Skip to main content

Extensible Skills: The Open/Closed Principle for AI

Making AI tools transparent, customizable, and extensible

The Extensible Skills Standard has been split into two documents for clarity:


Formal Standard (Normative)

The Extensible Skills Standard defines:

  • Three extensibility categories -- extensible, semi-extensible, not-extensible
  • DCI specification -- Syntax, execution model, and graceful degradation
  • Detection algorithm -- How categories are determined from SKILL.md content
  • Conformance requirements -- What registries must implement

Implementation Guide (Informative)

The Implementation Guide covers:

  • Getting started -- For Claude Code users and SpecWeave users
  • Architecture -- Cascading lookup, DCI blocks, and the Reflect system
  • Real-world examples -- How corrections become persistent preferences
  • Skill memory format -- Structured Markdown for customizations
  • FAQ -- Common questions and troubleshooting

Quick Reference

CategoryMeaningDetection
ExtensibleDCI block with skill-memories. Standard, discoverable customization.DCI block referencing skill-memories
Semi-ExtensibleMentions customization but not through the standard system.Keyword signals or DCI without skill-memories
Not ExtensibleNo customization mechanism. Fork to change.No signals detected

See Also


Version: 4.0.0 Authors: Anton Abyzov License: MIT