Browse skills

This skill helps refine an AI’s abilities by iteratively improving its responses based on feedback – boosting performance and accuracy.

Agentic Eval assesses an agent’s performance across multiple runs, identifying strengths and weaknesses for improved efficiency and reliability.

This skill helps refine an AI’s capabilities by iteratively improving its performance through targeted training and feedback – boosting accuracy & effectiveness.

Continuously refines its strategies and knowledge base through automated experimentation and data analysis to enhance performance.

Official openclaw skill covering testing, performance optimization for software development workflows.

Supercent-io's agent-evaluation assesses agent performance against defined metrics, providing actionable insights for improvement.

This skill helps your agent learn and adapt by analyzing its performance, boosting its capabilities and effectiveness over time.

Davila7's memory systems enable agents to store, retrieve, and utilize complex information across extended interactions for improved performance.

Evaluates agent performance based on defined metrics, providing actionable feedback for improvement and optimization.

Evaluates agent performance across diverse tasks, providing detailed metrics and actionable improvement suggestions.

Helps with testing, performance optimization as part of software development workflows workflows.

The Agentic Actions Auditor analyzes agent workflows for inefficiencies and potential issues, optimizing performance and ensuring reliable execution.

Automates MLflow agent performance evaluation using predefined metrics and datasets for consistent benchmarking.

Helps with performance optimization, analysis as part of agent workflows workflows.

Helps with performance optimization, testing, code review as part of software development workflows workflows.

Analyzes and optimizes collaborative agent teams' performance via detailed metrics and actionable insights from Terrylica.

Evaluates agent performance against defined metrics, providing actionable insights to improve effectiveness and efficiency.

Analyzes agent health data, identifies risks, and suggests improvements to optimize performance and prevent failures.

Ensures SecondSky agents adhere to optimal logging standards for debugging, auditing, and performance analysis.

This Evaluation Harness assesses model outputs against defined criteria, ensuring consistent and reliable performance evaluations for improved results.

Dicklesworthstone's agent-fungibility allows seamless task delegation between agents without performance degradation or context loss.

Helps with performance optimization, monitoring as part of orchestrating AI agents and multi-step workflows workflows.

Ruvnet's agent-performance-optimizer dynamically adjusts agent parameters to maximize efficiency and task completion rates.

Evaluates agent performance across diverse tasks using metrics like accuracy, efficiency, and robustness for actionable insights.