qa-expert by daymade/claude-code-skills
npx skills add https://github.com/daymade/claude-code-skills --skill qa-expert运用来自 Google 测试标准和 OWASP 安全最佳实践的成熟方法论,为任何软件项目建立世界级的 QA 测试流程。
在以下情况触发此技能:
一键初始化:
python scripts/init_qa_project.py <project-name> [output-directory]
创建内容:
tests/docs/、tests/e2e/、tests/fixtures/)TEST-EXECUTION-TRACKING.csv、)广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
BUG-TRACKING-TEMPLATE.csvBASELINE-METRICS.md、WEEKLY-PROGRESS-REPORT.md)对于自主执行(推荐):参见 references/master_qa_prompt.md - 单次复制粘贴命令即可实现 100 倍加速。
使用所有模板初始化完整的 QA 基础设施:
python scripts/init_qa_project.py <project-name> [output-directory]
创建目录结构、跟踪 CSV 文件、文档模板以及用于自主执行的主提示词。
使用时机:从零开始 QA 或迁移到结构化 QA 流程时。
遵循 AAA 模式(Arrange-Act-Assert)编写标准化、可复现的测试用例:
assets/templates/TEST-CASE-TEMPLATE.md测试用例格式:TC-[类别]-[编号](例如,TC-CLI-001、TC-WEB-042、TC-SEC-007)
参考:查看 references/google_testing_standards.md 获取完整的 AAA 模式指南和覆盖率阈值。
基本事实原则(关键):
02-CLI-TEST-CASES.md)= 权威来源,用于定义测试步骤references/ground_truth_principle.md 了解如何防止文档与 CSV 文件同步问题手动执行:
02-CLI-TEST-CASES.md)中读取测试用例 ← 始终从这里开始TEST-EXECUTION-TRACKING.csv(切勿批量更新)BUG-TRACKING-TEMPLATE.csv 中提交缺陷报告自主执行(推荐):
references/master_qa_prompt.md 复制主提示词创新点:相比手动执行快 100 倍 + 跟踪零人为错误 + 自动恢复能力。
使用适当的严重性分类提交缺陷报告:
必填字段:
严重性分类:
参考:查看 BUG-TRACKING-TEMPLATE.csv 获取包含示例的完整模板。
计算全面的 QA 指标和质量门状态:
python scripts/calculate_metrics.py <path/to/TEST-EXECUTION-TRACKING.csv>
指标仪表板包含:
质量门(所有必须通过才能发布):
| 门 | 目标 | 是否阻塞 |
|---|---|---|
| 测试执行 | 100% | 是 |
| 通过率 | ≥80% | 是 |
| P0 缺陷 | 0 | 是 |
| P1 缺陷 | ≤5 | 是 |
| 代码覆盖率 | ≥80% | 是 |
| 安全性 | 90% OWASP | 是 |
为利益相关者生成 QA 报告:
每日摘要(每日结束时):
每周报告(每周五):
WEEKLY-PROGRESS-REPORT.md(由初始化脚本创建)BASELINE-METRICS.md参考:查看 references/llm_prompts_library.md 获取 30 多个即用型报告提示词。
实施 OWASP Top 10 安全测试:
覆盖目标:
目标:90% OWASP 覆盖率(缓解 9/10 的威胁)。
每个安全测试都遵循 AAA 模式,并记录具体的攻击向量。
对于加入项目的新 QA 工程师,请完成 5 小时入职指南:
阅读:references/day1_onboarding.md
时间线:
检查点:到第一天结束时,环境运行正常,第一个测试已执行,为第 1 周做好准备。
使用单一主提示词启用 LLM 驱动的自主 QA 测试:
阅读:references/master_qa_prompt.md
功能:
优势:
用法:复制主提示词,粘贴到 LLM,让它自主运行 5 周。
从捆绑的参考资料中获取详细指南:
references/day1_onboarding.md - 新 QA 工程师的 5 小时入职指南references/master_qa_prompt.md - 用于自主 LLM 执行的单一命令(100 倍加速)references/llm_prompts_library.md - 30 多个用于特定 QA 任务的即用型提示词references/google_testing_standards.md - AAA 模式、覆盖率阈值、快速失败验证references/ground_truth_principle.md - 防止文档/CSV 同步问题(对测试套件完整性至关重要)测试用例模板和缺陷报告格式:
assets/templates/TEST-CASE-TEMPLATE.md - 包含 CLI 和安全示例的完整模板用于 QA 基础设施的自动化脚本:
scripts/init_qa_project.py - 初始化 QA 基础设施(一键设置)scripts/calculate_metrics.py - 生成质量指标仪表板1. python scripts/init_qa_project.py my-app ./
2. 填写 BASELINE-METRICS.md(记录当前状态)
3. 使用 assets/templates/TEST-CASE-TEMPLATE.md 编写测试用例
4. 从 references/master_qa_prompt.md 复制主提示词
5. 粘贴到 LLM → 自主执行开始
1. 阅读 references/master_qa_prompt.md
2. 复制单一主提示词(一段)
3. 粘贴到 LLM 对话
4. LLM 在 5 周内执行所有 342 个测试用例
5. LLM 自动更新跟踪 CSV 文件
6. LLM 自动生成每周报告
1. 阅读 references/google_testing_standards.md(OWASP 部分)
2. 为每个 OWASP 威胁编写 TC-SEC-XXX 测试用例
3. 目标 90% 覆盖率(9/10 威胁)
4. 在测试用例中记录缓解措施
1. 确保所有模板已填写
2. 验证 BASELINE-METRICS.md 完整
3. 打包 tests/docs/ 文件夹
4. 包含 references/master_qa_prompt.md 用于自主执行
5. QA 团队可以立即开始(第 1 天入职 → 5 周测试)
当满足以下条件时,此技能有效:
每周安装数
320
仓库
GitHub 星标数
708
首次出现
Jan 21, 2026
安全审计
安装于
opencode272
codex264
gemini-cli261
cursor256
github-copilot246
claude-code234
Establish world-class QA testing processes for any software project using proven methodologies from Google Testing Standards and OWASP security best practices.
Trigger this skill when:
One-command initialization :
python scripts/init_qa_project.py <project-name> [output-directory]
What gets created :
tests/docs/, tests/e2e/, tests/fixtures/)TEST-EXECUTION-TRACKING.csv, BUG-TRACKING-TEMPLATE.csv)BASELINE-METRICS.md, WEEKLY-PROGRESS-REPORT.md)For autonomous execution (recommended): See references/master_qa_prompt.md - single copy-paste command for 100x speedup.
Initialize complete QA infrastructure with all templates:
python scripts/init_qa_project.py <project-name> [output-directory]
Creates directory structure, tracking CSVs, documentation templates, and master prompt for autonomous execution.
Use when : Starting QA from scratch or migrating to structured QA process.
Write standardized, reproducible test cases following AAA pattern (Arrange-Act-Assert):
assets/templates/TEST-CASE-TEMPLATE.mdTest case format : TC-[CATEGORY]-[NUMBER] (e.g., TC-CLI-001, TC-WEB-042, TC-SEC-007)
Reference : See references/google_testing_standards.md for complete AAA pattern guidelines and coverage thresholds.
Ground Truth Principle (critical):
02-CLI-TEST-CASES.md) = authoritative source for test stepsreferences/ground_truth_principle.md for preventing doc/CSV sync issuesManual execution :
02-CLI-TEST-CASES.md) ← always start hereTEST-EXECUTION-TRACKING.csv immediately after EACH test (never batch)BUG-TRACKING-TEMPLATE.csv if test failsAutonomous execution (recommended):
references/master_qa_prompt.mdInnovation : 100x faster vs manual + zero human error in tracking + auto-resume capability.
File bugs with proper severity classification:
Required fields :
Severity classification :
Reference : See BUG-TRACKING-TEMPLATE.csv for complete template with examples.
Calculate comprehensive QA metrics and quality gates status:
python scripts/calculate_metrics.py <path/to/TEST-EXECUTION-TRACKING.csv>
Metrics dashboard includes :
Quality gates (all must pass for release):
| Gate | Target | Blocker |
|---|---|---|
| Test Execution | 100% | Yes |
| Pass Rate | ≥80% | Yes |
| P0 Bugs | 0 | Yes |
| P1 Bugs | ≤5 | Yes |
| Code Coverage | ≥80% | Yes |
| Security | 90% OWASP | Yes |
Generate QA reports for stakeholders:
Daily summary (end-of-day):
Weekly report (every Friday):
WEEKLY-PROGRESS-REPORT.md (created by init script)BASELINE-METRICS.mdReference : See references/llm_prompts_library.md for 30+ ready-to-use reporting prompts.
Implement OWASP Top 10 security testing:
Coverage targets :
Target : 90% OWASP coverage (9/10 threats mitigated).
Each security test follows AAA pattern with specific attack vectors documented.
For new QA engineers joining a project, complete 5-hour onboarding guide:
Read : references/day1_onboarding.md
Timeline :
Checkpoint : By end of Day 1, environment running, first test executed, ready for Week 1.
Enable LLM-driven autonomous QA testing with single master prompt:
Read : references/master_qa_prompt.md
Features :
Benefits :
Usage : Copy master prompt, paste to LLM, let it run autonomously for 5 weeks.
Access detailed guidelines from bundled references:
references/day1_onboarding.md - 5-hour onboarding guide for new QA engineersreferences/master_qa_prompt.md - Single command for autonomous LLM execution (100x speedup)references/llm_prompts_library.md - 30+ ready-to-use prompts for specific QA tasksreferences/google_testing_standards.md - AAA pattern, coverage thresholds, fail-fast validationreferences/ground_truth_principle.md - Preventing doc/CSV sync issues (critical for test suite integrity)Test case templates and bug report formats:
assets/templates/TEST-CASE-TEMPLATE.md - Complete template with CLI and security examplesAutomation scripts for QA infrastructure:
scripts/init_qa_project.py - Initialize QA infrastructure (one command setup)scripts/calculate_metrics.py - Generate quality metrics dashboard1. python scripts/init_qa_project.py my-app ./
2. Fill in BASELINE-METRICS.md (document current state)
3. Write test cases using assets/templates/TEST-CASE-TEMPLATE.md
4. Copy master prompt from references/master_qa_prompt.md
5. Paste to LLM → autonomous execution begins
1. Read references/master_qa_prompt.md
2. Copy the single master prompt (one paragraph)
3. Paste to LLM conversation
4. LLM executes all 342 test cases over 5 weeks
5. LLM updates tracking CSVs automatically
6. LLM generates weekly reports automatically
1. Read references/google_testing_standards.md (OWASP section)
2. Write TC-SEC-XXX test cases for each OWASP threat
3. Target 90% coverage (9/10 threats)
4. Document mitigations in test cases
1. Ensure all templates populated
2. Verify BASELINE-METRICS.md complete
3. Package tests/docs/ folder
4. Include references/master_qa_prompt.md for autonomous execution
5. QA team can start immediately (Day 1 onboarding → 5 weeks testing)
This skill is effective when:
Weekly Installs
320
Repository
GitHub Stars
708
First Seen
Jan 21, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode272
codex264
gemini-cli261
cursor256
github-copilot246
claude-code234
通过 LiteLLM 代理让 Claude Code 对接 GitHub Copilot 运行 | 高级变通方案指南
22,200 周安装
Google Ads Manager 技能:广告系列管理、关键词研究、出价优化与效果分析
311 周安装
Telegram机器人开发教程:构建AI助手、通知系统与群组自动化工具
311 周安装
AI图像生成提示词优化指南:DALL-E、Midjourney、Stable Diffusion提示工程技巧
311 周安装
AI协作头脑风暴工具 - 将想法转化为完整设计规范,支持代码模板与项目管理
311 周安装
解决 Docker 沙盒 npm 安装崩溃:sandbox-npm-install 技能详解与使用指南
311 周安装
网页设计方法论:生产级HTML/CSS构建模式与BEM命名规范
311 周安装