Which error types can this skill categorize?

The skill natively supports TIMEOUT, CRASH, VALIDATION, COORDINATION, and UNKNOWN error types, each with its own standardized format and potential recovery strategy.

Are there specific system dependencies for this skill?

Yes, it requires Bash 4.0+ and jq for JSON processing. While the core is Bash-based, the logging module also includes an optional TypeScript implementation requiring Node.js.

What is a Mega-Skill in the context of CFN?

A Mega-Skill is a consolidated package that combines multiple specialized sub-skills—in this case, error capture, batching, and logging—into a single, unified directory structure for easier management.

How does the batching module improve agent efficiency?

The batching module clusters similar errors by file and calculates execution 'waves,' allowing multiple errors to be fixed in parallel batches rather than one by one, significantly reducing processing time.

CFN Error & Batch Management

Name: CFN Error & Batch Management
Author: masharratt

bymasharratt

•

Analíticas y Monitorización

Automates error capture, intelligent batching, and structured logging to streamline AI agent recovery and orchestration.

Acerca de

CFN Error Management is a comprehensive 'mega-skill' designed for the Claude Flow Novice ecosystem that consolidates error handling into a single, unified workflow. It enables developers to capture and categorize agent failures such as timeouts and crashes, cluster those errors into batches for efficient parallel processing, and maintain structured logs with automated cleanup. This skill is essential for building resilient AI agentic loops where tracking, analyzing, and recovering from multiple asynchronous failures is critical to project success.

Características Principales

13 GitHub stars
Standardized error capture with categorization for TIMEOUT, CRASH, and VALIDATION errors
Structured logging with built-in log rotation and cleanup utilities
Category-based recovery strategies to preserve context during agent failures
Intelligent error batching by file clustering and wave calculation for parallel processing
Unified CLI wrappers for seamless integration into existing shell scripts

Casos de Uso

Batching multiple validation errors for consolidated processing by a repair agent
Managing high-volume agent execution failures in complex autonomous workflows
Maintaining auditable error logs for long-running AI orchestration tasks

Acerca de

Características Principales

13 GitHub stars
Standardized error capture with categorization for TIMEOUT, CRASH, and VALIDATION errors
Structured logging with built-in log rotation and cleanup utilities
Category-based recovery strategies to preserve context during agent failures
Intelligent error batching by file clustering and wave calculation for parallel processing
Unified CLI wrappers for seamless integration into existing shell scripts

Casos de Uso

Batching multiple validation errors for consolidated processing by a repair agent
Managing high-volume agent execution failures in complex autonomous workflows
Maintaining auditable error logs for long-running AI orchestration tasks