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 yunshu0909/yunshu_skillshub --skill prd-auto-test-loopgit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/prd-auto-test-loop)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/prd-auto-test-loop"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/prd-auto-test-loop/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/yunshu0909/yunshu_skillshub/prd-auto-test-loop"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/prd-auto-test-loop.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 | $0.00079 | $0.01359 |
| Opus 5 | $0.00039 | $0.00679 |
| Sonnet 5 | $0.00016 | $0.00272 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
prd-auto-test-loop 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 11d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD 自动化测试闭环
概览
使用此技能将发布测试固定为：主回归基线 + PRD 增量测试。
跨版本维护一套共享主回归测试。
每个 PRD 版本仅增加新增或变更相关用例。
将产物输出到 自动化测试/<version>/。
工作流
- 从 PRD 锁定范围。
- 提取版本目标、测试范围、非范围、验收标准。
- 若本次是增量变更，拒绝“整套重写测试”。
- 定义测试分层与边界。
- 将验收标准映射为
Unit / Integration / E2E。 - 读取
references/自动化测试封装指南.md的边界章节，标记A/H/A+H。
- 初始化版本测试目录。
- 读取
references/自动化测试封装指南.md的初始化命令与模板。 - 创建
自动化测试/<version>/，并生成TEST_PLAN.md、TEST_REPORT.md。
- 实现增量测试。
- 优先复用既有主回归用例。
- 仅新增 PRD 差异用例到
tests/。 - 保持断言确定性，避免脆弱 UI 选择器。
- 执行 AI 自测闭环。
- 固定顺序：
Unit -> Integration -> E2E。 - 失败时按根因修复并重跑（最多 3 轮）。
- 若被环境阻塞，明确记录阻塞项并停止宣称通过。
- 产出测试报告。
- 按模板填写命令、通过率、失败项、剩余风险。
- 输出发布门禁结论：
PASS或FAIL。
规则
- 不要每个 PRD 都从零重建整套测试。
- 必须同时维护“主回归套件 + 版本增量套件”。
- 每个版本必须绑定自己的
TEST_PLAN与TEST_REPORT。 - 必须给出可复现命令和结果摘要，禁止模糊结论。
- 不要声称覆盖全部质量风险，必须列出人工补测项。
自动化边界矩阵
适合自动化（建议 AI 覆盖）
- 功能正确性（状态流转、接口处理、校验规则）
- 回归路径（历史缺陷防回归）
- 确定性边界场景（空值、非法值、重复操作）
- 稳定冒烟流程（启动、关键导航、保存/提交）
- 可量化非功能指标（超时、错误率、崩溃率）
优先人工验证（建议人工兜底）
- 可用性与交互顺滑度
- 视觉质感与品牌一致性
- 业务策略合理性
- 开放式探索路径
- 产品取舍与发布优先级判断
验收标准标记法
A：可完全自动化H：仅人工验证A+H：自动化 + 人工联合验证
TEST_PLAN 模板
# TEST_PLAN（<version>）
## 1. 测试范围
- PRD：<path>
- 范围内：
- 非范围：
## 2. 完成门槛
1. 计划内用例：<x>/<x> 通过
2. P0 用例通过率：100%
3. 连续两轮稳定通过
4. 无阻断/严重缺陷遗留
## 3. 用例清单
### Unit
- UT-xx：
### Integration
- IT-xx：
### E2E
- E2E-xx：
## 4. 执行顺序
1. Unit
2. Integration
3. E2E
4. 自动修复循环（最多 3 轮）
## 5. 输出产物
- TEST_REPORT.md
- 命令执行结果摘要
TEST_REPORT 模板
# TEST_REPORT（<version>）
## 1. 结果摘要
- 日期：
- PRD：
- 结论：PASS | FAIL
## 2. 执行命令与结果
- <command>
- result:
## 3. 分层覆盖结果
- Unit：passed/total
- Integration：passed/total
- E2E：passed/total
## 4. 失败用例
- 用例 ID：
- 现象：
- 根因：
- 修复状态：
## 5. 剩余风险（人工补测）
- 风险点：
- 自动化无法完全覆盖原因：
## 6. 发布门禁
- 门禁检查状态：
- 最终决策：
版本目录初始化命令
在项目根目录执行：
version="V0.6"
base_dir="自动化测试/$version"
mkdir -p "$base_dir/tests/unit" "$base_dir/tests/integration" "$base_dir/tests/e2e"
cat > "$base_dir/TEST_PLAN.md" <<'TPL'
# TEST_PLAN（V0.6）
## 1. 测试范围
- PRD：
- 范围内：
- 非范围：
## 2. 完成门槛
1. 计划内用例全部通过
2. P0 用例通过率 100%
3. 连续两轮稳定通过
4. 无阻断/严重缺陷遗留
TPL
cat > "$base_dir/TEST_REPORT.md" <<'RPT'
# TEST_REPORT（V0.6）
## 1. 结果摘要
- 日期：
- 结论：
RPT
What ships with it
6 files 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.
- 11d ago First seen · 176 lines · 79 tokens per session scan A 2e1bca54dfb8
prd-auto-test-loop is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,359 once invoked, about $0.0004 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
axiom-testing
Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest. Covers unit tests, UI tests, async testing, test architecture.
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
test-automation
Execute Vitest and Playwright test suites with result collection and failure analysis.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
test-automation-expert
Comprehensive test automation specialist covering unit, integration, and E2E testing strategies. Expert in Jest, Vitest, Playwright, Cypress, pytest, and modern testing frameworks. Guides test pyramid design, coverage optimization, flaky test detection, and CI/CD integration. Activate on 'test strategy', 'unit tests'…
testing-patterns
Testing strategy: pyramid, AAA, mocks/fakes/stubs, flaky tests, coverage. Triggers: test, fixture, mock, stub, e2e, TDD, Playwright, Cypress, flaky, coverage, property-based.