Onboard Agent

This is scaffolding for agent systems, not individual prompts. It walks you through conventions first (delimiters, tool naming, logging format), then sets up the file structure (prompts/, tools/, tests/), then creates your first agent with a golden test case. The mandate to invoke /agent-workflow and run /teach-maestro if no context exists tells you this is meant for greenfield projects or adding agents to established workflows. Smart that it pushes you toward minimal viable tooling instead of overbuilding. If you're spinning up a multi-agent system or joining one mid-flight, this gives you the checklist so you don't skip the boring parts that matter later.

skills.sh installs: 328
GitHub stars: 602
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sharpdeveye/maestro --skill onboard-agent --agent claude-code

Installs into .claude/skills of the current project.

Files

MANDATORY PREPARATION

Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first.

Bootstrap a new agent workflow from scratch, or add a new agent to an existing system.

Step 1: Establish Conventions

## Workflow Conventions
### Prompt Format
- Delimiter style: [XML tags / markdown headers / triple-dash]
- Section order: [System → Context → Instructions → Input]
- Output format: [JSON with schema / markdown template]

### Tool Conventions
- Naming: [verb_noun / noun.verb / camelCase]
- Description template: [What → When → When Not → Returns]
- Error format: [{ code, message, details }]

### Logging
- Format: [JSON structured]
- Required fields: [workflow_id, step, timestamp, level]

### File Structure
- Prompts: [prompts/workflow-name/v1.md]
- Tools: [tools/tool-name.{ext}]
- Config: [config/environment.yaml]
- Tests: [tests/workflow-name/]