用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/a5c-ai/babysitter --skill uat-test-generator命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)
Atlas turns your STATED NEED into a real systems atlas by SCANNING your actual sources (Azure via `az`, git repos, local dirs) and process/data mining them, THEN enriching against the Atlas knowledge graph. Use this skill when asked to inventory/map your real systems, scan your cloud + repos + directories, mine the real processes or data they contain, or collect their real constraints/gotchas. (atlas, scan my systems, inventory our azure account, map my repos, real systems atlas, process mining, data mining, collect nuances, system discovery)
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
正在显示 SKILL.md
基于 SOC 职业分类
| name | uat-test-generator |
| description | Generate UAT test cases from requirements and acceptance criteria with traceability |
| allowed-tools | ["Read","Write","Glob","Grep","Bash"] |
| metadata | {"specialization":"business-analysis","domain":"business","id":"SK-012","category":"Testing"} |
| graph | {"domains":["domain:business-intelligence"],"specializations":["specialization:strategic-consulting"],"skillAreas":["skill-area:quality-management","skill-area:requirements-engineering","skill-area:business-analysis"],"workflows":["workflow:market-analysis"],"roles":["role:quality-analyst","role:business-analyst"]} |
The UAT Test Case Generator skill provides specialized capabilities for generating User Acceptance Testing test cases from requirements and acceptance criteria. This skill enables systematic test case development, test data specification, traceability maintenance, and export to test management tools.
Generate UAT test cases from these acceptance criteria:
[Acceptance criteria in Given-When-Then format]
Include positive and negative scenarios.
Create end-to-end test scenarios for:
[User story or feature description]
Generate complete user journey tests.
Define test data requirements for these test cases:
[Test case list]
Include data setup, dependencies, and sample values.
Calculate test coverage for:
Requirements: [Requirements list]
Test Cases: [Test case list]
Identify coverage gaps and missing tests.
This skill integrates with the following business analysis processes:
Test Case ID: TC-XXX
Title: [Descriptive test title]
Requirement ID: REQ-XXX
Priority: High/Medium/Low
Preconditions:
- [Precondition 1]
- [Precondition 2]
Test Steps:
| Step | Action | Expected Result |
|------|--------|-----------------|
| 1 | [Action] | [Expected] |
| 2 | [Action] | [Expected] |
Test Data:
- [Data item 1]: [Value]
- [Data item 2]: [Value]
Postconditions:
- [State after test]
| GWT Element | Test Case Element |
|---|---|
| Given | Preconditions |
| When | Test Steps (Actions) |
| Then | Expected Results |
| And | Additional steps or conditions |
| Type | Purpose | Examples |
|---|---|---|
| Positive | Verify correct behavior | Valid input, happy path |
| Negative | Verify error handling | Invalid input, edge cases |
| Boundary | Test limits | Min/max values, empty inputs |
| Integration | End-to-end flow | Complete user journeys |
| Regression | Verify unchanged behavior | Existing functionality |
Defect ID: DEF-XXX
Title: [Brief description]
Test Case: TC-XXX
Requirement: REQ-XXX
Severity: Critical/High/Medium/Low
Priority: P1/P2/P3/P4
Environment:
- Browser/Device: [Details]
- Environment: UAT/QA/Staging
Steps to Reproduce:
1. [Step 1]
2. [Step 2]
3. [Step 3]
Expected Result:
[What should happen]
Actual Result:
[What actually happened]
Attachments:
- [Screenshots, logs, etc.]
| Metric | Formula | Target |
|---|---|---|
| Requirements Coverage | Tested Reqs / Total Reqs | 100% |
| Test Execution | Executed Tests / Total Tests | 100% |
| Pass Rate | Passed Tests / Executed Tests | 95%+ |
| Defect Detection | Defects Found / Total Defects | High |
| Priority | Criteria | Testing Approach |
|---|---|---|
| P1 - Critical | Core functionality, regulatory | Must test every release |
| P2 - High | Important features, frequent use | Test in full regression |
| P3 - Medium | Secondary features | Test in major releases |
| P4 - Low | Edge cases, rare scenarios | Test periodically |