ce-optimize
Run metric-driven iterative optimization loops. Define a measurable goal, build measurement scaffolding, then run parallel experiments that try many approaches, measure each against hard gates and/or LLM-as-judge quality scores, keep improvements, and converge toward the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation. Inspired by Karpathy's autoresearch, generalized for multi-file code changes and non-ML domains.
Best for Systematic optimization pro…Works with GitHubLow risk
⌘source
- author
@EveryInc- language
- TypeScript
★15kstars
1.2kforks
Apr 18, 2026
✦overview.md
Key Features
- ·Run parallel experiments with multiple approaches
- ·Measure results against hard gates and LLM-as-judge quality scores
- ·Keep improvements and converge toward best solution
- ·Define measurable goals with measurement scaffolding
- ·Optimize clustering quality, search relevance, build performance, or prompt quality
Use Cases
- →Improving search relevance through systematic experimentation
- →Optimizing build performance with parallel test runs
- →Enhancing prompt quality through iterative refinement
- →Increasing clustering quality with metric-driven approaches
Best for
- ✓Systematic optimization projects
- ✓Metric-driven development teams
name
ce-optimize
description
Run metric-driven iterative optimization loops. Define a measurable goal, build measurement scaffolding, then run parallel experiments that try many approaches, measure each against hard gates and/or LLM-as-judge quality scores, keep improvements, and converge toward the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation. Inspired by Karpathy's autoresearch, generalized for multi-file code changes and non-ML domains.
argument-hint:[path to optimization spec YAML, or describe the optimization goal]
Iterative Optimization Loop
Run metric-driven iterative optimization. Define a goal, build measurement scaffolding, then run parallel experiments that converge toward the best solution.
Interaction Method
Use the platform's blocking question tool when available (AskUserQuestion in Claude Code, request_user_input in Codex, ask_user in Gemini). Otherwise, present numbered options in chat and wait for the user's reply before proceeding.
Input
<optimization_input> #$ARGUMENTS </optimization_input>
If the input above is empty, ask: "What would you like to optimize? Describe the goal, or provide a path to an optimization spec YAML file."
Optimization Spec Schema
Reference the spec schema for validation:
references/optimize-spec-schema.yaml
Experiment Log Schema
Reference the experiment log schema for state management:
references/experiment-log-schema.yaml
Quick Start
For a first run, optimize for signal and safety, not maximum throughput:
- Start from
references/example-hard-spec.yamlwhen the metric is objective and cheap to measure - Use
references/example-judge-spec.yamlonly when actual quality requires semantic judgment
$install
1-click copynpx skills add EveryInc/compound-engineering-plugin --skill ce-optimizeSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
1/ 5
poorThe SKILL.md content is hard to understand and quite ambiguous.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
1/ 5
not actionableThe SKILL.md is hard to act on; an agent would not know what to do.