Skills

Extend agent capabilities with standard Claude Code skills, a core concept the Dashboard's Library surfaces

Skills#

Which layer? Skills are an open-source core concept. They are declared in your YAML config and deployed to each agent by the manager at deploy time. The ID Agents Dashboard's Library view lets you browse the skills (and agents and teams) available to install, but the skills themselves are defined, deployed, and run by the core.

Skills extend agent capabilities. They are declared in the YAML config and automatically deployed to each agent's .claude/skills/ directory at deploy time. Skills are the primary mechanism for inter-agent communication, identity, and other core capabilities.

Skills#

Skills use the standard Claude Code skill format -- a SKILL.md file with YAML frontmatter inside a named directory. Drop any skill into skills/ and reference it by name in your config.

Built-in Skills#

SkillDescription
identityAgent name, team, and role
inter-agentMessaging, delegation, news feed for multi-agent coordination
catalogRESTAP self-description visible to other agents
walletOWS multi-chain wallet addresses (skipped if no wallet)
xmtpEncrypted messaging via XMTP network -- send and receive messages by ENS name (see XMTP Messaging)

Adding a Skill#

  1. Create a directory in skills/ with a SKILL.md file:
skills/my-skill/
  SKILL.md
  1. Add YAML frontmatter to SKILL.md:
---
name: my-skill
description: What this skill does. Claude uses this to decide when to invoke it.
allowed-tools: Bash
---

# My Skill

Instructions for the agent...
  1. Reference it in your config:
defaults:
  skills:
    - identity
    - inter-agent
    - catalog
    - wallet
    - my-skill

Skills from defaults and per-agent lists are merged (deduped). You can download skills from Anthropic or the community and drop them into the skills/ directory.

Per-Agent Skills#

Add skills to specific agents in addition to the defaults:

agents:
  - name: researcher
    skills: [custom-research-skill]
  - name: coder
    skills: [code-review-skill]

How Skills Are Deployed#

At deploy time, each skill's SKILL.md is copied to the agent's working directory at .claude/skills/<name>/SKILL.md -- the standard Claude Code location. Template variables ({{VAR}}) in the skill content are substituted with deploy-time values like the agent's name, team, and domain.

Operational Skills#

These skills are available in the skills/ directory for manual use but are not deployed to agents automatically:

SkillDescription
admin-controlManage the agent team from any Claude Code session -- remote commands, conversational messaging, and parallel work dispatch with polling. See CLI Reference -- Admin Control Skill
local-agentSpawn and manage local Claude Code agents
inter-agent-communicationShell scripts for agent-to-agent communication
restap-clientGeneric RESTAP client for testing
pollingAsync reply monitoring

To use these, reference them by name in your config's skills list.