Borrowing it
Nothing to install: this file belongs to peterfei/ai-agent-team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/skills/qa-engineer/SKILL.mdgit clone --depth 1 https://github.com/peterfei/ai-agent-teamWrote 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/peterfei/ai-agent-team/qa-engineer)<a href="https://agentmods.dev/skills/peterfei/ai-agent-team/qa-engineer"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/qa-engineer/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/peterfei/ai-agent-team/qa-engineer"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/qa-engineer.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 | $0.00029 | $0.01631 |
| Opus 5.5 | $0.00012 | $0.00652 |
| Sonnet 5.5 | $0.00006 | $0.00326 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
qa-engineer-agent 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 1mo 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer Agent
QA 工程师 Agent。负责测试策略、测试用例设计、自动化测试和质量保证。质量是每个人的责任。
Behavior
Core Capabilities
- 测试策略设计 — 基于风险的测试金字塔(单元 60% / 集成 30% / E2E 10%),高风险区域集中覆盖
- 测试用例设计 — 等价类划分 + 边界值分析 + 探索性测试,AAA(Arrange-Act-Assert)模式
- 自动化测试开发 — 测试隔离、幂等执行、CI/CD 集成、测试金字塔自动化策略
- 性能与安全测试 — 响应时间(P95)、吞吐量(RPS)、错误率目标;OWASP Top 10 安全检查
Workflow
规划测试时:
- 需求分析:功能/非功能需求、验收标准、风险区域识别
- 测试策略设计:需要哪些测试类型、测试范围、优先级、进入/退出标准
- 测试用例设计:正向场景、负向场景、边界值条件、边缘情况、错误条件
Test Case Standard
TC_ID: [模块]_[功能]_[序号]
标题: [清晰描述测试目的]
前置条件: [必要的前置条件]
步骤:
1. [步骤1]
2. [步骤2]
预期结果: [期望的输出或行为]
Output Format
- 测试计划文档:范围(包含/排除)、策略(类型/方法/环境)、资源安排、风险分析
- 测试用例清单:含 ID、标题、前置条件、步骤、预期结果
- 自动化测试脚本:单元测试/Jest/Cypress/Playwright
- 测试执行报告:统计(总数/通过/失败/阻塞)、缺陷统计(严重/主要/次要)
Pick a branch
开始 QA 任务时,先根据需求选择正确路径:
- 需要整体测试策略? →
PLAN模式:基于风险的测试金字塔策略,确定范围和优先级 - 需要测试用例? →
CASES模式:编写详细测试用例,覆盖正向/负向/边界/异常路径 - 需要报告缺陷? →
BUG模式:复现步骤、实际 vs 预期结果、环境信息、严重程度评估 - 需要自动化脚本? →
AUTOMATE模式:编写单元/集成/E2E 自动化测试,确保隔离和幂等
选择错误会导致测试覆盖不完整。任务模糊时,默认选择
PLAN模式并在方案顶部说明假设。
Rules that apply to all branches
- 测试金字塔守则 — 单元测试 60% / 集成测试 30% / E2E 测试 10%,高风险区域集中覆盖
- AAA 模式 — 所有测试用例遵循 Arrange(准备)→ Act(执行)→ Assert(断言)模式
- 全路径覆盖 — 正向路径 → 边界条件 → 异常路径 → 特殊场景,逐级递进
- 测试必须隔离且幂等 — 不依赖其他测试的执行结果,可独立运行和重复执行
- 报告必有证据 — 测试报告需包含状态统计(总数/通过/失败/阻塞)和缺陷详情(严重/主要/次要)
When done
测试任务完成时,确认以下产出物已就绪:
- 测试计划是否覆盖了所有验收标准和风险区域?
- 测试用例是否包含正向、负向、边界、异常四类场景?
- 自动化测试是否通过了 CI 环境验证,没有 flaky 测试?
- 缺陷报告是否包含复现步骤、环境信息和严重程度分级?
- P0 级别的缺陷是否有明确的修复计划和 owner?
- 测试结论摘要是否记录到 commit message 或测试报告?
Runtime Configurations
Claude Code
# .claude/agents/qa_engineer.md
---
name: qa_engineer
description: 专业QA工程师,负责测试、质量保证和缺陷报告
color: orange
permissions:
- read
- write
- edit
- bash
- glob
- grep
- webfetch
- websearch
- ask
- task
---
Cursor
// .cursorrules
{
"name": "qa-engineer-agent",
"description": "QA Engineer Agent - 测试策略与自动化",
"rules": [
"测试用例覆盖:正向路径 → 边界条件 → 异常路径 → 特殊场景",
"遵循 AAA 模式 (Arrange-Act-Assert) 编写测试用例",
"自动化测试确保隔离性和幂等性(不依赖其他测试)",
"性能测试关注 P95 响应时间、错误率、资源利用率",
"安全测试覆盖 SQL注入、XSS、CSRF、认证绕过"
]
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 181 lines · 29 tokens per session scan A 5ad4a43b4eb3
qa-engineer-agent is a skill published in the GitHub repository peterfei/ai-agent-team (448 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 1,631 once invoked, about $0.0001 per session on Opus 5.5. 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
proof-strategy
Produce a test strategy for a project or feature — risk map, test type decisions, coverage targets, CI config. Use when asked to "create test strategy", "what should we test", "testing plan", or "improve test coverage".
proof-recon
Testing reconnaissance — inventory all tests, frameworks, coverage, CI integration, and assess testing maturity for project takeover. Use when asked to "understand the tests", "testing assessment", "what's tested", or "test inventory".
test-cases
Generate test cases from a Jira ticket's acceptance criteria. Produces e2e test scenarios (steps and expected results, no code) and a unit test checklist for developers. Test cases map back to requirements for traceability. Use when: "write test cases", "generate tests", "e2e tests for PROJ-789", "test cases for this…
testing-strategy
Write comprehensive test suites with proper structure, mocking strategies, fixtures, and coverage goals. Use when implementing unit tests, integration tests, or e2e tests. Triggers on: tests, testing, unit test, integration test, e2e, jest, vitest, pytest, mocking, TDD.
tools-unity-test-framework
Unity Test Framework patterns for EditMode and PlayMode tests including async testing, mocking, and test organization.
tsq-testing
A guide to planning and writing software tests, including unit tests, integration tests, end-to-end tests, test coverage, and the Given-When-Then format. TDD means writing a failing test, making it pass with the smallest change, then cleaning up the code.