meta-optimize

Analyze ARIS usage logs and generate patch-ready optimizations for SKILL.md and workflows.

Updated Apr 1, 2026
One-click install
npx skills add https://github.com/Wenwen555/ARIS-LVLM --skill meta-optimize
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: meta-optimize
Source: https://github.com/Wenwen555/ARIS-LVLM/tree/main/skills/meta-optimize
Command: npx skills add https://github.com/Wenwen555/ARIS-LVLM --skill meta-optimize

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyzes ARIS usage logs to identify opportunities to improve SKILL.md prompts, reviewer guidance, and default workflow settings, delivering patch-ready recommendations.

Core Features & Use Cases

  • Surface actionable optimization targets from usage data (which skills, commands, and parameters are most used or overridden).
  • Propose minimal, reversible patches with justifications grounded in logs.
  • Coordinate cross-skill improvements via an outer-loop harness workflow, improving reliability and efficiency.

Quick Start

Run /meta-optimize after ARIS has collected sufficient logs to generate a patch-ready optimization proposal.

Frequently Asked Questions about meta-optimize

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

FAQPage Schema
How do I optimize ARIS workflows using usage logs?

ARIS workflow optimization analyzes usage logs at .aris/meta/events.jsonl to identify patterns, generating patch-ready recommendations for SKILL.md prompts and workflow defaults.

What is the minimum data needed to analyze skill invocation logs?

Analyzing skill invocation logs requires event data located at .aris/meta/events.jsonl with a minimum of 5 skill invocations to accurately identify usage patterns and propose optimizations.

How do I generate reversible prompt patches from analytics data?

Prompt patches are generated from analytics data by identifying overridden parameters and proposing minimal, reversible changes to SKILL.md and reviewer guidance grounded in actual usage logs.

Can I target a specific skill for harness optimization instead of all skills?

Yes, the harness optimization workflow can apply across all skills or target a specific skill if specified, generating concrete optimizations for reviewer prompts and workflow defaults.

Why are my ARIS optimization recommendations not reviewer-gated?

ARIS optimization recommendations are strictly reviewer-gated to ensure changes are minimal and reversible, preventing unverified patches from directly modifying SKILL.md prompts or workflow defaults.