Can it automatically improve my coding rules?

Yes, it generates suggested improvements that can be reviewed manually via `/learn:review` or applied automatically for high-confidence suggestions using `/learn:apply --auto`.

What are the environment requirements for this skill?

It requires AF_LEARNING_ENABLED=true and a valid Supabase configuration, including your Project URL and Service Role Key.

What data does the Learning Analyzer use?

It queries structured data stored in Supabase from your Aura Frog usage, including agent success rates, common patterns, workflow trends, and user feedback.

How do I trigger a performance analysis?

You can trigger a manual analysis by running the `/learn:analyze` command. You can also add flags like `--period 30d` or `--focus agents` for targeted reports.

Learning Analyzer

Name: Learning Analyzer
Author: nguyenthienthanh

bynguyenthienthanh

•

分析と監視

Identifies performance trends and optimization opportunities by analyzing structured development data from your workflows.

概要

The Learning Analyzer skill for Aura Frog empowers developers to turn historical workflow data into actionable insights. By querying Supabase-backed performance metrics, it identifies successful coding patterns, recurring failure points, and efficiency gaps within your AI-driven development process. It provides comprehensive reports including agent success rates, suggested rule updates, and specific optimization opportunities for TDD workflows, ensuring your Claude Code environment evolves and improves with every task.

主な機能

3 GitHub stars
Detailed agent performance tracking across different technology stacks and task types
Data-driven rule suggestions to refine AI behavior and project-specific guidelines
Customizable focus modes for agents, workflows, or feedback-specific analysis
Automated pattern recognition for identifying recurring success and failure points
Workflow efficiency analysis to pinpoint token waste and execution bottlenecks

ユースケース

Optimizing token consumption and execution speed in automated TDD cycles
Debugging systemic workflow failures in large-scale test suites or complex project migrations
Evaluating which AI agents perform best for specific tasks like React UI or API development

概要

主な機能

3 GitHub stars
Detailed agent performance tracking across different technology stacks and task types
Data-driven rule suggestions to refine AI behavior and project-specific guidelines
Customizable focus modes for agents, workflows, or feedback-specific analysis
Automated pattern recognition for identifying recurring success and failure points
Workflow efficiency analysis to pinpoint token waste and execution bottlenecks

ユースケース

Optimizing token consumption and execution speed in automated TDD cycles
Debugging systemic workflow failures in large-scale test suites or complex project migrations
Evaluating which AI agents perform best for specific tasks like React UI or API development