Agent Skills

Defines an open standard folder-based structure for encoding AI agent capabilities as reusable skill modules, using SKILL.md specification files to describe procedural knowledge, instructions, and resource dependencies. Skills are version-controlled packages that can be discovered and loaded by compatible agent products, enabling consistent skill definition across multiple downstream agent implementations without requiring each agent to implement its own skill format.

Provides reference SDK tooling that validates skill packages against the Agent Skills specification, ensuring SKILL.md files conform to required structure, contain necessary metadata, and follow best practices for skill definition. Validation occurs before skills are deployed to agent products, catching structural errors, missing required fields, and specification violations early in the development cycle.

Reference library converts SKILL.md definitions and skill package contents into XML representations optimized for agent consumption, enabling agents to parse and understand skill structure, instructions, and resource dependencies in a machine-readable format. This abstraction layer allows agents to work with skills without parsing raw Markdown, and enables optimization of skill descriptions for specific agent models or reasoning approaches.

Enables skills packaged in Agent Skills format to be discovered and loaded by multiple compatible agent products without modification, implementing a standardized discovery mechanism where agent products can locate, validate, and instantiate skills from repositories or local folders. Skills remain portable across agent implementations because they conform to a vendor-neutral specification rather than being tied to a specific agent's internal architecture.

Reference SDK and documentation provide optimization guidance for skill creators, including best practices for writing clear instructions, structuring multi-step workflows, and describing capabilities in ways that maximize agent understanding and execution success. Optimization recommendations cover instruction clarity, resource dependency specification, and skill description formatting to improve agent performance without requiring changes to the underlying Agent Skills format.

Supports version control and distribution of skill packages through standard folder structures and metadata, enabling skills to be versioned, released, and updated while maintaining compatibility with consuming agent products. Skills can be packaged as discrete versions with clear dependency specifications, allowing agents to request specific skill versions and enabling skill maintainers to evolve skills without breaking existing deployments.

Enables creation and management of centralized or distributed skill repositories where Agent Skills-compatible skills can be published, discovered, and shared across the agent ecosystem. Repository integration supports skill discovery by agent products, metadata indexing for searchability, and community contribution workflows, creating a marketplace-like ecosystem for reusable agent capabilities.

Enables encoding of complex multi-step workflows and procedural knowledge as structured skill definitions, allowing agents to understand task decomposition, step sequencing, and conditional logic required for domain-specific processes. Skills can specify prerequisites, dependencies between steps, and success criteria, enabling agents to plan and execute workflows with clear understanding of task structure rather than treating skills as black boxes.

Enables skills to declare external resource dependencies (APIs, databases, files, credentials) and specify how agents should access or provision these resources during skill execution. Skills can specify required resources, optional resources, and resource constraints, allowing agents to validate that necessary resources are available before executing skills and enabling resource provisioning workflows.