What problem does it solve? Delegating development work to a remote AI agent is error-prone: tasks run against the pushed repository rather than local changes, execute asynchronously without completion callbacks, and require manual polling to discover results. This Skill provides the operational knowledge to create, monitor, and manage Netlify agent tasks correctly. ## Core Features & Use Cases - Remote Task Creation: Launch Claude, Codex, or Gemini agents against a linked Netlify site with prompts, branch targeting, and model selection via netlify agents:create. - Task Lifecycle Management: List, inspect, and stop agent tasks with netlify agents:list, agents:show, and agents:stop, polling until terminal states (done, error, cancelled). - Cross-Model Delegation: Get a second opinion on your implementation from a different model, discover edge cases, or run independent work in parallel while you continue locally. - Use Case: You just refactored an authentication flow and want validation. Push your branch, then delegate a security audit prompt to a different agent on Netlify, polling the task ID until it completes. ## Quick Start Ask the agent to run a code review task on your Netlify site using the Claude agent and poll the returned task ID until it reports done.
