AI Skills Overview
A comprehensive system of learnable, composable capabilities for effective AI interaction
What Are AI Skills
AI Skills are learned capabilities that enable you to interact with AI systems effectively. Unlike technical tools or model-specific features, skills are cognitive and operational practices that transfer across different platforms and use cases.
Each skill addresses a specific dimension of AI interaction: establishing context, structuring problems, crafting instructions, evaluating outputs, or recovering from errors. Skills are learnable through practice, composable into workflows, and transferable across domains.
Think of skills as the craftsmanship of AI interaction. Tools and models change, but the underlying skills—how to frame problems, communicate requirements, assess quality—remain stable and applicable regardless of technology.
How to Use This Library
Learn Sequentially
Skills build on each other. Foundation skills (Context Management, Abstraction) enable cognitive skills, which enable operational and meta skills. Following the recommended order ensures you have prerequisites for each next skill.
Reference as Needed
Each skill page provides a complete explanation: what the skill is, why it matters, core concepts, common mistakes, and when to use it. You can return to specific pages as a reference when applying skills in practice.
Compose Skills
Real-world tasks require multiple skills. Planning needs Task Decomposition and Reasoning. Evaluation triggers Iteration. Understanding how skills connect enables you to assemble effective workflows for any problem.
Core Skills (Recommended Order)
Ten foundational capabilities that form a complete system for AI interaction
Context Management
Establishes the foundation by providing AI with the right background information
Abstraction
Simplifies complexity by identifying essential elements and filtering noise
Task Decomposition
Breaks complex objectives into independently executable subtasks
Instruction Design
Creates precise directives that eliminate ambiguity and guide execution
Reasoning
Structures thinking to analyze problems and make logical connections
Planning
Sequences and schedules work to achieve objectives efficiently
Tool Use
Extends capabilities by integrating external tools and data sources
Evaluation
Systematically assesses outputs against predefined quality criteria
Iteration
Refines solutions through targeted improvements based on feedback
Error Recovery
Handles failures and implements fallback strategies when execution fails
How These Skills Work Together
Layered Foundation
Skills form a dependency stack. Foundation skills (Context Management, Abstraction) establish the cognitive infrastructure. Cognitive skills (Task Decomposition, Reasoning, Planning) operate on that infrastructure. Operational and Meta skills (Instruction Design, Tool Use, Evaluation, Iteration, Error Recovery) refine and optimize the process.
Skill Synergy
Skills amplify each other. Task Decomposition depends on Abstraction to identify clean boundaries. Planning requires Decomposition to define what to plan. Evaluation triggers Iteration. Error Recovery relies on all other skills to define what "normal" execution looks like. No skill operates in isolation.
Problem-Solving Pipeline
Together, skills form a complete problem-solving pipeline. Context Management provides information. Abstraction extracts structure. Task Decomposition breaks work into units. Instruction Design directs execution. Reasoning solves each unit. Planning sequences the solution. Tool Use extends capabilities. Evaluation validates results. Iteration refines. Error Recovery handles failures.
Composable Capability
You don't need all skills for every task. Simple queries might only require Context Management. Complex analysis needs Foundation, Cognitive, and Meta skills. Understanding each skill's role lets you compose the right subset for your current problem.
Ready to master AI skills?
Start with Context Management