AI Agent Skills
What are Agent Skills ?
Agent Skills was developed by Anthropic as an open standard and was later adopted by other agent products.
It is an open format for extending the AI Agent capabilities with Knowledge and workflows.
Why Agent Skills?
Agent often don’t have context. Skills give Enhancing Agent Capabilities like,
- Domain Expertise
- Legal Review Processes
- Data Analysis Pipelines
- Presentation Formatting
- Repeatable Workflows
- Multi-Step Tasks
- Consistent Procedures
- Auditable Workflows
- Cross Product Reuse
- Skills-compatible Agents
- Reusable Instructions
- Company Specific Context
How do Agent Skills work ?
- Discovery : Agents Loads skill names and descriptions at startup.
- Activation : The agent reads full instructions when a task matches
- Execution : The agent follows instructions, executing code and loading files
Directory Structure
my-skill/
├── SKILL.md # Required: metadata + instructions
├── scripts/ # Optional: executable code
├── references/ # Optional: documentation
├── assets/ # Optional: templates, resources
└── … # Any additional files or directories
SKILL.md format
The SKILL.md file must contain YAML frontmatter followed by Markdown content.Below are the fields,
| Field | Required | Constraints |
|---|---|---|
name | Yes | Max 64 characters. Lowercase letters, numbers, and hyphens only. Must not start or end with a hyphen. |
description | Yes | Max 1024 characters. Non-empty. Describes what the skill does and when to use it. |
license | No | License name or reference to a bundled license file. |
compatibility | No | Max 500 characters. Indicates environment requirements (intended product, system packages, network access, etc.). |
metadata | No | Arbitrary key-value mapping for additional metadata. |
allowed-tools | No | Space-separated string of pre-approved tools the skill may use. (Experimental) |
Thank You .. !!