Skills

Skills are folders of instructions, scripts, and resources that extend Ante's capabilities. They follow the open Agent Skills format, making them portable across compatible agent products.

Creating a skill

A skill is a directory containing a SKILL.md file:

commit/
└── SKILL.md

SKILL.md uses YAML frontmatter followed by Markdown instructions:

---
name: commit
description: Create a git commit with a descriptive message following conventional commit format.
---

Look at the current git diff and create a commit with a clear,
descriptive message that follows conventional commit format.
Use `git add` to stage relevant files first.

Example: review skill with tools and references

review/
├── SKILL.md
└── references/
    └── checklist.md

---
name: review
description: Review code changes for bugs, security issues, and style.
allowed-tools:
  - Read
  - Glob
  - Grep
---

Review the code at $ARGUMENTS for bugs, security vulnerabilities, style issues, and missing error handling.

See [checklist](references/checklist.md) for the full review checklist.

note

The allowed-tools field also accepts a comma-separated string ("Read, Glob, Grep") or a space-separated string ("Read Glob Grep") in addition to the YAML array format.

Skill directories

Directory	Scope
~/.ante/skills/	User-level (available in all projects)
.agents/skills/	Project-level
.ante/skills/	Project-level
.claude/skills/	Project-level (Claude Code compatibility)

SKILL.md frontmatter

Field	Required	Default	Description
name	No	Directory name	Identifier for the skill
description	No	First paragraph	What this skill does and when to use it
argument-hint	No	—	Hint text for expected arguments (e.g. <path>)
user-invocable	No	true	Whether the skill can be invoked via slash command
disable-model-invocation	No	false	Prevents the model from invoking this skill automatically
allowed-tools	No	—	Pre-approved tools the skill can use
metadata	No	—	Arbitrary key-value pairs

Optional directories

my-skill/
├── SKILL.md           # Required — instructions
├── scripts/           # Executable code the agent can run
├── references/        # Additional docs loaded on demand
└── assets/            # Templates, schemas, data files

How skills are discovered

Skills are discovered in precedence order (later overrides earlier):

1. System-level (built-in skills)
2. ~/.ante/skills/ (user-level)
3. .agents/skills/ (project-level)
4. .ante/skills/ (project-level)
5. .claude/skills/ (project-level)

Using skills

/commit
/review src/core/session.rs

The $ARGUMENTS placeholder in the skill instructions is replaced with whatever you pass after the skill name.

Learn more

See the full specification for details on naming conventions, progressive disclosure, and validation.