first-ask
- Use it when:
- You want the agent to pin a task down with you before it starts working.
- It does:
- Asks about scope, deliverables, success criteria and requirements, explores the project, and keeps asking until you have nothing to add.
- You get:
- A short plan and a todo list, then the agent carries out the task.
- Needs:
- VS Code with the Joyride extension, whose joyride_request_human_input tool it asks through.
Needs VS Code with the Joyride extension: it asks its questions through Joyride's joyride_request_human_input tool.
TL;DR
first-ask makes the agent refine a task with you before doing it. It asks specific questions through joyride_request_human_input, a tool of the Joyride extension for VS Code: what the task covers and aims for, what it should deliver, how success is judged, and its technical and procedural requirements. Between questions it explores the project with its other tools, researches on the web when something calls for it, and organizes the task into sections or steps, keeping its understanding as simple as it can. Before starting, it asks whether you have anything more to add and keeps refining until you don't. Then it shows you its plan with little repetition, writes a todo list and gets to work. Unlike a planning skill that stops at a document, it goes on to do the task itself once the questions are answered.
Summarizes the skill at 797337f.
npx skills add https://github.com/github/awesome-copilot --skill first-ask skills.sh pageSource on GitHubAll skills from github/awesome-copilot
- Total Downloads
- 8,800 on skills.sh, Nov 9, 2026
- Repo stars
- 40,943 github/awesome-copilot
- First seen
- Feb 25, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 12 |
| Sep 28 | 15 |
| Oct 5 | 13 |
| Oct 12 | 2 |
| Oct 19 | 0 |
| Oct 26 | 0 |
| Nov 2 | 2 |
| Nov 9 | 0 |
| Category |
Make the agent question you and write the plan down before it writes code. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills. |
|---|---|
| Type |
A multi-step process the agent follows: interview, debug, run a TDD loop, review. |
| Effect |
Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code. |
| Needs |
A specific command-line tool or desktop app must be installed, such as gh, agent-browser, LibreOffice, Obsidian or a vendor CLI. |
| Publisher |
A verified publisher on skills.sh, or the company or maintainer behind the product the skill operates. |
| Topics | |
| Stack |
SKILL.md
From github/awesome-copilot at 797337f. Checked daily, last changed Nov 6, 2026.
Frontmatter
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_inputtool. - 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_inputtool 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!