Assesses PopKit plugin efficiency with metrics for context usage, token consumption, lazy loading, startup performance, and file access. Outputs JSON score, bottlenecks, and optimizations.
From popkit-opsnpx claudepluginhub jrc1883/popkit-ai --plugin popkit-opsThis skill uses the workspace's default tool permissions.
checklists/context-efficiency.jsonchecklists/file-access-patterns.jsonchecklists/startup-performance.jsonscripts/analyze_loading.pyscripts/calculate_efficiency.pyscripts/measure_context.pystandards/context-efficiency.mdstandards/file-access.mdstandards/startup-performance.mdstandards/token-consumption.mdDesigns and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Provides concrete, reproducible performance assessment for PopKit plugins using:
python skills/pop-assessment-performance/scripts/measure_context.py packages/plugin/
python skills/pop-assessment-performance/scripts/analyze_loading.py packages/plugin/
python skills/pop-assessment-performance/scripts/calculate_efficiency.py packages/plugin/
Read and apply checklists in order:
checklists/context-efficiency.json - Context window usagechecklists/startup-performance.json - Plugin initializationchecklists/file-access-patterns.json - Read/write efficiencyCombine automated metrics with checklist results for final performance report.
| Standard | File | Key Checks |
|---|---|---|
| Context Efficiency | standards/context-efficiency.md | CE-001 through CE-008 |
| Startup Performance | standards/startup-performance.md | SP-001 through SP-006 |
| File Access | standards/file-access.md | FA-001 through FA-008 |
| Token Consumption | standards/token-consumption.md | TC-001 through TC-006 |
| Metric | Target | Warning | Critical |
|---|---|---|---|
| Skill Prompt Size | <2000 tokens | 2000-4000 | >4000 |
| Agent Prompt Size | <5000 tokens | 5000-8000 | >8000 |
| Tier-1 Agent Count | <=15 | 16-20 | >20 |
| File Reads/Operation | <5 | 5-10 | >10 |
| Startup Files | <10 | 10-20 | >20 |
Returns JSON with:
efficiency_score: 0-100 (higher = better)metrics: Collected performance measurementsbottlenecks: Identified performance issuesoptimizations: Recommended improvements