Skip to main content

testing-strategy

Selects the one owning test for each acceptance criterion at the boundary where its behavior is observable, using repository evidence and maintenance cost. Use when deciding integration or E2E coverage.

来源信息

仓库
shinpr/agentic-code
最近来源活动
2026年11月3日 02:21
检测到的 SKILL.md 语言
英语
星标
51
Forks
4

安装方式

默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。

检查来源文件

决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。

正在显示 SKILL.md

SKILL.md
来源说明 · 只读预览
name
testing-strategy
description
Selects the one owning test for each acceptance criterion at the boundary where its behavior is observable, using repository evidence and maintenance cost. Use when deciding integration or E2E coverage.
# Test Strategy ## Purpose Select one owning test per behavioral claim at the boundary where the claim is observable, as `testing` defines. Candidate discovery does not create an obligation to implement every technically valid test. ## Selection Process For each acceptance criterion that may require integration or E2E proof: 1. **Name the observable boundary**: Identify the interaction, persisted effect, process, or user journey that must be proven. 2. **Check the existing owner**: When an established test owns the claim at that boundary with assertions that detect its material failure, update it rather than adding another. 3. **Select the owning level**: - use integration when the behavior is observable at a component, persistence, or process boundary; - use E2E when the behavior is observable only across the complete journey; - leave the cases of a calculation, parsing, or branching rule inside the behavior to that rule's unit test. 4. **Compare cost**: Consider setup, execution time, brittleness, maintenance, and diagnostic value using repository evidence rather than fixed universal scores. 5. **Retain valuable proof**: Select a new test only when its regression-detection value justifies that cost. No new integration or E2E test is a valid conclusion when existing tests already own each claim. ## Priority Prioritize proof for: - core user or consumer journeys; - shared or public contracts; - persisted state transitions; - security, authorization, compliance, or irreversible effects; - integrations with demonstrated failure risk. Priority does not determine test level. Use the narrowest boundary that can observe the prioritized behavior. ## Deduplication Before adding a test: - search the existing suite for equivalent behavior; - identify overlapping proof at other levels; - extend existing coverage when that remains clear and maintainable; - keep one representative proof when several candidates observe the same risk. ## Selection Record Record only decisions needed by planning or review: ```text Acceptance criterion: [identifier or behavior] Selected proof: existing | unit | integration | E2E | none Boundary observed: [observable interaction or result] Reason: [why this test owns the claim at this boundary] ``` ## Completion Check - Every selected test traces to an observable requirement or accepted contract. - Each claim has one owning test, and an existing owner was updated rather than duplicated.
在 GitHub 查看