workflow-monitor

## Table of Contents

- [Philosophy](#philosophy)
- [Quick Start](#quick-start)
- [Detection Patterns](#detection-patterns)
- [Workflow](#workflow)
- [Issue Template](#issue-template)
- [Configuration](#configuration)
- [Guardrails](#guardrails)
- [Integration Points](#integration-points)
- [Output Format](#output-format)

# Workflow Monitor

Monitor workflow executions for errors and inefficiencies, automatically creating GitHub issues for improvements.

## Philosophy

Workflows should improve over time. When execution issues occur, capturing them systematically enables continuous improvement. This skill hooks into workflow execution to detect problems and propose fixes.

## Quick Start

### Manual Invocation

```bash
# After a failed workflow
/workflow-monitor --analyze-last

# Monitor a specific workflow execution
/workflow-monitor --session <session-id>

# Analyze efficiency of recent workflows
/workflow-monitor --efficiency-report
```

### Automatic Monitoring (via hooks)

When enabled, workflow-monitor observes execution and flags:
- Command failures (exit codes > 0)
- Timeout events
- Repeated retry patterns
- Context exhaustion
- Inefficient tool usage

## Detection Patterns

### Error Detection

| Pattern | Signal | Severity |
|---------|--------|----------|
| Command failure | Exit code > 0 | High |
| Timeout | Exceeded timeout limit | High |
| Retry loop | Same command >3 times | Medium |
| Context exhaustion | >90% context used | Medium |
| Tool misuse | Wrong tool for task | Low |

### Efficiency Detection

| Pattern | Signal | Threshold |
|---------|--------|-----------|
| Verbose output | >1000 lines from command | 500 lines recommended |
| Redundant reads | Same file read >2 times | 2 reads max |
| Sequential vs parallel | Independent tasks run sequentially | Should parallelize |
| Over-fetching | Read entire file when snippet needed | Use offset/limit |

## Workflow

### Phase 1: Capture (`workflow-monitor:capture-complete`)

1. **Log execution even