performance-monitor
Skill0 starsChanged 13 months agoMITView on GitHub
Track execution metrics and performance of skills including execution time, memory usage, and success rates
- Installs packages
4 other projects use a version of this.
Adopted by
Most recently taken up by
- mysleekdesigns/crawlforge-mcptheir own version, first seen Oct 11, 2026
- code-with-mehedi/nextjs-claude-startertheir own version, first seen Aug 25, 2026
- jshsakura/awesome-opencode-skillstheir own version, first seen Jul 8, 2026
- belokonm/claude-supercode-skillstheir own version, first seen Jan 12, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- jshsakura/awesome-opencode-skills★ 31same name
- belokonm/claude-supercode-skills★ 11same name
- mysleekdesigns/crawlforge-mcp★ 6same name
- code-with-mehedi/nextjs-claude-starter★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- aws-cost-analyzerSkill
- code-reviewerSkill
- dast-scannerSkill
- database-optimizerSkill
- dependency-checkerSkill
- git-workflowSkill
- java-profilerSkill
- jira-integrationSkill
- memory-analyzerSkill
- penetration-testerSkill
- python-profilerSkill
- refactoring-assistantSkill
- sast-analyzerSkill
- security-scannerSkill
- skill-validatorSkill
- tdd-workflowSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
After implementing new skills to establish baselines
- Distinctive: line 14
When investigating performance degradation
- Distinctive: line 17
When debugging memory issues
- Distinctive: line 186
Check for inefficient algorithms (O(n²))
- Distinctive: line 187
Look for unnecessary I/O operations
- Distinctive: line 191
Check for memory leaks
- Distinctive: line 193
Use generators instead of lists
- Distinctive: line 200
Add retry logic for transient failures
- Distinctive: line 231
Keep last 1000 executions per skill
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Performance Monitor
Overview
Tracks and analyzes performance metrics for Claude Code skills and tools, recording execution time, memory usage, success/failure rates, and generating comprehensive performance reports.
When to Use
- After implementing new skills to establish baselines
- When investigating performance degradation
- For capacity planning and resource optimization
- During performance optimization cycles
- When debugging memory issues
Capabilities
1. Metrics Collection
- Execution time tracking
- Memory usage monitoring (MB)
- Success/failure rate recording
- Timestamp logging
- Error message capture
2. Statistical Analysis
- Average/min/max execution times
- Memory usage patterns
- Success rate calculations
- Usage frequency tracking
- Trend analysis
3. Performance Reporting
- Summary reports by skill
- Top slowest skills identification
- Memory-intensive skill detection
- Most-used skills ranking
- Failure rate analysis
Usage
Generate Performance Report
python .claude/skills/performance-monitor/performance-monitor.py reportRun Test Execution with Monitoring
python .claude/skills/performance-monitor/performance-monitor.py testCustom Metrics File
python .claude/skills/performance-monitor/performance-monitor.py report custom_metrics.jsonReport Output Example
================================================================================
PERFORMANCE MONITORING REPORT
================================================================================
Total recorded executions: 147
Tracked skills: 12
Skill Executions Avg Time Avg Memory Success Rate
--------------------------------------------------------------------------------
database-optimizer 45 2.341s 124.5MB 100.0%
python-profiler 32 1.892s 89.3MB 96.9%
sast-analyzer 28 5.123s 256.7MB 100.0%
aws-cost-analyzer 18 3.445s 178.2MB 94.4%
memory-analyzer 12 4.567s 312.1MB 91.7%
code-reviewer 8 1.234s 67.8MB 100.0%
================================================================================
PERFORMANCE INSIGHTS
================================================================================
🐌 Slowest Skills (Average):
• sast-analyzer: 5.123s
• memory-analyzer: 4.567s
• aws-cost-analyzer: 3.445s
💾 Most Memory Intensive:
• memory-analyzer: 312.1MB
• sast-analyzer: 256.7MB
• aws-cost-analyzer: 178.2MB
⭐ Most Used Skills:
• database-optimizer: 45 executions
• python-profiler: 32 executions
• sast-analyzer: 28 executions
⚠️ Skills with Failures:
• memory-analyzer: 1 failures (8.3%)
• aws-cost-analyzer: 1 failures (5.6%)
• python-profiler: 1 failures (3.1%)Instrumenting Your Code
Python Decorator
from .claude.skills.performance-monitor import performance_monitor
@monitor_performance('my-custom-skill')
def my_skill_function():
# Your code here
passManual Recording
from .claude.skills.performance-monitor import PerformanceMonitor
import time
monitor = PerformanceMonitor()
start = time.time()
try:
# Your code
success = True
error = None
except Exception as e:
success = False
error = str(e)
execution_time = time.time() - start
memory_used = 50 # MB
monitor.record_execution(
skill_name='my-skill',
execution_time=execution_time,
memory_used=memory_used,
success=success,
error=error
)Data Storage
Metrics are stored in JSON format at performance_metrics.json:
[
{
"timestamp": "2025-01-15T10:30:45.123456",
"skill": "python-profiler",
"execution_time": 1.892,
"memory_used_mb": 89.3,
"success": true,
"error": null
}
]Performance Optimization Guidelines
Execution Time
- Target: < 5s for most skills
- Acceptable: 5-10s for complex analysis
- Investigate: > 10s execution time
Memory Usage
- Light: < 100MB
- Moderate: 100-300MB
- Heavy: > 300MB (review for optimization)
Success Rate
- Excellent: > 98%
- Good: 95-98%
- Needs attention: < 95%
Troubleshooting
High Execution Time
- Profile the skill with cProfile or pyinstrument
- Check for inefficient algorithms (O(n²))
- Look for unnecessary I/O operations
- Review external API calls
High Memory Usage
- Check for memory leaks
- Review large data structure usage
- Use generators instead of lists
- Implement streaming for large files
Low Success Rate
- Review error messages in metrics file
- Add error handling
- Validate input data
- Add retry logic for transient failures
CI/CD Integration
GitHub Actions
name: Performance Monitoring
on: [push]
jobs:
monitor:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Run with monitoring
run: |
python .claude/skills/performance-monitor/performance-monitor.py test
- name: Generate report
run: |
python .claude/skills/performance-monitor/performance-monitor.py reportRequirements
pip install psutil # For memory monitoringMetrics Retention
- Keep last 1000 executions per skill
- Archive monthly reports
- Clear old metrics:
rm performance_metrics.json
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

