Contract-based framework for orchestrating multi-agent Claude workflows using YAML runbooks. Compiles into executable skills with loop, parallel execution, and checkpoint support for complex automation tasks.
agent-runbook is a skill framework designed for Claude Code and Codex that enables developers to define and execute multi-agent workflows through YAML-based runbooks. It provides a structured, contract-based approach to agent orchestration, allowing complex automation sequences with support for loops, parallel execution paths, and checkpoint recovery mechanisms.
Clone or download the agent-runbook repository from GitHub. Define your multi-agent workflow in YAML format following the runbook schema. Use the compilation tool to convert your YAML runbook into a SKILL.md file that can be executed within Claude Code or Codex environments. Reference the provided documentation and examples for configuration patterns.
Thesis Structure Helper assists students and researchers in organizing their academic theses by providing…
作成者 FormAI
Dependency Auditor helps developers audit project dependencies for security vulnerabilities, licensing is…
作成者 EnergyAI
FAQ Generator Pro auto-generates FAQ pages from support tickets, documentation, and product information.…
作成者 EmailForge