pass directly but CI discovers zero"…
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…
cy-execute-task
Implement and verify an existing CompozyOS spec task, then update its tracking. Excludes review remediation.