self-improve

Analyze quality signals, optimize prompts, and generate a learning report.

Updated Aug 27, 2026

Search Tags:#prompt engineering #optimization #self-improvement #ai development #skill creation #learning

Ready to run

npx skills add https://github.com/knsiuss/orion --skill self-improve-knsiuss

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: self-improve
Source: https://github.com/knsiuss/orion/tree/main/workspace/skills/self-improve
Command: npx skills add https://github.com/knsiuss/orion --skill self-improve-knsiuss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the process of improving EDITH's performance by analyzing past interactions, optimizing its internal prompts, and identifying potential new skills.

Core Features & Use Cases

Automated Learning Cycle: Triggers EDITH's weekly self-improvement process.
Performance Analysis: Reviews feedback signals to identify areas of struggle.
Prompt Optimization: Proposes and applies improvements to EDITH's mutable prompts.
Skill Discovery: Identifies recurring user workflows that can be turned into new auto-skills.
Reporting: Generates a summary of learning activities and proposed changes.
Use Case: After a period of extensive use, you can manually trigger this skill to ensure EDITH is continuously learning and improving its responses and task execution.

Quick Start

Instruct EDITH to run its self-improvement cycle.

Frequently Asked Questions about self-improve

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

FAQPage Schema

How do I optimize AI prompts automatically based on past interactions?▼

This Skill automates prompt optimization by analyzing past interaction quality signals to identify struggle areas and propose targeted prompt improvements. It requires your explicit approval before applying any mutable prompt changes to the system.

What is the process for identifying recurring user workflows for new skill creation?▼

Identifying recurring workflows for skill creation involves analyzing past user interactions to detect repeated patterns. The system drafts these detected workflows as candidate auto-skills, presenting a learning report for your review and approval.

How do I run an automated learning cycle to analyze AI performance feedback?▼

You run an automated learning cycle by manually triggering the self-improvement process. This cycle reviews performance feedback signals to identify areas where the AI struggles, subsequently proposing prompt optimizations and generating a summary learning report.

Does the AI self-improvement process require manual approval for prompt changes?▼

Yes, the AI self-improvement process requires explicit user approval for prompt changes. It also requires user review of candidate auto-skills drafted from detected recurring workflows before any new skill creation or system modification occurs.

When should I manually trigger an AI self-improvement cycle?▼

You should manually trigger an AI self-improvement cycle after a period of extensive system use. This ensures the system continuously learns from accumulated interaction data, optimizing its responses and task execution capabilities over time.