CtrlK
BlogDocsLog inGet started
Tessl Logo

bug-reproduction-test-generator

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.

90

1.41x
Quality

88%

Does it follow best practices?

Impact

92%

1.41x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

100%

Config Loader Bug Reproduction

Bug reproduction test with stack trace

Criteria
Without context
With context

Uses pytest framework

100%

100%

Issue reference in test

100%

100%

Asserts buggy behavior

100%

100%

Inline comments present

100%

100%

Does not modify source

100%

100%

Markdown summary present

100%

100%

Summary: how it reproduces

100%

100%

Summary: symptoms validated

100%

100%

Summary: run instructions

100%

100%

Plan-for-fix comment

100%

100%

93%

53%

Date Utility Bug Investigation

Underspecified issue handling and assumption documentation

Criteria
Without context
With context

Uses Jest framework

100%

100%

Issue reference in test

100%

100%

Assumptions stated in test

0%

100%

Summary documents what is unclear

0%

53%

Asserts buggy behavior

0%

100%

Does not modify source

100%

100%

Markdown summary present

100%

100%

Summary: assumptions section

0%

100%

84%

29%

Data Validator Regression Test

Minimal test with assertion specificity

Criteria
Without context
With context

Uses pytest/class style

100%

100%

Asserts ValueError type

33%

100%

Asserts error message text

0%

0%

Issue reference in test

100%

100%

Inline comments in test body

0%

90%

Minimal setup

100%

100%

Does not modify source

100%

100%

Plan-for-fix comment

0%

100%

Markdown summary present

100%

100%

Summary: run instructions

100%

100%

Repository
ArabelaTso/Skills-4-SE
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.