Publishing skills
A skill is a self-describing capability an LLM client can load. ARP §6.1 adopts the agentskills.io open spec and the Anthropic Claude Skills frontmatter format verbatim — your skill is portable to all four channels at once.
SKILL.md format
Every skill ships as a single SKILL.md file with YAML frontmatter and a Markdown body:
---
name: my-skill
description: One-sentence summary of what this skill does. Trigger on phrases like "do X", "search for Y".
version: 1.0.0
license: MIT
allowed_tools: Read, Glob, Bash
auto_invocable: false # default — opt-in to auto-load (safer)
metadata:
owner: my-team
tags: [observability, eval]
oasf_skill_ids: [1106] # optional AGNTCY OASF taxonomy ref
---
# My Skill
What this skill does. When to invoke. Steps to follow. Hard rules.
The body is freeform Markdown — Claude Code reads it verbatim.Required vs optional
| Field | Status | Notes |
|---|---|---|
| name | REQUIRED | Lowercase kebab-case. Must match directory name. |
| description | REQUIRED | Tells the LLM when to invoke. List trigger phrases. |
| version | optional | Semver. Bump on breaking changes. |
| license | optional | SPDX identifier (MIT, Apache-2.0, CC-BY-4.0...). |
| allowed_tools | optional | Comma-separated allowlist of tools the skill needs. |
| auto_invocable | optional | Default false. Opt-in to LLM auto-loading. (Polarity-flipped from Anthropic's disable-model-invocation.) |
| metadata | optional | Free-form key/value bag (owner, tags, dashboard URLs). |
| oasf_skill_ids | optional | AGNTCY OASF taxonomy IDs (LF AI & Data alignment). |
Where to publish
One SKILL.md, four distribution channels:
- Anthropic Skills marketplace — PR to anthropics/skills. Reach: 125K+ Claude Code users.
- agentskills.io — web upload UI. Reach: 30+ runtime adopters.
- AGNTCY Hosted Agent Directory — OASF descriptor at
/.well-known/oasf-descriptor.json. Reach: LF AI & Data ecosystem. (AgentMinds publishes one.) - Your own repo — anyone with a clone can use it. Reach: viral / org-internal.
Reference: AgentMinds' own skills
- agentminds-push-report — pushes ARP report from the user's project
- agentminds-status — system health snapshot from
/health - agentminds-agents — list + manually trigger central agents
- agentminds-pool — knowledge pool inspector