Skip to content
Ontology

Skill Ontology

Skill Ontology organizes individual skills into a structured, composable network, enabling agents to reason, plan, and execute complex tasks as an extensible, maintainable capability system.

How it worksWhen querying for a task, the system traverses this graph to identify the necessary collections and skills to construct a capable agent.

SKILL TAXONOMYSkills16,896 totalhas_categoryDevelopment13,652AI & Generation3,007Research0Data & Science0Business0Testing & QA0has_tagSKILL RELATION GRAPHSimilar ToBelong ToCompose WithDepend Onnextjs-expertreact-patternsseabornmatplotlibplaywrightbrowser-automationSKILL PACKAGE LIBRARYdata-pipeline6 skillsweb-automation5 skillscontent-generation5 skillssecurity-audit5 skillsdevops-automation5 skillsresearch-assistant5 skillsCategorySkillPackageSimilar ToBelong ToCompose WithDepend On
Architecture

Three-Layer Design

How skills are organized from abstract taxonomy to deployable packages.

1. Skill Taxonomy

The Abstraction Layer

The top layer defines the broad categorization and detailed tags of skills. It organizes capabilities into categories such as:

  • Development, AI & Generation, Testing
  • Research, Data & Science
  • Business, Productivity, Security
Purpose: Classification & Vocabulary — 9 categories, 0+ tags

2. Skill Relation Graph

The Semantic Layer

The middle layer instantiates specific skills and defines how they interact. It maps relationships using edges like:

  • compose_with: Combining patterns
  • similar_to: Mapping alternatives
  • depend_on: Establishing prerequisites
  • belong_to: Sub-component within a larger skill
Purpose: Reasoning & Composition — 16,896 skills, 4 relationship types

3. Skill Collection

The Execution Layer

Groups related skills into deployable units. These are the actual functional toolkits agents load at runtime. Examples:

Purpose: Deployment & Execution — 6 collections, 31 skills

Relationship Types

Similar To
similar_to

Functionally equivalent or substitutable skills

Belong To
belong_to

Hierarchical categorization within larger workflows

Compose With
compose_with

Skills that combine together with output-to-input flow

Depend On
depend_on

Prerequisites and environment setup requirements

Skill Graph
Interactive force-graph with 16,896+ skills
Explore →
Collections
6 curated skill bundles
Browse →
Skills Catalog
Browse all skills with taxonomy filters
Browse →
Skills ontology

Explore the skill network

Discover how AI skills connect, compose, and depend on each other across the platform.

Catalog Workspace

Discover agents, MCP servers, and skills in one governed surface

Use structured catalog views to compare readiness, ownership, integrations, and deployment posture before rollout.