error-recovery

Classifies workflow failures and executes auto-fix strategies.

Updated Jan 5, 2026
One-click install
npx skills add https://github.com/Marcus-Mok-GH/Claude-code-conductor --skill error-recovery-marcus-mok-gh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: error-recovery
Source: https://github.com/Marcus-Mok-GH/Claude-code-conductor/tree/main/.claude/skills/error-recovery
Command: npx skills add https://github.com/Marcus-Mok-GH/Claude-code-conductor --skill error-recovery-marcus-mok-gh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the classification and recovery of workflow failures, reducing the need for manual intervention and speeding up the resolution process.

Core Features & Use Cases

  • Failure Classification: Automatically categorizes failures into critical, fixable, or unknown categories.
  • Auto-Fix Strategies: Implements up to three auto-fix strategies for common issues, such as re-running tests, clearing caches, and rebuilding.
  • Critical Failure Handling: Stops workflows immediately for critical issues, requiring manual intervention and reporting.
  • Use Case: In a sprint where a feature fails during implementation, the skill can automatically identify the issue, attempt fixes, and guide the team on whether manual intervention is needed.

Quick Start

When a workflow component fails, load the error-recovery skill and classify the failure. If fixable, execute auto-fix strategies. If critical, stop and report to the user.

Frequently Asked Questions about error-recovery

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

FAQPage Schema
How do I automate workflow failure recovery in software development pipelines?

Automate workflow failure recovery by classifying errors into critical, fixable, or unknown categories, then executing predefined auto-fix strategies like re-running tests or clearing caches to reduce manual intervention.

What types of workflow failures can be automatically classified and fixed?

Workflow failures are automatically classified into critical, fixable, or unknown categories. Fixable failures trigger predefined auto-fix strategies, while critical failures immediately stop workflows and require manual intervention and reporting.

How does automated error handling determine when to stop a software development pipeline?

Automated error handling stops a software development pipeline when it classifies a failure as critical. This immediate stoppage requires manual intervention and generates a report to guide the team on resolving the issue.

Do I need a state.yaml file to classify and report workflow failures?

Yes, you need a state.yaml file to classify and report workflow failures. The automated recovery process requires this file to accurately categorize errors and execute the appropriate predefined auto-fix scripts.

What auto-fix strategies are available for workflow failures during a sprint?

Available auto-fix strategies for workflow failures include re-running tests, clearing caches, and rebuilding. Up to three strategies are implemented to automatically resolve common fixable issues during a sprint.

Can I use scripts to handle critical failure handling in automated workflows?

Scripts are used for executing automated fixes on fixable failures, but critical failure handling stops workflows immediately and requires manual intervention, using the state.yaml file to report errors rather than running auto-fix scripts.