meta-optimize

Name: meta-optimize
Availability: InStock
Author: lightrain-a

Analyze ARIS usage logs to propose ranked optimizations for harness components.

Updated May 20, 2026

Search Tags:#skill optimization #usage analytics #prompt tuning #aris #workflow tuning #evidence-based patches #meta-harness

Ready to run

npx skills add https://github.com/lightrain-a/medtrace-aris --skill meta-optimize-lightrain-a

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: meta-optimize
Source: https://github.com/lightrain-a/medtrace-aris/tree/main/.vendor/aris/skills/meta-optimize
Command: npx skills add https://github.com/lightrain-a/medtrace-aris --skill meta-optimize-lightrain-a

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It turns accumulated ARIS usage logs into evidence-backed improvements for ARIS’s own SKILL.md prompts, reviewer gates, and workflow defaults, reducing repeated manual overrides and recurring failures.

Core Features & Use Cases

Log-driven harness optimization: Analyzes .aris/meta/events.jsonl to find frequent overrides, tool failure patterns, and convergence behavior.
Targeted patch proposals: Ranks optimization opportunities and generates minimal diffs to SKILL.md components for safer, incremental changes.
Reviewer-gated recommendations: Cross-model review is used to validate that proposed patches are supported by evidence and won’t break common workflows.
Human-in-the-loop application: Produces a report and supports explicit user-approved application with backups and change logging.

Quick Start

Run meta-optimize on your ARIS project after enabling Claude Code meta logging and collecting at least 5 logged workflow runs.

Frequently Asked Questions about meta-optimize

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

FAQPage Schema

How do I optimize prompt workflows using usage logs?▼

You can optimize prompt workflows by analyzing accumulated usage logs to identify frequent parameter overrides and tool failure patterns, then generating minimal patch diffs for SKILL.md components and convergence rules.

What is evidence-based prompt tuning for AI agent harnesses?▼

Evidence-based prompt tuning uses real auto-review-loop behavior and tool failure data from execution logs to propose targeted improvements to reviewer gates and workflow defaults instead of manual adjustments.

How many logged workflow runs do I need before optimizing ARIS skills?▼

You need at least 5 logged workflow runs in your events log after enabling Claude Code meta logging to start analyzing tool failures and generating targeted patch proposals for your ARIS project.

Can I apply workflow tuning patches automatically without manual review?▼

No, workflow tuning requires a human-in-the-loop application flow where cross-model adversarial review validates proposed patches first, followed by explicit user approval before applying changes with backups and change logging.

What is the best way to reduce recurring tool failures in AI research workflows?▼

The best way to reduce recurring tool failures is analyzing auto-review-loop behavior and override frequency from real usage logs to rank optimization targets and generate evidence-grounded patches for workflow defaults.

Why does meta-optimization require cross-model adversarial review?▼

Cross-model adversarial review validates that proposed optimization patches are supported by evidence from usage logs and will not break common workflows, ensuring safer incremental changes before user-approved application.