learning-analyzer

Analyze collected learning data from Supabase to identify success patterns, failure patterns, optimization opportunities, and agent performance trends.

Best use case

learning-analyzer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Analyze collected learning data from Supabase to identify success patterns, failure patterns, optimization opportunities, and agent performance trends.

Teams using learning-analyzer should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/learning-analyzer/SKILL.md --create-dirs "https://raw.githubusercontent.com/nguyenthienthanh/aura-frog/main/aura-frog/skills/learning-analyzer/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/learning-analyzer/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How learning-analyzer Compares

Feature / Agentlearning-analyzerStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Analyze collected learning data from Supabase to identify success patterns, failure patterns, optimization opportunities, and agent performance trends.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

> **AI-consumed reference.** Optimized for Claude to read during execution.
> Human-readable explanation: see [docs/architecture/HIERARCHICAL_PLANNING.md](../../../docs/architecture/HIERARCHICAL_PLANNING.md)
> or [docs/getting-started/](../../../docs/getting-started/) depending on topic.


# Learning Analyzer Skill

Analyze learning data from Supabase: success/failure patterns, optimization opportunities, agent performance.

---

## Usage

```bash
/af learn analyze                      # Full analysis
/af learn analyze --period 30d         # Last 30 days
/af learn analyze --focus agents       # Agent performance
/af learn analyze --focus workflows    # Workflow patterns
/af learn analyze --focus feedback     # User feedback
```

---

## Process

### 1. Query Supabase Views

```toon
views[5]{view,purpose}:
  v_agent_success_rates,Agent performance by task type
  v_common_patterns,Identified patterns
  v_improvement_suggestions,Actionable suggestions
  v_workflow_trends,Weekly workflow trends
  v_feedback_summary,Feedback statistics
```

### 2. AI Pattern Recognition

Identify: Top 3 success patterns, top 3 failure patterns, top 3 optimization opportunities, agent recommendations.

### 3. Output Report

```markdown
## Learning Analysis Report
Generated: {timestamp} | Period: {dates}

### Success Patterns
1. **Pattern:** {description} — Frequency: {N}, Confidence: {%}

### Failure Patterns
1. **Pattern:** {description} — Impact: {severity}, Suggested Fix: {fix}

### Optimization Opportunities
1. **Opportunity:** {description} — Savings: {tokens/time}

### Agent Recommendations
| Task Type | Agent | Success Rate | Confidence |

### Suggested Rule Updates
- [ ] {suggestion}
```

---

## Environment

```bash
AF_LEARNING_ENABLED=true
SUPABASE_URL=https://your-project.supabase.co
SUPABASE_SERVICE_KEY=your-service-role-key
```

---

## Integration

After analysis, improvements can be: reviewed (`/af learn review`), auto-applied (`/af learn apply --auto`, high confidence only), or saved as pending (`/af learn save`).

---

Related Skills

We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.