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-tech-selectiongit 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-tech-selection)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-tech-selection"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-tech-selection.svg" alt="Measured on agentmods" 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 | $0.00127 | $0.03077 |
| Opus 5 | $0.00063 | $0.01538 |
| Sonnet 5 | $0.00025 | $0.00615 |
| Haiku 4.5 | $0.00013 | $0.00308 |
Grade A, and why
qa-tech-selection 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 2d 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.
测试技术选型
核心原则
工具替换快，思维不过时——选型要基于业务需求，不是技术偏好。
选型框架
维度1：需求分析
需求收集：
├─ 业务需求
│ ├─ 测试类型：功能/性能/安全/兼容
│ ├─ 测试规模：用例数量/执行频率
│ ├─ 团队规模：人员数量/技能水平
│ └─ 预算限制：采购预算/维护成本
│
├─ 技术需求
│ ├─ 技术栈：语言/框架/协议
│ ├─ 集成需求：CI/CD/监控/报告
│ ├─ 扩展需求：并发/分布式/云化
│ └─ 维护需求：升级/扩展/迁移
│
└─ 约束条件
├─ 时间约束：上线时间
├─ 资源约束：人力/预算
├─ 技术约束：现有技术栈
└─ 合规约束：安全/隐私
维度2：方案评估
评估维度：
├─ 功能性
│ ├─ 功能覆盖：是否满足需求
│ ├─ 功能深度：功能完善程度
│ ├─ 扩展性：是否支持扩展
│ └─ 定制性：是否支持定制
│
├─ 易用性
│ ├─ 学习成本：上手难度
│ ├─ 使用体验：操作便捷性
│ ├─ 文档质量：文档完善程度
│ └─ 社区支持：社区活跃度
│
├─ 性能
│ ├─ 执行效率：执行速度
│ ├─ 资源消耗：CPU/内存/磁盘
│ ├─ 并发能力：支持并发数
│ └─ 稳定性：长期运行稳定性
│
├─ 成本
│ ├─ 采购成本：License费用
│ ├─ 实施成本：部署/集成成本
│ ├─ 维护成本：升级/维护成本
│ └─ 培训成本：人员培训成本
│
└─ 风险
├─ 技术风险：技术成熟度
├─ 供应商风险：供应商稳定性
├─ 迁移风险：迁移难度
└─ 锁定风险：厂商锁定
维度3：决策矩阵
决策矩阵：
| 方案 | 功能性 | 易用性 | 性能 | 成本 | 风险 | 总分 |
|---|---|---|---|---|---|---|
| 方案A | 9 | 8 | 7 | 6 | 7 | 37 |
| 方案B | 8 | 9 | 8 | 7 | 8 | 40 |
| 方案C | 7 | 7 | 9 | 8 | 6 | 37 |
权重：
- 功能性：30%
- 易用性：25%
- 性能：20%
- 成本：15%
- 风险：10%
常见选型场景
场景1：自动化框架选型
选项对比：
├─ Playwright
│ ├─ 优点：多浏览器、自动等待、调试友好
│ ├─ 缺点：社区相对较小
│ └─ 适用：现代Web应用、多浏览器测试
│
├─ Cypress
│ ├─ 优点：实时调试、自动重试、CI友好
│ ├─ 缺点：仅支持Chrome、iframe支持差
│ └─ 适用：单页应用、快速反馈
│
├─ Selenium
│ ├─ 优点：生态成熟、语言支持多、社区大
│ ├─ 缺点：配置复杂、调试困难
│ └─ 适用：传统Web应用、多语言团队
│
└─ 决策依据：
├─ 团队技术栈
├─ 应用架构
├─ 测试需求
└─ 维护成本
场景2：性能测试工具选型
选项对比：
├─ JMeter
│ ├─ 优点：功能全面、插件丰富、社区大
│ ├─ 缺点：界面复杂、资源消耗大
│ └─ 适用：复杂性能测试、协议测试
│
├─ Locust
│ ├─ 优点：代码化、分布式、轻量
│ ├─ 缺点：需要编程能力
│ └─ 适用：API性能测试、分布式测试
│
├─ k6
│ ├─ 优点：现代化、脚本化、CI友好
│ ├─ 缺点：社区相对较小
│ └─ 适用：现代应用、DevOps集成
│
└─ 决策依据：
├─ 测试类型
├─ 团队技能
├─ 集成需求
└─ 性能要求
场景3：测试管理平台选型
选项对比：
├─ 开源方案
│ ├─ TestLink：功能简单、免费
│ ├─ 飞书/钉钉：协作方便、集成度高
│ └─ 自研：完全定制、成本高
│
├─ 商业方案
│ ├─ 禅道：功能全面、中文友好
│ ├─ JIRA：生态丰富、扩展性强
│ └─ Zephyr：JIRA集成、测试专业
│
└─ 决策依据：
├─ 团队规模
├─ 功能需求
├─ 预算限制
└─ 集成需求
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.
- 2d ago Changed 55fc7603428a
- 8d ago First seen · 292 lines · 127 tokens per session scan A a659c4142bb2
qa-tech-selection is a skill published in the GitHub repository Kokxi/qa-test-skills (24 stars, last pushed 5d ago), licensed MIT. It adds 127 tokens to every session and 3,077 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
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…
octocode-graph-eval
Use when you need a measurable keep/discard loop — goal→KPI, baseline vs target, held-out checks, eval suites, or don't-stop-till-done against a runnable sensor. Not for ordinary ship checks where 'tests passed' is enough.
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.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
react-development
React 19+ with TypeScript — hooks, custom hooks, state management (useState/useReducer/useContext), React Query/SWR, Tailwind CSS, performance. Use when building React components, apps, or optimizing renders.