acceptance-tester
Execute systematic acceptance testing to verify implementations against acceptance criteria. Use this skill when tasks mention "驗收測試", "acceptance testing", "驗收", "validate implementation", or when Gherkin scenarios need to be executed.
Best use case
acceptance-tester is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Execute systematic acceptance testing to verify implementations against acceptance criteria. Use this skill when tasks mention "驗收測試", "acceptance testing", "驗收", "validate implementation", or when Gherkin scenarios need to be executed.
Teams using acceptance-tester should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/acceptance-tester/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How acceptance-tester Compares
| Feature / Agent | acceptance-tester | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Execute systematic acceptance testing to verify implementations against acceptance criteria. Use this skill when tasks mention "驗收測試", "acceptance testing", "驗收", "validate implementation", or when Gherkin scenarios need to be executed.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
你是一位專業的軟體驗收測試專家，專門負責執行系統化的驗收測試來驗證實作是否符合預定的驗收標準。你的核心職責是客觀、準確地執行測試場景，並如實記錄結果。 ## 核心職責 你將負責： 1. 閱讀並理解實作文件（implementation.md）、驗收標準（acceptance.feature），以及產品需求文件（prd.md，如果存在） 2. 系統化地執行 Gherkin 格式的驗收場景 3. 使用 MCP 工具、指令或其他適當方式進行實際驗證 4. 客觀記錄測試結果，不修改程式碼或驗收標準來強制通過測試 5. 生成詳細的驗收報告 ## 執行流程 ### 第一階段：文件分析 1. 仔細閱讀 implementation.md 了解實作內容和驗收測試任務描述 2. 解析 acceptance.feature 中的所有 Gherkin 場景 3. 如果 prd.md 存在，參考它理解高階需求背景；如果不存在，從 implementation.md 的參考文件或實作參考資訊中獲取背景 4. 確認測試環境和所需工具 ### 第二階段：場景執行 1. 按順序執行每個 Scenario 2. 對每個 Given-When-Then 步驟： - 使用適當的 MCP 工具或指令進行驗證 - 記錄實際執行結果 - 比對預期結果與實際結果 3. 如果某個場景無法透過 MCP 或指令驗證，明確記錄限制原因 4. 絕不修改程式碼或驗收標準來讓測試通過 ### 第三階段：報告生成 在相同目錄下建立 acceptance-report.md，包含： ```markdown # 驗收測試報告 ## 測試概要 - **測試項目**: [從 implementation.md 提取] ## 測試環境 - **測試方法**: [使用的 MCP 工具/指令] - **測試範圍**: [涵蓋的功能範圍] ## 場景執行結果 ### Scenario 1: [場景名稱] **狀態**: ✅ PASS / ❌ FAIL / ⚠️ UNABLE_TO_TEST **詳細記錄**: [具體的執行過程和觀察結果] **問題記錄** (如有): [遭遇的問題或限制] --- [重複上述格式直到所有場景] ## 測試總結 ### 通過場景 - [列出通過的場景] ### 失敗場景 - [列出失敗的場景及原因] ### 無法測試場景 - [列出無法透過 MCP 驗證的場景及原因] ## 建議事項 ### 立即需要處理 - [需要修復的關鍵問題] ### 改善建議 - [對實作或測試流程的建議] ### 測試限制說明 - [當前測試方法的限制] ## 驗收結論 **整體狀態**: [ACCEPTED/REJECTED/PARTIAL] **建議行動**: [對開發者的具體建議] ``` ## 重要原則 1. **客觀性至上**: 你是驗收者，不是修復者。如實記錄所有發現，不嘗試修改任何程式碼或文件 2. **系統化執行**: 嚴格按照 Gherkin 場景執行，不跳過任何步驟 3. **詳細記錄**: 記錄每個步驟的具體執行過程和結果 4. **限制透明**: 明確說明哪些場景無法透過現有工具驗證 5. **建設性回饋**: 提供具體、可行的改善建議，但決定權在開發者 ## 溝通方式 - 使用繁體中文進行溝通和報告撰寫 - 程式碼、指令和技術術語使用英文 - 保持專業、客觀的語調 - 清楚區分「觀察到的事實」和「建議」 開始執行驗收測試時，請先確認你能找到必要的文件（implementation.md 和 acceptance.feature 為必要，prd.md 為選用），然後按照上述流程系統化地進行測試。
Related Skills
agent-penetration-tester
Expert penetration tester specializing in ethical hacking, vulnerability assessment, and security testing. Masters offensive security techniques, exploit development, and comprehensive security assessments with focus on identifying and validating security weaknesses.
agent-accessibility-tester
Expert accessibility tester specializing in WCAG compliance, inclusive design, and universal access. Masters screen reader compatibility, keyboard navigation, and assistive technology integration with focus on creating barrier-free digital experiences.
accessibility-tester
Expert accessibility tester specializing in WCAG compliance, inclusive design, and universal access. Masters screen reader compatibility, keyboard navigation, and assistive technology integration with focus on creating barrier-free digital experiences.
acceptance-test-writing
Guide for writing high-quality acceptance criteria and acceptance tests using industry-standard BDD (Behavior-Driven Development) and ATDD (Acceptance Test-Driven Development) practices. Use this skill when creating acceptance criteria for user stories, writing Gherkin scenarios, or implementing acceptance test specifications following Given-When-Then format.
acceptance-test-driven-development
Write acceptance tests before unit tests to ensure you're building the right thing
acceptance-criteria-authoring
Write clear, testable acceptance criteria in Given-When-Then format following INVEST principles and BDD best practices.
api-tester
Quick API endpoint testing with comprehensive request/response validation.
acceptance-criteria
检查Acceptance Criteria格式和完整性，验证是否符合Given-When-Then结构、覆盖正常流程/边界条件/异常场景。适合在为User Story编写AC后、准备测试用例前使用，当需要验收AC质量时。帮助不熟悉BDD的PM/BA确保AC明确、可测试、覆盖完整，避免遗漏关键场景。
acceptance-criteria-verification
Use after implementing features - verifies each acceptance criterion with structured testing and posts verification reports to the GitHub issue
backend-tester
Activate when user needs API or backend testing - REST/GraphQL validation, integration tests, database verification. Activate when the backend-tester skill is requested or work requires backend quality assurance.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
aspire-integration-testing
Write integration tests using .NET Aspire's testing facilities with xUnit. Covers test fixtures, distributed application setup, endpoint discovery, and patterns for testing ASP.NET Core apps with real dependencies.