majiayu000 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
# 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)
- Log execution events - Commands, outputs, timing
- Tag anomalies - Failures, timeouts, inefficiencies
- Store evidence - For reproducibility
Phase 2: Analyze (workflow-monitor:analysis-complete)
- Classify issues - Error type, severity, scope
- Identify root cause - What triggered the issue
- Suggest fix - What would prevent recurrence
Phase 3: Report (workflow-monitor:report-generated)
- Generate issue body - Structured format
- Assign labels - workflow, bug, enhancement
- Link evidence - Command outputs, session info
Phase 4: Create Issue (workflow-monitor:issue-created)
- Check for duplicates - Search existing issues
- Create if unique - Via gh CLI
- Link to session - For traceability
Issue Template
## Background
Detected during workflow execution on [DATE].
**Source:** [workflow name] session [session-id]
## Problem
[Description of the error or inefficiency]
**Evidence:**
[Command that failed or was inefficient] [Output excerpt]
## Suggested Fix
[What should change to prevent this]
## Acceptance Criteria
- [ ] [Specific fix criterion]
- [ ] Tests added for new behavior
- [ ] Documentation updated
---
*Created automatically by workflow-monitor*
Configuration
# .workflow-monitor.yaml
enabled: true
auto_create_issues: false # Require approval before creating
severity_threshold: "medium" # Only report medium+ severity
efficiency_threshold: 0.7 # Flag workflows below 70% efficiency
detection:
command_failures: true
timeouts: true
retry_loops: true
context_exhaustion: true
tool_misuse: true
efficiency:
verbose_output_limit: 500
max_file_reads: 2
parallel_detection: true
Guardrails
- No duplicate issues - Check existing issues before creating
- Approval required - Unless
auto_create_issues: true - Evidence required - Every issue must have reproducible evidence
- Rate limiting - Max 5 issues per session
Required TodoWrite Items
workflow-monitor:capture-completeworkflow-monitor:analysis-completeworkflow-monitor:report-generatedworkflow-monitor:issue-created(if issue created)
Integration Points
imbue:evidence-logging: Captures execution evidencesanctum:fix-workflow: Implements suggested fixes- Hooks: Can be triggered by session hooks for automatic monitoring
Output Format
Efficiency Report
## Workflow Efficiency Report
**Session:** [session-id]
**Duration:** 12m 34s
**Efficiency Score:** 0.72 (72%)
### Issues Detected
| Type | Count | Impact |
|------|-------|--------|
| Verbose output | 3 | Medium |
| Redundant reads | 2 | Low |
| Sequential tasks | 1 | Medium |
### Recommendations
1. Use `--quiet` flags for npm/pip commands
2. Cache file contents instead of re-reading
3. Parallelize independent file operations
### Create Issues?
- [ ] Issue 1: Verbose output from npm install
- [ ] Issue 2: Redundant file reads in validation
Related Skills
imbue:evidence-logging: Evidence capture methodologysanctum:fix-workflow: Workflow improvement commandimbue:proof-of-work: Validation methodology
Status: Skeleton implementation. Requires:
- Hook integration for automatic monitoring
- Efficiency scoring algorithm
- Duplicate detection logic