benchmark-optimization-loop
🤖 AI Summary
This skill takes vague performance goals (e.g., "make it 20x faster") and runs a bounded, measurable optimization loop: it measures a baseline, generates one-hypothesis-at-a-time code variants, runs them against a correctness gate, and rejects failures until the search budget (max variants/time/spend) is exhausted.
How to Install
Claude Code:
git clone --depth 1 https://github.com/affaan-m/ECC.git && cp ECC/skills/benchmark-optimization-loop ~/.claude/skills/benchmark-optimization-loop -r# Benchmark Optimization Loop
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.
## Required Baseline
Do not optimize until these exist:
- the operation being optimized;
- the correctness gate that must stay green;
- the metric: wall time, p95 latency, rows/sec, cost/run, memory, error rate;
- the current baseline;
- the search budget: max variants, max time, max spend, max data impact.
If the user asks for an unrealistic target, keep the ambition but make the loop
bounded and measurable.
## Loop
1. Measure the baseline.
2. Identify bottlenecks from evidence.
3. Generate variants that test one hypothesis each.
4. Run variants with the same input shape.
5. Reject variants that fail correctness, safety, or reproducibility.
6. Promote the fastest safe variant.
7. Codify the winning path in a script, command, test, config, or doc.
8. Rerun the baseline and winner to confirm the delta.
## Variant Table
Track variants like this:
```text
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
```
## Recursive Search
For recursive or hyperparameter work:
- persist every run to a ledger;
- compare against the prior accepted winner, not only the previous run;
- keep a holdout or replay check;
- stop when improvement is within noise, correctness fails, cost exceeds the
budget, or the search starts changing more variables than it can explain.
Use phrases like "best measured safe variant" instead of "global optimum" unless
the search space was actually exhaustive.
## Promotion Gate
A variant cannot become the new default until:
- correctness tests pass;
- the performance delta is repeated or explained;
- rollback is obvious;
- the change is encoded in source control or a durable runbook;
- the final summary includes exact commands and measurements.
Details
| Category | Coding → generation |
| Source | affaan-m/ECC |
| SKILL.md | View on GitHub → |
| Repo Stars | ★ 220.5K |
| Est. per Skill | N/A (shared across 121 skills from this repo) |
| Difficulty | Intermediate |
| Risk Level | N/A |
Related Skills
jq
jq — JSON Querying and Transformation Overview jq is the standard CLI tool for querying and reshapin
angular-ui-patterns
Angular UI Patterns Core Principles Never show stale UI - Loading states only when actually loading
animejs-animation
Anime.js Animation Skill Anime.js is a lightweight but extremely powerful JavaScript animation engin
cc-skill-continuous-learning
cc-skill-continuous-learning Development skill skill. When to Use This skill is applicable to execut
Works Well With
Skills from the same repository — often designed to work together
accessibility
Accessibility (WCAG 2.2) This skill ensures that digital interfaces are Perceivable, Operable, Under
agent-architecture-audit
Agent Architecture Audit A diagnostic workflow for agent systems that hide failures behind wrapper l
agent-eval
Agent Eval Skill A lightweight CLI tool for comparing coding agents head-to-head on reproducible tas