NEW Browse AI tools across categories — updated daily. See what's new →

Test Fixing

Detect failing tests and propose patches or fixes

Version1.0.0
LicenseApache-2.0
Token count~523
UpdatedJun 5, 2026

Install

Quick install

via npx skills · works with 57+ agents
npx skills add https://github.com/mhattingpete/claude-skills-marketplace/tree/main/engineering-workflow-plugin/skills/test-fixing
Or pick agent:
npx skills add mhattingpete/claude-skills-marketplace --skill test-fixing --agent claude-code
npx skills add mhattingpete/claude-skills-marketplace --skill test-fixing --agent cursor
npx skills add mhattingpete/claude-skills-marketplace --skill test-fixing --agent codex
npx skills add mhattingpete/claude-skills-marketplace --skill test-fixing --agent opencode
npx skills add mhattingpete/claude-skills-marketplace --skill test-fixing --agent github-copilot
npx skills add mhattingpete/claude-skills-marketplace --skill test-fixing --agent windsurf
More install options

Shorthand — useful for multi-skill repos:

npx skills add mhattingpete/claude-skills-marketplace --skill test-fixing

Manual — clone the repo and drop the folder into your agent's skills directory:

git clone https://github.com/mhattingpete/claude-skills-marketplace.git
cp -r claude-skills-marketplace/engineering-workflow-plugin/skills/test-fixing ~/.claude/skills/
How to use: Once installed, ask your agent to "use the test-fixing skill" or describe what you want (e.g. "Detect failing tests and propose patches or fixes"). Requires Node.js 18+.

test-fixing

Detect failing tests and propose patches or fixes

What is it?
A skill for detecting failing tests and proposing targeted patches or fixes. It analyzes test failures, identifies root causes, and generates minimal code changes to make tests pass. Designed for rapid test stabilization in continuous integration pipelines and development workflows.

How to use it?

When tests fail, the skill:
  • Analyzes test output to identify which tests failed and why
  • Traces failures back to the source code that caused them
  • Generates minimal, focused patches to fix the failing tests
  • Verifies that proposed fixes don't break other tests

The skill distinguishes between test bugs (fix the test) and code bugs (fix the implementation), ensuring the right thing gets fixed.

Key Features

  • Automatic test failure analysis and root cause identification
  • Minimal patch generation targeting specific failing tests
  • Distinction between test bugs and implementation bugs
  • Cross-test impact analysis to prevent regression
  • Integration with CI/CD pipelines for automated fix proposals
  • Support for multiple testing frameworks and languages
  • Systematic debugging workflow with verification stepsView on GitHub

GitHub Stats

StarsForksLast UpdateAuthormhattingpeteLicenseApache-2.0Version1.0.0

Categories

Developer ToolsProductivity

Tags

automationaitestinggitcodingdebugging

Features

Related Skills

More from Developer Tools

git-pushing

Automate git operations and repository interactions

350mhattingpeteDeveloper ToolsProductivity00

review-implementing

Evaluate code implementation plans and align with specs

350mhattingpeteDeveloper ToolsProductivity00

Google Sheets CLI

Google Sheets CLI automation

41gmickelDeveloper ToolsProductivity00

---

Source: https://github.com/mhattingpete/claude-skills-marketplace/tree/main/engineering-workflow-plugin/skills/test-fixing
Author: mhattingpete
License: https://opensource.org/licenses/Apache-2.0
GitHub Stars: 350
Tags: automation, ai, testing, git, coding, debugging

SKILL.md source

---
name: test-fixing
description: Detect failing tests and propose patches or fixes
---

# test-fixing

Detect failing tests and propose patches or fixes

What is it?
A skill for detecting failing tests and proposing targeted patches or fixes. It analyzes test failures, identifies root causes, and generates minimal code changes to make tests pass. Designed for rapid test stabilization in continuous integration pipelines and development workflows.

## How to use it?
When tests fail, the skill:

* Analyzes test output to identify which tests failed and why

* Traces failures back to the source code that caused them

* Generates minimal, focused patches to fix the failing tests

* Verifies that proposed fixes don't break other tests

The skill distinguishes between test bugs (fix the test) and code bugs (fix the implementation), ensuring the right thing gets fixed.

## Key Features

* Automatic test failure analysis and root cause identification
* Minimal patch generation targeting specific failing tests
* Distinction between test bugs and implementation bugs
* Cross-test impact analysis to prevent regression
* Integration with CI/CD pipelines for automated fix proposals
* Support for multiple testing frameworks and languages
* Systematic debugging workflow with verification stepsView on GitHub

### GitHub Stats
StarsForksLast UpdateAuthormhattingpeteLicenseApache-2.0Version1.0.0

### Categories
Developer ToolsProductivity

### Tags
automationaitestinggitcodingdebugging

### Features

## Related Skills
More from Developer Tools

### git-pushing
Automate git operations and repository interactions

350mhattingpeteDeveloper ToolsProductivity00

### review-implementing
Evaluate code implementation plans and align with specs

350mhattingpeteDeveloper ToolsProductivity00

### Google Sheets CLI
Google Sheets CLI automation

41gmickelDeveloper ToolsProductivity00

---

**Source**: https://github.com/mhattingpete/claude-skills-marketplace/tree/main/engineering-workflow-plugin/skills/test-fixing
**Author**: mhattingpete
**License**: https://opensource.org/licenses/Apache-2.0
**GitHub Stars**: 350
**Tags**: automation, ai, testing, git, coding, debugging

Related skills 6

agent-browser

★ Featured Official

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use...

vercel-labs 297k
Testing & Quality

grill-me

★ Featured

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

mattpocock 192k
Testing & Quality

grill-with-docs

★ Featured

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

mattpocock 138k
Testing & Quality

minimal-run-and-audit

★ Featured

RigorPilot trusted execution and reporting skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end...

lllllllama 127k
Testing & Quality

polish

★ Featured

Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.

pbakaus 86k
Testing & Quality

critique

★ Featured

Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

pbakaus 83k
Testing & Quality