arabelatso/skills-4-se/bug-reproduction-test-generator
- community
Checking that the SKILL.md file is still in the repository.
Automatically generates executable tests that reproduce reported bugs from issue reports and code repositories. Use when users need to: (1) Create a test that reproduces a bug described in an issue report, (2) Generate failing tests from bug descriptions, stack traces, or error messages, (3) Validate bug reports by creating reproducible test cases, (4) Convert issue reports into executable regression tests. Takes a repository and issue report as input and produces test code that reliably triggers the reported bug.
Install
npx vskill@latest install arabelatso/skills-4-se/bug-reproduction-test-generatorSKILL.md
Bug Reproduction Test Generator
Generate executable tests that reproduce reported bugs based on issue reports and code repositories.
Workflow
Follow these steps to generate a bug reproduction test:
1. Analyze the Issue Report
Extract key information from the issue report:
- Symptoms: What goes wrong? (incorrect output, exception, crash, assertion failure, unexpected behavior)
- Affected components: Which modules, classes, or functions are involved?
- Triggering conditions: What inputs, states, or sequences trigger the bug?
- Stack traces: If provided, identify the call chain and failure point
- Expected vs. actual behavior: What should happen vs. what actually happens?
2. Inspect the Repository
Identify relevant code and context:
- Locate the affected components mentioned in the issue
- Find entry points (public APIs, main functions, test fixtures)
- Understand dependencies and required setup
- Identify the test framework used (pytest, unittest, JUnit, Jest, etc.)
- Check existing test patterns for consistency
3. Generate the Reproduction Test
Create a minimal, focused test that:
Test structure:
- Uses the repository's existing test framework and conventions
- Sets up minimal preconditions needed to trigger the bug
- Executes the code path that triggers the bug
- Asserts the symptom described in the issue report
Assertions:
- For exceptions: Assert the exception type and message match the report
- For incorrect output: Assert actual output matches the reported incorrect behavior
- For crashes: Assert the crash occurs at the expected point
- For assertion failures: Reproduce the failing assertion
Documentation:
- Add inline comments explaining the reproduction logic
- Reference the issue number/URL in the test name or docstring
- Document any assumptions made due to underspecified details
4. Output Format
Provide:
- Executable test code in the appropriate language and framework
- Inline comments explaining how the test reproduces the bug
- Markdown summary including:
- How the test reproduces the issue
- Which symptoms it validates
- Any assumptions made
- Instructions for running the test
Example Workflow
Issue Report:
Generated Test (Python/pytest):
Summary:
pytest test_stats.py::test_calculate_average_empty_list_reproduction
assert calculate_average([]) == 0
Language-Specific Patterns
Python (pytest/unittest)
Java (JUnit)
JavaScript (Jest)
Constraints
- Do not modify production code - Only create test code
- Do not assume fixes - Test the buggy behavior, not the expected correct behavior (unless explicitly stated in the issue)
- Document assumptions - If the issue is underspecified, state assumptions clearly
- Prefer minimal tests - Focus on isolating the bug, avoid unnecessary setup
- Match existing patterns - Follow the repository's test conventions and style
Handling Underspecified Issues
When the issue report lacks details:
- State assumptions explicitly in test comments
- Document what's unclear in the summary
- Provide multiple test variants if multiple interpretations are possible
- Ask clarifying questions if critical information is missing
Example:
Tips for Effective Reproduction Tests
- Start simple - Begin with the most direct path to trigger the bug
- Isolate the bug - Remove unrelated setup and assertions
- Make it deterministic - Avoid flaky conditions (timing, randomness)
- Reference the issue - Include issue number in test name and comments
- Verify it fails - Run the test to confirm it reproduces the bug
- Plan for the fix - Comment on how the test should change after the bug is fixed
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/bug-reproduction-test-generator/SKILL.md
Popularity
- Repository stars
- 63
- Repository forks
- 5
- 7-day trend score
- 21
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 20 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/arabelatso/skills-4-se/bug-reproduction-test-generator)