Skip to content

Agent Skills

Define reusable behavior via SKILL.md definitions

Agent skills let Anthracode discover reusable instructions from your repo or home directory. Skills are loaded on-demand via the native skill tool—agents see available skills and can load the full content when needed.


Create one folder per skill name and put a SKILL.md inside it. Anthracode searches these locations:

  • Project config: .anthracode/skills/<name>/SKILL.md
  • Global config: ~/.config/anthracode/skills/<name>/SKILL.md
  • Project Claude-compatible: .claude/skills/<name>/SKILL.md
  • Global Claude-compatible: ~/.claude/skills/<name>/SKILL.md
  • Project agent-compatible: .agents/skills/<name>/SKILL.md
  • Global agent-compatible: ~/.agents/skills/<name>/SKILL.md

For project-local paths, Anthracode walks up from your current working directory until it reaches the git worktree. It loads any matching skills/*/SKILL.md in .anthracode/ and any matching .claude/skills/*/SKILL.md or .agents/skills/*/SKILL.md along the way.

Global definitions are also loaded from ~/.config/anthracode/skills/*/SKILL.md, ~/.claude/skills/*/SKILL.md, and ~/.agents/skills/*/SKILL.md.


Each SKILL.md must start with YAML frontmatter. Only these fields are recognized:

  • name (required)
  • description (required)
  • license (optional)
  • compatibility (optional)
  • metadata (optional, string-to-string map)

Unknown frontmatter fields are ignored.


Skills can also be pulled from remote registries. Configure them in anthracode.jsonc:

{
"skills": {
"urls": ["https://skills.sh/.well-known/skills/"]
}
}

Skills are downloaded to a local cache on startup. See skills.sh for the public skill registry.


name should follow these conventions:

  • 1–64 characters
  • Lowercase alphanumeric with single hyphen separators
  • Not start or end with -
  • Not contain consecutive --
  • Match the directory name that contains SKILL.md

Skills that don’t follow these conventions may still be loaded but may not display correctly in the TUI.

Equivalent regex:

^[a-z0-9]+(-[a-z0-9]+)*$

description must be 1-1024 characters. Keep it specific enough for the agent to choose correctly.


Create .anthracode/skills/git-release/SKILL.md like this:

---
name: git-release
description: Create consistent releases and changelogs
license: MIT
compatibility: anthracode
metadata:
audience: maintainers
workflow: github
---
## What I do
- Draft release notes from merged PRs
- Propose a version bump
- Provide a copy-pasteable `gh release create` command
## When to use me
Use this when you are preparing a tagged release.
Ask clarifying questions if the target versioning scheme is unclear.

Anthracode lists available skills in the skill tool description. Each entry includes the skill name and description:

<available_skills>
<skill>
<name>git-release</name>
<description>Create consistent releases and changelogs</description>
</skill>
</available_skills>

The agent loads a skill by calling the tool:

skill({ name: "git-release" })

Control which skills agents can access using pattern-based permissions in anthracode.jsonc:

{
"permission": {
"skill": {
"*": "allow",
"pr-review": "allow",
"internal-*": "deny",
"experimental-*": "ask"
}
}
}
PermissionBehavior
allowSkill loads immediately
denySkill hidden from agent, access rejected
askUser prompted for approval before loading

Patterns support wildcards: internal-* matches internal-docs, internal-tools, etc.


Give specific agents different permissions than the global defaults.

For custom agents (in agent frontmatter):

---
permission:
skill:
"documents-*": "allow"
---

For built-in agents (in anthracode.jsonc):

{
"agent": {
"plan": {
"permission": {
"skill": {
"internal-*": "allow"
}
}
}
}
}

Completely disable skills for agents that shouldn’t use them:

For custom agents:

---
tools:
skill: false
---

For built-in agents:

{
"agent": {
"plan": {
"tools": {
"skill": false
}
}
}
}

When disabled, the <available_skills> section is omitted entirely.


If a skill does not show up:

  1. Verify SKILL.md is spelled in all caps
  2. Check that frontmatter includes name and description
  3. Ensure skill names are unique across all locations
  4. Check permissions—skills with deny are hidden from agents