Use when the user wants to improve their Claude Code usage efficiency, reduce errors, speed up workflows, or asks "how can I be more productive", "optimize my usage", "what am I doing wrong", or wants suggestions to work more effectively.
From cc-telemetrynpx claudepluginhub layerdynamics/lore --plugin cc-telemetryThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.
Help users optimize their Claude Code workflows by analyzing usage patterns, identifying inefficiencies, and suggesting improvements.
Activate when the user:
Gather usage data:
/cc-telemetry:stats
/cc-telemetry:sessions --tail 10
/cc-telemetry:errors --tail 20
/cc-telemetry:performance
Look for:
Performance Inefficiencies:
Error Patterns:
Workflow Issues:
Unused Potential:
Rank opportunities:
Provide specific, actionable advice:
Format:
## Workflow Optimization Recommendations
### High Priority
1. **[Issue]**: [Description of problem]
- **Impact**: [How much time/errors this causes]
- **Fix**: [Specific action to take]
- **Example**: [Show how to do it]
### Medium Priority
[...same format...]
### Quick Wins
[Small changes with immediate benefit]
Problem: Reading same file multiple times
Tool calls: Read file.txt → Read file.txt → Read file.txt
Solution: Read once, work from memory
Recommendation: After first Read, reference the content mentally instead of re-reading
Problem: Using Read for large files
Read 50MB-log.txt → timeout → error
Solution: Use targeted tools
Recommendation: Use Grep to search large files, or Bash with head/tail
Problem: Multiple small edits
Edit (add line 1) → Edit (add line 2) → Edit (add line 3)
Solution: Batch edits
Recommendation: Make multiple changes in one Edit call
Problem: Enabled plugins never used
Plugins installed: api-docs, test-runner
Usage: 0 calls in 30 days
Solution: Learn and use installed tools
Recommendation: Try /api-docs:generate or /test-runner:run next time you need them
Problem: Manual trial-and-error debugging
Pattern: Edit → Run → Error → Edit → Run → Error (10x)
Solution: Use systematic debugging
Recommendation: Use /systematic-debugging skill before making changes
Problem: Same error 15x in 2 weeks
Error: "PermissionError: /etc/config.txt"
Solution: Fix root cause once
Recommendation: Move config.txt to ~/project/ where you have write access
User: "How can I be faster?"
Analysis:
Recommendations:
Expected impact: 30% faster sessions, 9% fewer errors
User: "I keep making the same mistakes"
Analysis:
Recommendation:
# Workflow Optimization Report
## Current Performance
- Sessions analyzed: [N]
- Avg tools per session: [X]
- Error rate: [Y]%
- Top tools: [list]
## Identified Issues
1. [Issue with frequency and impact]
2. [Issue with frequency and impact]
...
## Recommendations
### High Priority (Do First)
✅ [Action]: [Benefit]
### Medium Priority (Do Soon)
✅ [Action]: [Benefit]
### Low Priority (Nice to Have)
✅ [Action]: [Benefit]
## Expected Impact
Implementing these recommendations should:
- Reduce errors by ~[X]%
- Speed up sessions by ~[Y]%
- Improve tool efficiency by ~[Z]%