self-improving-meta

Log meta-learnings and apply fixes to core agent infrastructure files.

Updated Apr 13, 2026

Search Tags:#hooks #infrastructure #coordination #memory-management #prompt-management #metaleaning

Ready to run

npx skills add https://github.com/jose-compu/self-improving-skills --skill self-improving-meta

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: self-improving-meta
Source: https://github.com/jose-compu/self-improving-skills/tree/main/self-improving-meta
Command: npx skills add https://github.com/jose-compu/self-improving-skills --skill self-improving-meta

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Improves the agent infrastructure itself — core prompt files (AGENTS.md, SOUL.md, TOOLS.md, CLAUDE.md), skill definitions, hooks, rules, extensions, and memory management.

Core Features & Use Cases

Centralizes meta-learnings and feature requests to stable files like LEARNINGS.md, META_ISSUES.md, and FEATURE_REQUESTS.md.
Propagates vetted fixes across shared infrastructure so all skills inherit improvements.
Detects and resolves prompt drift, rule conflicts, context bloat, and memory degradation, enabling safer meta-skill extractions.

Quick Start

Run a meta-learnings review after major changes to capture infrastructure improvements and propagate fixes across shared files.

Frequently Asked Questions about self-improving-meta

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

FAQPage Schema

How do I prevent prompt drift in agent infrastructure across multiple sessions?▼

To prevent prompt drift in agent infrastructure, this skill logs meta-learnings and applies targeted fixes to core prompt files. It detects drift across sessions and promotes widely applicable improvements into shared infrastructure for consistent agent behavior.

What is the best way to resolve rule conflicts and context bloat in agent prompts?▼

Resolving rule conflicts and context bloat involves centralizing meta-learnings into stable files and hardening core prompt files. This process detects infrastructure degradation and propagates vetted fixes across shared components to maintain optimal agent performance.

How do I propagate infrastructure fixes across all agent skills safely?▼

You can propagate infrastructure fixes safely by using hook validation and meta-extraction workflows. This ensures that vetted improvements to core prompt files, memory policies, and hooks are inherited consistently across all skills without breaking existing functionality.

Can I use this to fix memory degradation and misinterpretations in my agents?▼

Yes, you can fix memory degradation and misinterpretations by operating across all sessions to detect these issues. It applies improvements to memory policies and core infrastructure files, ensuring agents handle context and instructions accurately over time.

Does this skill require existing core prompt files like AGENTS.md or CLAUDE.md to work?▼

The skill improves existing core prompt files such as AGENTS.md, CLAUDE.md, SOUL.md, and TOOLS.md. It consolidates feature requests and learnings into files like LEARNINGS.md, hardening the current agent setup rather than generating an infrastructure from scratch.

When should I run a meta-learnings review for my agent infrastructure?▼

You should run a meta-learnings review after major changes to capture infrastructure improvements and propagate fixes. This workflow detects prompt drift, rule conflicts, and memory degradation, ensuring your shared files remain stable across all active sessions.