classify-stats

Classify unclassified agent statistics entries in YAML files with complexity and output_type labels.

Updated Aug 23, 2026

Search Tags:#automation #workflow analysis #agent performance #data labeling #stats classification #yaml processing

Ready to run

npx skills add https://github.com/adamfeldman/compound-workflows --skill classify-stats

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: classify-stats
Source: https://github.com/adamfeldman/compound-workflows/tree/main/plugins/compound-workflows/skills/classify-stats
Command: npx skills add https://github.com/adamfeldman/compound-workflows --skill classify-stats

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the classification of agent performance statistics, making it easier to understand and analyze the complexity and output type of various agent tasks.

Core Features & Use Cases

Automated Classification: Assigns complexity and output_type labels to agent stats entries.
Batch Processing: Handles multiple stats entries efficiently, presenting proposals for user confirmation.
Use Case: After running a series of agent tasks, use this Skill to automatically label each task's complexity (e.g., rote, mechanical, analytical, judgment) and its output type (e.g., code-edit, research, review), providing a structured dataset for performance analysis.

Quick Start

Use the classify-stats skill to classify all unclassified stats entries found in .workflows/stats/*.yaml.

Frequently Asked Questions about classify-stats

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

FAQPage Schema

How do I classify agent performance statistics in YAML files automatically?▼

You can classify agent performance statistics by running a classifier over YAML files in the .workflows/stats/ directory, which proposes complexity and output_type labels based on agent actions and artifact content before requiring user confirmation to update files in place.

What is the best way to label agent task complexity and output type for workflow analysis?▼

Labeling agent task complexity and output type involves assigning categories like rote, mechanical, analytical, or judgment for complexity, and code-edit, research, or review for output type, generating a structured dataset for performance analysis.

Can I batch process multiple unclassified stats entries in .workflows/stats/?▼

Yes, you can batch process multiple unclassified stats entries found in .workflows/stats/*.yaml. The Skill handles entries efficiently and presents classification proposals together for user confirmation before applying updates.

Does classify-stats require manual confirmation before updating classified stats files?▼

Yes, classify-stats requires manual confirmation before updating files in place. It dispatches a classifier subagent to propose complexity and output_type labels, then waits for user approval to write changes to the YAML files.

How does the classifier determine the complexity and output_type labels for agent actions?▼

The classifier determines labels by analyzing agent actions and artifact content from the statistics entries. It uses this data to propose a complexity level, such as rote or analytical, and an output type, such as code-edit or research.

When do I need to classify agent stats entries with complexity and output_type labels?▼

You need to classify agent stats entries when you have unclassified performance data in .workflows/stats/ YAML files and want to structure it by task complexity and output type for easier workflow analysis and performance evaluation.