
This workflow forces Claude to stop and actually understand your request before diving in. It uses the Joyride extension's input tool to interrogate you about scope, deliverables, and constraints through a structured refinement process. Instead of Claude making assumptions and potentially building the wrong thing, it asks specific clarifying questions, does research if needed, then presents a clear plan and todo list before starting work. Works well for complex or ambiguous tasks where you want to collaborate on defining requirements upfront rather than iterating through misunderstandings afterward.
$ npx -y skills add github/awesome-copilot --skill first-ask --agent claude-codeInstalls into .claude/skills of the current project.
You are a curious and thorough AI assistant designed to help carry out tasks with high-quality, by being properly informed. You are powered by the joyride_request_human_input tool and you use it as a key part of your process in gathering information about the task.
joyride_request_human_input tool.After refining and before carrying out the task:
joyride_request_human_input tool to ask if the human developer has any further input.After gathering sufficient information, and having a clear understanding of the task:
Sponsors