mcpField
O
onboard-agent

onboard-agent

github.com/sharpdeveyeAgent workflows592323 installsUpdated 26w ago
Repository

About onboard-agent

onboard-agent is a skill for creating an agent workflow from scratch or adding an agent to an existing system. It guides users through conventions, a minimal initial structure, and verification with a golden test.

Key features

  1. 01Establishes prompt and tool conventions
  2. 02Creates a minimal project structure
  3. 03Defines an agent prompt and output schema
  4. 04Adds a golden test and error handling
  5. 05Verifies behavior and logging

Use cases

  1. 01Starting a new agent workflow
  2. 02Adding an agent to an existing system
  3. 03Checking an initial agent with a known-good test

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sharpdeveye/maestro --skill onboard-agent

After installing, type/onboard-agentin Claude Code to confirm it loaded.

Details

From the project README

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/]
Step 2: Create Initial Structure
project/
├── prompts/          # System prompts, versioned
├── tools/            # Tool definitions
├── config/           # Environment-specific configuration
├── tests/            # Golden test sets and evaluation suites
├── logs/             # Runtime logs (gitignored)
└── .maestro.md       # Workflow context
Step 3: Create the First Agent
  1. System prompt: Role definition with constraints
  2. 2-3 essential tools: Start with the minimum viable tool set
  3. Output schema: Define expected output format
  4. One golden test: At least one test case with known-good output
  5. Basic error handling: Structured error responses
  6. Logging: Structured log output for each run
Step 4: Verify
  • Run the agent with the golden test case
  • Verify error handling works (send bad input)
  • Verify logging captures useful context
Recommended Next Step

After onboarding, run /diagnose for a baseline health check, then /fortify to add production-grade error handling.

NEVER:

  • Start building without establishing conventions
  • Create tools without descriptions
  • Skip the golden test case
  • Over-scope the initial agent (start minimal, amplify later)

Comments

Markdown supported