Agent Skills
Teach your AI agent how to use Agent Messenger CLIs effectively.
Agent Skills are instruction files that teach AI coding agents how to use tools effectively. Agent Messenger includes skills for Slack, Discord, and Teams.
What Are Agent Skills?
When you give an AI agent access to a CLI tool, it needs to know:
- What commands are available
- How to format arguments
- What output to expect
- Best practices and common patterns
Agent Skills provide this knowledge in a structured format that AI agents can understand.
Installation
Skills CLI
The fastest way to add Agent Messenger skills to your project:
npx skills add devxoul/agent-messengerThis adds the skill files to your project's .skills/ directory.
Claude Code
Add Agent Messenger skills to Claude Code:
# From terminal
claude plugin marketplace add devxoul/agent-messenger
claude plugin install agent-messengerOr from within Claude Code:
/plugin marketplace add devxoul/agent-messenger
/plugin install agent-messengerOpenCode
Add to your opencode.jsonc:
{
"plugins": [
"agent-messenger@1.1.0"
]
}How It Works
Once installed, your AI agent can:
- Understand the CLI - Know what commands exist and how to use them
- Extract credentials - Run
agent-slack auth extractautomatically - Send messages - Compose and send messages on your behalf
- Read context - Get workspace snapshots to understand conversations
- React appropriately - Add reactions, reply in threads, etc.
Example Interaction
With Agent Messenger skills installed, you can ask your AI agent:
"Send a message to #general saying the build passed"
The agent will:
- Check if credentials are configured
- Run
agent-slack auth extractif needed - Execute
agent-slack message send general "The build passed" - Confirm the message was sent
Skill Contents
Each platform skill includes:
| Section | Description |
|---|---|
| Authentication | How to extract and manage tokens |
| Commands | Full command reference with examples |
| Output Format | Expected JSON structure for parsing |
| Error Handling | Common errors and how to recover |
| Best Practices | Tips for reliable agent workflows |