AI Agent Hub
Back to skills
Software Test Case Design icon

Software Test Case Design

Development Updated 2026.08.30

Paste the following prompt into your AI chat to install this skill:

Install @user_15292d5a/yjkj-software-test-case-design into your AI assistant using https://skillhub.cn/install/skillhub.md.

About this skill

Problem

API, AI Agent, and functional test cases are often drafted as flat bullet lists, missing edge cases, platform differences, and acceptance criteria. This skill turns type detection, rule loading, case generation, and self-checking into a repeatable workflow, helping engineers turn a short request into structured Markdown table test cases.

How It Works

  • Type detection: It distinguishes API Test, Agent Test, AI Agent, and default functional testing from keywords.
  • Rule loading: It always reads templates/common-rules.md, then loads core-capabilities/api-testing.md, core-capabilities/agent-testing.md, or core-capabilities/functional-testing.md based on the selected type.
  • Platform overlay: For non-API scenarios, it can add platform rules triggered by Mobile Testing, Mini-Program Testing, H5 Testing, Desktop Testing, or PC Web Testing.
  • Generation and self-check: It generates cases, validates them against the applicable API, Agent, functional, and platform checklists, and outputs a Markdown table following examples/format-spec.md.

Boundaries

It is suitable for functional testing, API testing, AI Agent testing, basic security testing, and platform-related testing. It does not generate test plans, test strategies, penetration test execution, vulnerability scanning, performance or stress testing, or automation scripts.

Use Cases

  • When an order service API needs acceptance, draft cases for parameters, error codes, and auth failures.
  • When preparing an AI Agent launch, cover intent detection, clarification, tool calls, and refusal cases.
  • Before H5 release, organize cases for mobile browsers, weak network, payment callbacks, and sharing flows.
  • Before mini-program review, design cases for authorization, sharing, subscriptions, and lifecycle checks.

Best For

  • Test engineers who need API acceptance cases for parameters, authentication, and failure paths.
  • Product or ML engineers preparing an AI Agent launch and covering intent, tools, and refusal cases.
  • Frontend or test owners who need H5 acceptance cases for weak network, payments, and sharing flows.
  • Test engineers preparing mini-program release cases for auth, subscriptions, and lifecycle checks.

Related Skills

Android Dependency Class Lookup icon
Android Dependency Class Lookup
@user_d2af0937/android-lib-lookup

Automatically indexes Gradle-cached AAR/JAR dependency classes and returns library coordinates, versions, and public APIs by fully qualified name, using only the Python standard library.

Development 2026.08.29 ↓ 363
General Algorithm Training icon
General Algorithm Training
@user_db1d96f9/music-algo-train

Codifies AMT and YourMT3 training conventions, script patterns, hyperparameters, precision, checkpoints, and NaN safeguards.

Development 2026.08.29 ↓ 363
PKM Knowledge Base Retrieval icon
PKM Knowledge Base Retrieval
@user_e3c9e60f/test2333

Retrieve relevant chunks from a customer-managed PKM dataset by dataset_id and return concise, source-annotated answers.

Development 2026.08.29 ↓ 363
Requirement-to-Testpoint Extraction icon
Requirement-to-Testpoint Extraction
@user_827d1ddb/requirement-to-testpoints

Convert PRDs, user stories, or functional specs into prioritized test-point checklists covering functional, business-rule, boundary, exception, and non-functional dimensions.

Development 2026.08.29 ↓ 349