worker-integration

Dispatch tasks to worker-agents and track performance metrics.

Updated Jun 5, 2026

Search Tags:#feedback loop #agent coordination #performance tracking #task dispatch #intelligent systems

Ready to run

npx skills add https://github.com/LGugui/cerebro-template --skill worker-integration-lgugui

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: worker-integration
Source: https://github.com/LGugui/cerebro-template/tree/main/.claude/skills/worker-integration
Command: npx skills add https://github.com/LGugui/cerebro-template --skill worker-integration-lgugui

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

The worker-integration Skill addresses the challenge of efficiently dispatching tasks to the most appropriate agents and tracking their performance for continuous improvement.

Core Features & Use Cases

Intelligent Task Dispatch: Automatically dispatches tasks to the optimal agents based on trigger type and historical performance.
Performance Tracking: Monitors and provides detailed metrics on agent performance, including latency, quality score, and success rate.
Agent Selection: Uses a feedback loop to learn from execution history and improve agent selection over time.
Memory Key Patterns: Consistent pattern for storing results using a structured keying system.
Benchmark Thresholds: Monitors agents against predefined performance thresholds to ensure quality and efficiency.
Feedback Loop: Allows for the recording of execution feedback for continuous improvement of the system.
Integration Statistics: Provides statistics on the overall integration and performance of the worker-agent system.

Quick Start

View performance metrics for the worker-integration Skill by running the command: npx agentic-flow workers metrics.

Frequently Asked Questions about worker-integration

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

FAQPage Schema

How does agent performance tracking work for monitoring execution quality?▼

You can view integration statistics and performance metrics by running the `npx agentic-flow workers metrics` command. This provides detailed data on agent latency, quality scores, and overall worker-agent system performance.

Can I use a feedback loop to continuously improve agent selection?▼

Yes, the system applies a feedback loop by recording execution feedback after task completion. This mechanism allows the integration to learn from historical performance and refine future agent selection automatically.

What is the best way to monitor worker-agents against benchmark thresholds?▼

The best way to monitor worker-agents is by setting predefined benchmark thresholds for success rate and latency. The system tracks these performance metrics automatically and flags agents that fail to meet the established quality standards.

How do I store execution results using memory key patterns?▼

Execution results are stored using a structured memory key pattern system. This consistent keying approach ensures that performance data and feedback loop records are organized for reliable retrieval and continuous improvement analysis.