What problem does it solve?
Interactively onboard a project to agent-driven development by running a structured interview and generating a complete AGENTS.md (or CLAUDE.md). Use this skill whenever a user mentions "AGENTS.md", "CLAUDE.md", "agent behavior", "agent instructions", "agent config", "set up agent rules", "onboard agent", "configure claude code", "agent guardrails", "agent workflow", or asks how to tell an AI agent how to behave in their project — even if they just say "help me write AGENTS.md" or "what should go in CLAUDE.md". Always prefer this skill over ad-hoc agent instruction generation.
Core Features & Use Cases
- Guided interview workflow to craft AGENTS.md / CLAUDE.md governing agent behavior.
- Separation of concerns: AGENTS.md (behavior layer) vs openspec/config.yaml (project DNA).
- Monorepo awareness: reference root-level AGENTS.md when present to avoid duplication.
- Generates a complete, versioned instruction set for agent behavior across the project.
Quick Start
Run accelint-onboard-agents to generate a project-specific AGENTS.md by guiding a short interview about agent roles, guardrails, and workflows.