skills.rest
zhuyingqin
zhuyingqinCOMMUNITY
Explore all skills by this author →
GitHub

meta-optimize

Analyze ARIS usage logs to propose evidence-backed SKILL.md optimizations.

1|1|Updated May 19, 2026
Search Tags:#agentic workflows#usage analytics#review-loop#harness engineering#prompt tuning#meta-optimization#log-driven improvement
One-click install
npx skills add https://github.com/zhuyingqin/ARIS-WEB --skill meta-optimize-zhuyingqin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: meta-optimize
Source: https://github.com/zhuyingqin/ARIS-WEB/tree/main/crates/runtime/assets/skills/meta-optimize
Command: npx skills add https://github.com/zhuyingqin/ARIS-WEB --skill meta-optimize-zhuyingqin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Meta-Optimize turns accumulated ARIS usage and failure traces into practical, log-validated improvements for skill harness components, reducing manual tweaks and making future runs more reliable.

Core Features & Use Cases

  • Log-driven skill harness analysis: checks .aris/meta/events.jsonl and derives patterns in frequency, failures, convergence behavior, and human interventions.
  • Ranked optimization targets: identifies high-impact tuning opportunities such as review-loop thresholds, retry behavior, and default prompt/watchword lists.
  • Minimal patch proposals with evidence: generates small diffs tied to specific signals and sends them for cross-model adversarial review before recommending changes.
  • Safe, user-approved application workflow: supports backing up SKILL.md, applying only with approval, and recording changes to .aris/meta/optimizations.jsonl.

Quick Start

Run /meta-optimize to analyze your logged runs and get recommended, reviewer-gated patch diffs for improving ARIS skill defaults.

Frequently Asked Questions about meta-optimize

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

FAQPage Schema
How do I optimize agentic workflow prompts using usage logs?▼

To optimize agentic workflow prompts using usage logs, analyze ARIS execution traces to identify failure patterns and propose evidence-backed minimal diffs to SKILL.md defaults, gated by cross-model reviewer evaluation and user approval.

How does log-driven skill improvement work for recurring workflow failures?▼

Log-driven skill improvement works by reading `.aris/meta/events.jsonl` to rank optimization targets like review-loop thresholds and retry recovery behaviors based on observed frequency and convergence signals.

Can I apply prompt tuning recommendations across all my ARIS skills at once?▼

Yes, you can apply prompt tuning recommendations across one or all ARIS skills, as the analysis identifies common manual interventions across your workflow execution patterns and generates minimal patch proposals with evidence.

What is the safest way to apply meta-optimization patches to harness engineering defaults?▼

The safest way to apply meta-optimization patches is by backing up SKILL.md, applying only user-approved reviewer-gated diffs, and recording the changes to `.aris/meta/optimizations.jsonl` for tracking.

Do I need .aris/meta/events.jsonl logs to run log-driven workflow optimization?▼

Yes, you need accumulated `.aris/meta/events.jsonl` logs to run log-driven workflow optimization, because the analysis derives patterns in failures, convergence behavior, and human interventions from these usage traces.

Related Skills

Explore More Education & Research Skills→
duypham2801duypham2801

meta-optimize

Analyze JSONL event logs and propose reviewer-gated SKILL.md patches.

Community
Advanced
goupup-aigoupup-ai
2

meta-optimize

Analyze ARIS usage logs to propose evidence-backed SKILL.md patch improvements.

Community
Advanced
Mang30Mang30

meta-optimize

Analyze ARIS usage logs to propose evidence-backed SKILL.md patch diffs.

Community
Advanced
catlog22catlog22
76

maestro-ralph

Orchestrate Session/Run workflows with policy checks and terminal decision making.

Community
Advanced