self-improving-ai

Consolidate AI/LLM learnings into reusable Skill units with YAML metadata.

Updated Apr 13, 2026

Search Tags:#ai #llm #rag #skill #learnings #prompt-engineering #model-selection

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Consolidate AI/LLM learnings (model selection, prompt engineering, inference tuning, RAG pipelines, multimodal handling, and guardrail adjustments) into a standalone Skill unit for reuse.

Core Features & Use Cases

Logging learnings across model configurations, prompts, RAG pipelines, evaluation benchmarks, and guardrail tuning.
Generating reusable playbooks and promotion workflows to model selection, prompt libraries, and runbooks, enabling cross-project consistency.
Example use case: extract a recurring RAG tuning pattern from multiple projects and promote it into a skill for broader deployment.

Quick Start

Log a new learning entry describing a model issue or improvement into the .learnings directory to publish it as a reusable skill.

Frequently Asked Questions about self-improving-ai

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

FAQPage Schema

How do I consolidate AI learnings into a reusable skill?▼

Consolidate AI learnings by logging model selection, prompt engineering, and RAG pipeline configurations into a `.learnings` directory to generate a standalone skill unit with YAML frontmatter for reuse.

What is the best way to document LLM prompt engineering patterns for cross-project reuse?▼

Document LLM prompt engineering patterns by categorizing them into reusable playbooks and promotion workflows, enabling cross-project consistency by extracting recurring tuning patterns into a standalone skill.

Can I use this skill to log RAG pipeline tuning adjustments?▼

Yes, you can log RAG pipeline tuning adjustments by creating an entry in the `.learnings` directory, which captures inference tuning and guardrail adjustments to promote into a reusable skill.

How do I structure metadata for AI model selection runbooks?▼

Structure metadata for AI model selection runbooks by ensuring the SKILL.md file includes YAML frontmatter with at least a name and description, plus optional assets, references, and scripts for discovery and integration.

Does this skill support multimodal processing guardrail documentation?▼

Yes, the scope explicitly covers multimodal processing documentation, allowing you to log and categorize guardrail adjustments alongside code-generation and evaluation benchmarks within the skill.

What are the limitations of promoting AI learnings into standalone skills?▼

Limitations include the requirement to maintain precise metadata in YAML frontmatter for discovery and the need to explicitly define categorization and promotion criteria to ensure the consolidated AI learnings remain reusable across projects.