first-ask

github/awesome-copilot

Interrogates task scope, deliverables, and constraints via interactive Q&A before the agent starts working.

What is first-ask?

first-ask is an interactive task-refinement workflow that uses the Joyride extension's human-input tool to ask clarifying questions about scope, deliverables, and constraints before the agent starts work. It's useful when you want the agent to fully understand a task and confirm a plan with you before executing it, rather than guessing requirements.

Asks targeted clarifying questions using the joyride_request_human_input tool whenever details are unclear
Iteratively refines understanding of task scope, objectives, and deliverables
Performs project exploration and web research as needed to inform understanding
Checks with the human for further input until no more clarification is needed
Presents a concise plan and creates a todo list before starting the actual work

How to install first-ask

npx skills add https://github.com/github/awesome-copilot --skill first-ask

Prerequisites

Joyride extension installed and enabled (provides the joyride_request_human_input tool)

Claude Code

Cursor

Windsurf

Cline

How to use first-ask

1.Ensure the Joyride extension is installed and active in your editor.
2.Give the agent a task to perform.
3.Respond to the clarifying questions asked via the joyride_request_human_input tool, covering scope, deliverables, and constraints.
4.Allow the agent to perform any needed project exploration or web research it identifies as necessary.
5.When prompted, provide any further input or confirm you have none, repeating until refinement is complete.
6.Review the plan and todo list the agent presents.
7.Let the agent proceed to carry out the task.

Use cases

Good for

Clarifying an ambiguous or underspecified task before an agent begins implementation
Ensuring deliverables and success criteria are agreed upon before significant work starts
Combining clarifying questions with project exploration or web research to build a clear plan
Producing a reviewable plan and todo list prior to execution for high-stakes or complex tasks

Who it's for

Developers who want agents to confirm requirements before making changes
Users working on ambiguous or complex tasks who prefer a guided clarification step
Teams using Joyride-enabled editors who want human-in-the-loop task planning

first-ask FAQ

Does this skill require any special VS Code extension?

Yes, it requires the Joyride extension, since the workflow depends on the joyride_request_human_input tool.

What happens if I don't have Joyride installed?

The skill cannot function as designed because its core interaction mechanism, the joyride_request_human_input tool, comes from Joyride.

Will the agent start working immediately on my request?

No, it first interrogates scope, deliverables, and constraints, and only begins work after you confirm there is no further input needed.

Does it create a plan before doing the work?

Yes, after refining understanding it presents a plan with minimal redundancy and creates a todo list before starting work.

Full instructions (SKILL.md)

Source of truth, from github/awesome-copilot.

name: first-ask description: 'Interactive, input-tool powered, task refinement workflow: interrogates scope, deliverables, constraints before carrying out the task; Requires the Joyride extension.'

Act Informed: First understand together with the human, then do

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.

<refining> Your goal is to iteratively refine your understanding of the task by:

Understanding the task scope and objectives
At all times when you need clarification on details, ask specific questions to the user using the joyride_request_human_input tool.
Defining expected deliverables and success criteria
Perform project explorations, using available tools, to further your understanding of the task
- If something needs web research, do that
Clarifying technical and procedural requirements
Organizing the task into clear sections or steps
Ensuring your understanding of the task is as simple as it can be </refining>

After refining and before carrying out the task:

Use the joyride_request_human_input tool to ask if the human developer has any further input.
Keep refining until the human has no further input.

After gathering sufficient information, and having a clear understanding of the task:

Show your plan to the user with redundancy kept to a minimum
Create a todo list
Get to work!

Surgical code refactoring to improve maintainability without changing behavior.

19k installsAudited