tdd-debugger

Diagnose failing pytest outputs and propose minimal fixes using git history.

Updated Jan 17, 2026
One-click install
npx skills add https://github.com/chijunzheng/ShowMe --skill tdd-debugger
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tdd-debugger
Source: https://github.com/chijunzheng/ShowMe/tree/main/.claude/skills/tdd-debugger
Command: npx skills add https://github.com/chijunzheng/ShowMe --skill tdd-debugger

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Systematically diagnose why tests fail in TDD projects and propose minimal fixes to restore passing tests.

Core Features & Use Cases

  • Systematic failure analysis: parses test outputs, stack traces, and recent changes to identify root causes.
  • Regression tracing: leverages git history to locate when failures were introduced and guides regression fixes.
  • Minimal intervention: recommends the smallest changes that make tests pass, avoiding large refactors.
  • Isolated path tracing: traces code paths to pinpoint failing logic and validate fixes.

Quick Start

Provide failing test output to the agent and request a minimal, safe fix.

Frequently Asked Questions about tdd-debugger

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
Can I use this approach to fix failing implementations without large refactors?

Yes, you can fix failing implementations by recommending the smallest changes that make tests pass, avoiding large refactors while ensuring the test-driven development project maintains its expected behavior.

What is the best way to fix flaky tests and unclear error messages?

Fixing flaky tests and unclear error messages involves systematically analyzing test outputs, tracing isolated code paths to pinpoint failing logic, and proposing concrete, minimal fixes to stabilize the test suite.

How do I isolate failing logic in a test-driven development workflow?

Isolate failing logic in a test-driven development workflow by tracing code paths from the test failure, validating the fix against the isolated failure, and ensuring the minimal intervention passes the tests.

Can I use this approach to fix failing implementations without large refactors?

Yes, you can fix failing implementations by recommending the smallest changes that make tests pass, avoiding large refactors while ensuring the test-driven development project maintains its expected behavior.