skills.rest
lucking7
lucking7COMMUNITY
Explore all skills by this author →
GitHub

ce-optimize

Automates iterative optimization loops for measurable outcomes using configurable metrics and experiment tracking.

Updated Jun 7, 2026
Search Tags:#optimization#metrics#experimentation#algorithm improvement#systematic testing
One-click install
npx skills add https://github.com/lucking7/compound-engineering-skills --skill ce-optimize-lucking7
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ce-optimize
Source: https://github.com/lucking7/compound-engineering-skills/tree/main/skills/ce-optimize
Command: npx skills add https://github.com/lucking7/compound-engineering-skills --skill ce-optimize-lucking7

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates iterative optimization for measurable outcomes such as clustering quality, search relevance, build performance, or any quantifiable goal that benefits from systematic experimentation.

Core Features & Use Cases

  • Iterative Optimization: Run experiments to converge on the best solution by defining a measurable goal, running parallel experiments, measuring results, and keeping improvements.
  • Flexible Metrics: Supports optimization against hard metrics (quantitative) and LLM-as-judge (qualitative).
  • Experiment Tracking: Keeps a persistent log of experiments, allowing for recovery and analysis.
  • Use Case: Optimize clustering quality by running experiments on different clustering algorithms, measuring their performance, and keeping the best one.

Quick Start

Use the ce-optimize skill to run an optimization loop on your clustering algorithm.

Frequently Asked Questions about ce-optimize

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate iterative optimization for search relevance and clustering quality?▼

Iterative optimization requires a well-defined optimization specification and a measurement harness to evaluate results. You must establish quantifiable hard metrics or qualitative judgment criteria before running systematic experiments and keeping improvements.

Can I optimize algorithms using qualitative metrics instead of hard quantitative data?▼

Yes, algorithm optimization supports both hard quantitative metrics and LLM-as-judge qualitative evaluation. You can run systematic experiments against either measurement type to converge on the best solution for your measurable outcomes.

How do I track and recover system optimization experiments?▼

System optimization tracking maintains a persistent log of all experiments, allowing for recovery and analysis. This experiment tracking records each iterative test so you can resume or evaluate previous clustering and search relevance runs.

What is the best way to run parallel experiments for build performance optimization?▼

The best way to run parallel experiments for build performance is to define a measurable goal, execute systematic testing variations, measure the harness results, and keep the improvements. This iterative optimization loop ensures measurable performance gains.

Does systematic experimentation work for any quantifiable goal beyond clustering?▼

Systematic experimentation works for any quantifiable goal like build performance, search relevance, or clustering quality. As long as you provide a well-defined optimization specification and a measurement harness, the iterative process can evaluate and keep improvements.

Related Skills

Explore More Software Engineering Skills→
psd401psd401
2

meta-experiment

Design, run, and interpret controlled experiments to validate software changes.

Official
Advanced
tbroadleytbroadley

read-inspect-eval

Extract samples, messages, events, and metrics from Inspect AI .eval logs.

Community
Intermediate
BoraPerusicBoraPerusic

llm-evaluation

Evaluate LLM outputs with automated metrics and human judgments.

Community
Advanced
PatkikPatkik

scikit-learn

Organize and execute classical machine learning workflows with scikit-learn pipelines.

Community
Advanced