agentleFS
mavka-aimavka-ai/unit-tests-skills/skills/generate-tests/SKILL.md

generate-tests

Skill55 starsChanged 59 days agoMITView on GitHub

Use when the user asks to generate, create, write, or add unit tests for existing code, or to cover a class, method, or file with tests — including Java targets using JUnit 5, Mockito, or AssertJ. Not for analysis-only requests that stop at listing test cases.

7 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions7 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 7

    1. coco-research/coco★ 797same name
    2. hidai25/eval-view★ 140same name
    3. Terryc21/sitrep★ 50same name
    4. zbruhnke/claude-code-starter★ 16same name
    5. chidekina/aria-superpowers★ 2same name
    6. simu5116/ClaudeCode★ 0same name
    7. toantran292/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

20 rules. 0 are common, 13 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 13

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not skip any step in the workflow below.

    line 18
  2. Distinctive:

    Do not take shortcuts with test data — read the actual classes to use correct constructors and fields.

    line 19
  3. Very specific:

    Read dependencies: Follow imports to read DTOs, entities, enums, custom exceptions, and other types referenced by the target (as specified …

    line 29
  4. Very specific:

    Check for existing tests: Search for {ClassName}Test or {ClassName}Tests in the test directory (as specified in existing-test-awareness …

    line 30
  5. Distinctive:

    If found, read fully — you will add missing tests to it, not create a new file

    line 31
  6. Distinctive:

    If not found, scan 2-3 neighboring test classes to learn project conventions

    line 32
  7. Very specific:

    Test method name format: {testedMethod}_{givenState}_{expectedOutcome}

    line 71
  8. Distinctive:

    If an existing test class was found in Step 1, add new test methods to it (do not create a duplicate file)

    line 85
  9. Distinctive:

    Create or update the test file using the Write tool

    line 87
  10. Very specific:

    Run compilation and fix any issues (max 5 attempts — see compilation-verification.md)

    line 91
  11. Very specific:

    Run the generated test class to verify all tests pass (see test-execution-verification.md)

    line 92
  12. Very specific:

    If a test resists fixing after 3 attempts, keep it in the file: mark it @Disabled with the reason and report it (see …

    line 94
  13. Distinctive:

    If the specified target does not exist, inform the user with the exact path you searched and ask for clarification.

    line 102
  14. Distinctive:

    If the target code is in a language without specific rules (not Java), apply only the general rules and inform the user that …

    line 105
  15. Distinctive:

    If compilation fails after 5 attempts:

    line 108
  16. Distinctive:

    Stop and show the user the remaining errors

    line 109
  17. Distinctive:

    Ask the user to resolve the build issue before continuing

    line 111
  18. Distinctive:

    If tests fail because the production code behaves differently than expected:

    line 114
  19. Distinctive:

    Do NOT modify production code

    line 115
  20. Very specific:

    If the behavior seems like a bug, add a comment: // NOTE: current behavior may be a bug — {description}

    line 117

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Generate Tests Skill

You will analyze code and generate high-quality unit tests for a given target.

Target to test: $ARGUMENTS

Quality Standards

  • Take your time to analyze the code thoroughly before generating test cases.
  • Quality is more important than speed — read all relevant source files and rules carefully.
  • Do not skip any step in the workflow below. Every step exists for a reason.
  • Do not take shortcuts with test data — read the actual classes to use correct constructors and fields.

Instructions

Step 1: Read Rules and Analyze Context

  1. Read the relevant rules from ./rules/tests/ based on code type (see Rules Reference below)
  2. Read the target source file/class/method
  3. Read dependencies: Follow imports to read DTOs, entities, enums, custom exceptions, and other types referenced by the target (as specified in code-context-analysis rule)
  4. Check for existing tests: Search for {ClassName}Test or {ClassName}Tests in the test directory (as specified in existing-test-awareness rule)
    • If found, read fully — you will add missing tests to it, not create a new file
    • If not found, scan 2-3 neighboring test classes to learn project conventions

Step 2: Establish the Test Case List

If a test case list for this target is already present — generate-test-cases ran first, whether the user invoked it or the agent did — that list is the plan. Generate from it. Do not re-analyze the target from scratch; where your reading of the code differs, name the cases you add or drop and why, so the change to the plan is visible.

If there is no such list, produce one here before writing any test code:

  1. Analyze ALL code branches, including:
    • Success paths
    • Error/exception paths
    • Validation logic
    • Private/protected methods called by the target
    • Security annotations (if present)
  2. Apply the INCLUDE/EXCLUDE rules strictly
  3. Output the list in the format below

Either way, continue straight to Step 3. The list is printed so the user can audit the plan against the generated tests afterwards; the run stays unattended end to end.

Test Case Output Format

## Test Cases for {ClassName}.{methodName}

### 1. {testMethodName}
- **Given:** {preconditions/input state}
- **When:** {action being tested}
- **Then:** {expected outcome}
- **Code branch:** {which code path this covers}

### 2. {testMethodName}
...

Naming Convention

Test method name format: {testedMethod}_{givenState}_{expectedOutcome}

Examples:

  • calculateTotal_validProducts_returnsSum
  • calculateTotal_emptyList_throwsIllegalArgumentException
  • getUser_unauthorized_returns401

Step 3: Generate Test Code

  1. Determine code type and apply the matching rules:
    • Controller → Apply controller-test-rules.md (use @WebMvcTest, MockMvc patterns)
    • Service / Domain logic → Apply domain-service-rules.md (use @ExtendWith(MockitoExtension.class), Mockito patterns)
    • Repository / Messaging / Other types → Apply domain-service-rules.md as baseline; inform the user that type-specific rules are not yet available
    • All Java code → Always apply java-test-template.md, argument-matching.md, json-serialization.md regardless of code type
  2. If an existing test class was found in Step 1, add new test methods to it (do not create a duplicate file)
  3. Generate tests following all rules and the test cases from Step 2
  4. Create or update the test file using the Write tool

Step 4: Verify Compilation and Execution

  1. Run compilation and fix any issues (max 5 attempts — see compilation-verification.md)
  2. Run the generated test class to verify all tests pass (see test-execution-verification.md)
  3. Fix any failing tests by changing the test — production code stays as it is
  4. If a test resists fixing after 3 attempts, keep it in the file: mark it @Disabled with the reason and report it (see test-execution-verification.md)

Troubleshooting

Target file not found

If the specified target does not exist, inform the user with the exact path you searched and ask for clarification.

Unsupported language

If the target code is in a language without specific rules (not Java), apply only the general rules and inform the user that language-specific conventions may need manual review.

Compilation keeps failing

If compilation fails after 5 attempts:

  1. Stop and show the user the remaining errors
  2. Suggest possible causes (missing dependencies, incompatible versions)
  3. Ask the user to resolve the build issue before continuing

Tests fail due to production code behavior

If tests fail because the production code behaves differently than expected:

  1. Do NOT modify production code
  2. Fix the test to match actual behavior
  3. If the behavior seems like a bug, add a comment: // NOTE: current behavior may be a bug — {description}

Example

User says: "/generate-tests src/main/java/com/example/service/OrderService.java"

Step 1: Agent reads rules, reads OrderService.java, reads OrderRequest.java,
        Order.java, OrderRepository.java (dependencies), checks for
        existing OrderServiceTest.java

Step 2: Agent outputs 7 test cases covering:
        - createOrder success path
        - createOrder with invalid request (validation)
        - processPayment success
        - processPayment failure
        - calculateTotal with products
        - calculateTotal with empty list
        - cancelOrder for non-existent order

Step 3: Agent generates OrderServiceTest.java with @ExtendWith(MockitoExtension.class),
        mocked repository and payment service, 7 test methods.

Step 4: Agent runs `mvn test -Dtest=OrderServiceTest -q`, all tests pass.

Result: Complete test file delivered with 7 passing tests.

Rules Reference

CRITICAL: You MUST read and apply all relevant rules from the ./rules/tests/ directory.

Maintenance note: General rules in ./rules/tests/general/ are shared with the generate-test-cases skill (which has copies in rules/general/). When updating rules, keep both locations in sync.

General Rules (Always Apply)

  • general/test-case-generation-strategy.md - INCLUDE/EXCLUDE criteria
  • general/naming-conventions.md - Test naming format
  • general/general-principles.md - Core testing principles (Given-When-Then, actual/expected)
  • general/technology-stack-detection.md - Detect language and framework
  • general/what-makes-good-test.md - Clarity, Completeness, Conciseness, Resilience
  • general/cleanly-create-test-data.md - Use helpers and builders for test data
  • general/keep-cause-effect-clear.md - Effects follow causes immediately
  • general/no-logic-in-tests.md - KISS > DRY, avoid logic in assertions
  • general/keep-tests-focused.md - One scenario per test
  • general/test-behaviors-not-methods.md - Separate tests for behaviors
  • general/verify-relevant-arguments-only.md - Only verify relevant mock arguments
  • general/prefer-public-apis.md - Test public APIs over private methods
  • general/existing-test-awareness.md - Check for existing tests, match project conventions
  • general/code-context-analysis.md - Read dependencies before writing tests

Java Unit Tests

  • java/unit/java-test-template.md - Basic template, FORBIDDEN annotations
  • java/unit/json-serialization.md - Use explicit JSON literals
  • java/unit/argument-matching.md - Use ArgumentCaptor, not any()
  • java/unit/logging-rules.md - OutputCaptureExtension for logs
  • java/unit/domain-service-rules.md - Mockito patterns for services
  • java/unit/controller-test-rules.md - @WebMvcTest and MockMvc patterns for controllers

Post-Generation

  • post-generation/compilation-verification.md - Verify compilation
  • post-generation/test-execution-verification.md - Verify tests pass

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.