mcpbeat Sign in

Test Case Writing Agent Skill

Use this skill when you need to create high-quality test cases with normal, exception, and boundary scenarios; triggers include 测试用例编写 and test case writing.

10k tokens
context cost
the whole folder, loaded on every use
36
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
144
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/naodeng/awesome-qa-skills --skill test-case-writing

What comes with it

36 916 bytes besides the instruction
README.md
agents/openai.yaml
evals/cases/basic-success.yaml
evals/cases/edge-incomplete-input.yaml
evals/cases/edge-risk-priority.yaml
evals/eval.yaml
examples/README.md
examples/test-case-patterns/README.md
output-formats.md
output-templates/template-csv.csv
output-templates/template-excel.tsv
output-templates/template-json.json
output-templates/template-markdown.md
output-templates/template-word.md
output-templates/template-xmind.md
prompts/test-case-writing.md
quick-start.md
references/local/FAQ.md
scripts/batch_convert_templates.py
scripts/convert_formats.py
scripts/convert_output_formats.py
scripts/convert_to_csv.py
scripts/convert_to_excel.py
scripts/convert_to_json.py
scripts/convert_to_markdown.py
scripts/convert_to_word.py
scripts/convert_to_xmind.py
scripts/parse_csv.py
scripts/parse_excel.py
scripts/parse_formats.py
scripts/parse_json.py
scripts/parse_markdown.py
scripts/parse_output_formats.py
scripts/parse_word.py
scripts/parse_xmind.py

The instruction itself

as written by the author

测试用例编写(中文版)

英文版: 见对应英文技能。

何时使用

  • 需要在真实项目里处理 test case writing 相关任务。
  • 需要一份可以直接用于执行、评审或跟进的结果。

执行流程

  • 阅读并遵循「按需加载」中的主提示词(覆盖清单、输出结构、质量要求)。
  • 只补充真正影响结果的项目上下文:范围、环境、限制、风险、依赖、期望产出。
  • 信息不全时先给可用初版,并显式标出假设与信息缺口。
  • 默认 Markdown;用户指定其他格式时再切换。

核心约束

  • 按风险/业务影响排优先级,不要平均摊铺。
  • 把「已确认事实」和「当前假设」分开写。
  • 不要编造用户未提供的接口、字段、环境或根因细节。
  • 结果必须可执行:场景具体、有优先级、能指导下一步。

按需加载

  • 产出前必须阅读并遵循 prompts/test-case-writing.md(最低覆盖清单、输出结构、质量要求)。
  • 需要 Excel/CSV/JSON/Word 等格式时:读 output-formats.md,并按用户格式要求输出。
  • 需要套用现成模板时:读 output-templates/ 中匹配的模板,不要自创冲突结构。
  • 用户要示例或对标现有资产时:读 examples/ 中相关样例。
  • 需要框架规范、排障、报告 schema 等深资料时:只读 references/ 里与当前问题相关的文件,不要整目录通读。
  • 需要格式转换或辅助校验时:优先使用 scripts/ 中已有脚本,而不是重写一遍。
  • 需要评测/回归本 skill 时:使用 evals/,并用 skill-up 校验与运行。
  • 用户只要最短上手路径时:读 quick-start.md。

交付前自检

  • [ ] 已遵循主提示词的输出结构
  • [ ] 最低覆盖关注:范围、用例优先级、前置条件、测试数据、步骤、预期结果、正向场景、异常场景…(细节以主提示词为准)
  • [ ] 已覆盖最低清单,或标明为何省略
  • [ ] 高风险项有明确优先级
  • [ ] 未编造用户未提供的细节
  • [ ] 假设与信息缺口已标明

常见误区

  • 范围和上下文都不清楚时,不要假装已经完整可用。
  • 不要把所有项写成同等重要。
  • 不要跳过假设与信息缺口。
  • 不要输出大段与当前工具链无关的空泛理论。

Other skills for the same job

different authors, same section of the catalogue
Test Driven Development
by w95
×7

Use when implementing any feature or bugfix, before writing implementation code

2k tokens
Test Driven Development
by ComeOnOliver
×2

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

6k tokens
Writing Skills
by ComeOnOliver
×1

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization

32k tokens
Writing Tests
by remotion-dev
vendor

Rules for writing and reviewing tests in the Remotion repository. Use whenever adding, editing, or reviewing tests, especially for Studio UI, rendering, CLI, server, media, and cross-package changes, to prefer complete integration workflows over narrow helper tests and implementation details.

3k tokens
Cuda Attention Kernel Patterns
by microsoft
vendor

Patterns and pitfalls for the ONNX domain Attention operator (opset 23/24) CUDA implementation. Use when modifying the dispatch cascade in core/providers/cuda/llm/attention.cc, writing mask/bias CUDA kernels, debugging attention test routing, or adding features to the ONNX Attention op. NOT for contrib domain MultiHeadAttention/GroupQueryAttention.

7k tokens
Ad Model Onboard
by NVIDIA
vendor

> Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.

8k tokens
Ad Model Onboard
by NVIDIA
vendor

Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.

8k tokens
Angular Architect
by Jeffallan

Generates Angular 17+ standalone components, configures advanced routing with lazy loading and guards, implements NgRx state management, applies RxJS patterns, and optimizes bundle performance. Use when building Angular 17+ applications with standalone components or signals, setting up NgRx stores, establishing RxJS reactive patterns, performance tuning, or writing Angular tests for enterprise apps.

13k tokens

How to use it

Copy the folder

Take naodeng/awesome-qa-test-case-writing from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.