---
title: "Skills"
description: "Agent Plugins uses the [Agent Skills specification](https://agentskills.io/specification) without redefining the skill format. Agent Plugins defines only where skills are discovered inside a plugin and how failures are i"
canonical: https://agentpluginsdirectory.com/spec/plugin-authors/skills
last-updated: 2026-09-21
---

# Skills

Agent Plugins uses the [Agent Skills specification](https://agentskills.io/specification) without redefining the skill format. Agent Plugins defines only where skills are discovered inside a plugin and how failures are isolated.

## Directory layout
Place each skill in an immediate child directory of `skills/`:

```text
skills/
└── deploy/
    ├── SKILL.md
    ├── scripts/
    │   └── rollback.sh
    ├── references/
    │   └── runbook.md
    ├── assets/
    └── examples/
```

An immediate child is a discovered skill when its path named exactly `SKILL.md` resolves to a regular file. Clients do not recursively search deeper descendants for additional skills.

## Skill format
`SKILL.md` frontmatter and instructions follow the Agent Skills specification. A skill may contain any additional files and directories it needs. `scripts/`, `references/`, and `assets/` are common conventions described by Agent Skills, not an exhaustive allowlist. The Agent Skills specification is the source of truth for skill validity.

## Failure isolation
If one discovered skill is invalid, the client skips that skill, reports it when practical, and continues loading other skills and component types.

If `skills/` is missing, the plugin is still valid. If the path exists but is not a directory, the skills component type is invalid without invalidating independent components such as MCP servers.