accelint-onboard-agents

Generate AGENTS.md files through a structured interview about agent behavior.

17|1|Updated Mar 14, 2025
One-click install
npx skills add https://github.com/deckgl-fiber-renderer/fiber.gl --skill accelint-onboard-agents
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: accelint-onboard-agents
Source: https://github.com/deckgl-fiber-renderer/fiber.gl/tree/main/.agents/skills/accelint-onboard-agents
Command: npx skills add https://github.com/deckgl-fiber-renderer/fiber.gl --skill accelint-onboard-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

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.

Frequently Asked Questions about accelint-onboard-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an AGENTS.md file to set up AI coding agent rules?

To create an AGENTS.md file, this skill conducts a structured interview to define agent roles, guardrails, and workflows, outputting a complete rules-driven instruction set for AI coding agents in your project root.

What is the difference between AGENTS.md and CLAUDE.md for configuring agent behavior?

Both AGENTS.md and CLAUDE.md serve as the behavior layer governing AI agent actions. This skill generates either file format to establish explicit agent roles, guardrails, workflows, and governance rules for your coding environment.

Can I set up agent guardrails and workflows for a monorepo?

Yes, you can configure agent guardrails for a monorepo. The skill features monorepo awareness, referencing root-level AGENTS.md files when present to avoid duplication and ensure consistent agent behavior across nested projects.

How do I structure agent instructions separately from project configuration?

You structure agent instructions by separating concerns: AGENTS.md acts as the behavior layer defining agent actions, while openspec/config.yaml manages the project DNA, ensuring clean separation between behavioral rules and project configuration.

What should go into agent instructions for an AI coding assistant?

Agent instructions should include explicit agent roles, guardrails, workflows, and governance rules. The skill interactively onboards your project by interviewing you to generate a versioned instruction set tailored to your specific development needs.