Start code logging quality inspection and improvement

Use for requests like: "Check if logs are okay", "Improve logging", "Any issues with log code?", "Check logging before production deployment", "Too many console.log statements", "Is error logging working properly?", "Optimize logs"

Automatically handles:

• Auto-detect logging patterns in code

• Provide language-specific optimization suggestions (JavaScript, Python, Java, Go, etc.)

• Validate production environment safety

• Observability improvement guidance

3-step automated workflow: 1 Logging quality analysis → 2 Improvement roadmap generation → 3 Deployment safety validation

Settings (optional): environment, serviceCriticality, targetScore, maxChanges, focus Defaults: production environment, high criticality, 80-point target, 5 changes max, comprehensive analysis

Logging code quality analysis and issue diagnosis

When used: Automatically executed after setup_analysis_session or when direct logging analysis is needed

Analysis items:

• Detect console.log/print overuse patterns

• Sensitive information exposure risks (password, token, email, etc.)

• Missing error handling and context loss

• Performance blocking logging (synchronous I/O)

• Lack of observability (correlation ID, tracing)

• DEBUG logging inappropriate for production

Output: Provides professional logging analysis guidelines to LLMs for accurate quality assessment

Supported languages: JavaScript, TypeScript, Python, Java, Go, C++, C#, Ruby Environment: differentiated analysis for development, production

Generate logging improvement roadmap and specific modification suggestions

When used: Automatically executed after analyze_logging completion or when direct improvement suggestions are needed

What it provides:

• Immediately applicable Quick Wins (1-2 hours)

• Phased migration plan (prevents Big Bang approach)

• Line-by-line precise modification code

• ROI-based prioritization (cost vs. benefit)

• Implementation difficulty and estimated time required

• Required library/configuration guidance

Improvement patterns:

• console.log → structured logger (winston, pino)

• Error ignoring → complete context preservation

• Synchronous logging → asynchronous performance optimization

• Sensitive data exposure → complete removal/masking

• Untraceable → correlation ID addition

Operational safety: Preserve existing logic, incremental application, rollback plan

Final logging safety validation before production deployment

When used: Automatically executed after suggest_improvements completion or when final pre-deployment inspection is needed

Strict GO/NO-GO determination:

• Immediate NO-GO if even one Critical issue exists

• Comprehensive evaluation of security, performance, operational stability

• Focus on actual service failure possibilities

5-stage safety validation: 1 Security Gate: Complete sensitive data blocking (password, token, PII) 2 Performance Gate: Prevent service performance blocking 3 Observability Gate: Ensure incident response capability 4 Operational Gate: Monitoring system integration 5 Compliance Gate: Regulatory compliance (GDPR, audit)

Deployment decision:

• GO: Safe to deploy

• CONDITIONAL GO: Deploy with caution due to limited risks

• NO-GO: Deployment prohibited, fixes required

Critical Blockers: console.log, sensitive data exposure, synchronous I/O logging, error ignoring