Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency/throughput/cost, or choose the best implementation by repeated measured tests.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "benchmark-optimization-loop" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/benchmark-optimization-loop/SKILL.md 2. Save it as ~/.claude/skills/benchmark-optimization-loop/SKILL.md 3. Reload skills and tell me it's ready
Use this skill to convert "make it 20x faster" or "try 50 recursive optimizations" into a bounded measured loop that can actually improve a system.
Do not optimize until these exist:
If the user asks for an unrealistic target, keep the ambition but make the loop bounded and measurable.
Track variants like this:
Variant | Hypothesis | Command | Time | Correct? | Notes
baseline | current path | npm run job | 120s | yes | stable
batch-500 | fewer round trips | npm run job -- --batch 500 | 42s | yes | winner
parallel-8 | more workers | npm run job -- --workers 8 | 31s | no | rate limited
For recursive or hyperparameter work:
Use phrases like "best measured safe variant" instead of "global optimum" unless the search space was actually exhaustive.
A variant cannot become the new default until:
Coordinate behavior-preserving code refactors with tests, review, and gated commits.
Operate long-running agent workloads with monitoring, security, and lifecycle control.
Build a motion foundation for React/Next.js with safe, accessible performance rules.
Unify multi-channel notifications for routing, deduplication, escalation, and inbox consolidation.
Generate or audit design systems and review styling consistency changes.
Learn SwiftUI architecture, state management, navigation, and performance best practices.