skills.rest
wangrenzhu-ola
wangrenzhu-olaCOMMUNITY
Explore all skills by this author →
GitHub

gh:optimize

Automate optimization loops by measuring code variants against a shared harness.

2|1|Updated Apr 17, 2026
Search Tags:#optimization#guardrails#git-worktree#experiments#llm-judge#crash-recovery#measurement-harness
One-click install
npx skills add https://github.com/wangrenzhu-ola/GaleHarnessCodingCLI --skill gh-optimize
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gh:optimize
Source: https://github.com/wangrenzhu-ola/GaleHarnessCodingCLI/tree/main/plugins/galeharness-cli/skills/gh-optimize
Command: npx skills add https://github.com/wangrenzhu-ola/GaleHarnessCodingCLI --skill gh-optimize

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Skill orchestrates metric-driven optimization loops by repeatedly evaluating multiple code or configuration variants against a shared measurement harness, then surfacing a durable best solution. It emphasizes reproducibility, guardrails, and crash-safe logging to support long-running experiments.

Core Features & Use Cases

  • Orchestrates iterative experiments with a repeatable harness and explicit guardrails
  • Supports both objective hard metrics and LLM-as-judge scoring for qualitative targets
  • Manages hypothesis backlog, per-experiment worktrees, and persistent result logs for auditability
  • Suitable for tuning memory, latency, clustering quality, prompt efficiency, and other measurable outcomes

Quick Start

Provide the optimization goal or path to a spec YAML file to start the workflow.

Frequently Asked Questions about gh:optimize

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

FAQPage Schema
How do I automate iterative code optimization with measurable metrics?▼

Automate iterative code optimization by orchestrating repeated evaluations of code variants against a shared measurement harness, surfacing the best durable solution with disk-backed logs.

Can I use LLM-as-judge scoring for qualitative optimization targets?▼

LLM-as-judge scoring supports qualitative optimization targets by evaluating code variants alongside objective hard metrics within the same measurement harness.

How does crash recovery work for long-running optimization experiments?▼

Crash recovery for long-running optimization experiments relies on guardrails and disk-backed logs to ensure reproducibility and auditable results across iterative runs.

What is the best way to manage multiple code variants during tuning experiments?▼

Manage multiple code variants during tuning experiments by utilizing per-experiment git worktrees and tracking a hypothesis backlog to maintain provenance and auditability.

Does this optimization workflow support tuning latency and prompt efficiency?▼

Latency and prompt efficiency tuning are supported by the metric-driven optimization workflow, which accommodates measurable outcomes like memory, latency, and clustering quality.

How do I start a metric-driven optimization loop?▼

Start a metric-driven optimization loop by providing an optimization goal or a path to a spec YAML file to initialize the automated workflow.

Related Skills

Explore More Software Engineering Skills→
psd401psd401
2

meta-experiment

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

Official
Advanced
LeiisawesomeLeiisawesome

research-workflow

Automate governance and reproducibility for quantitative research workflows.

Community
Advanced
wshobsonwshobson
38.6k

llm-evaluation

Implement automated metrics, human feedback, and LLM-as-Judge evaluations for LLM applications.

Community
Advanced
SeemSeamSeemSeam
17

mobile-device-quality

Validate mobile apps using simulator, emulator, device, log, and crash evidence.

Community
Intermediate