First Ask — Agent Skill by GitHub

From the author

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

— the description by PEZ

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

First-ask is a structured workflow designed to improve task outcomes by ensuring the AI fully understands the user's requirements before starting work. It leverages the Joyride extension to facilitate an iterative dialogue, prompting the user for scope, deliverables, constraints, and success criteria. By requiring the agent to pause and verify its understanding, it minimizes assumptions and ensures that the final plan is aligned with the user's expectations.

What it does

Interrogates the user to define task scope and objectives.
Uses interactive input tools to clarify technical and procedural requirements.
Organizes complex tasks into clear, actionable steps.
Validates the final plan with the user before execution.
Maintains an iterative feedback loop until the user confirms readiness.

When to use it

When a task is ambiguous or requires specific constraints.
When you want to ensure the AI understands your success criteria before it begins.
When working on complex projects that benefit from a structured planning phase.
When you want to avoid rework by aligning on deliverables early.

Advantages

Reduces misunderstandings by forcing early clarification.
Ensures high-quality outputs through structured planning.
Provides a clear roadmap before any actual work is performed.
Keeps the user in control of the task's direction.

Usage examples

“Help me write a technical report on our new API.”: The agent will initiate a series of questions to determine the target audience, technical depth, required sections, and specific API features to cover.
“Refactor this legacy module.”: The agent will ask about existing test coverage, performance constraints, and specific areas of concern before proposing a refactoring plan.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/github/first-ask/download
Unzip it into the cross-client skills folder of your project:
```
mkdir -p .agents/skills && unzip first-ask.zip -d .agents/skills
```

Documentation by PEZ

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!

Files

ATTRIBUTION.mdAdded by AutoGineer1.1 KiB
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md1.5 KiB

Requirements and compatibility

Written for: GitHub Copilot

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Handoff
Matt Pocock· Community
Generates a concise handoff document to facilitate seamless transitions between AI agents.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Chief Of Staff
Matt Pocock· Community
A strategic orchestration agent that manages long-term goals by coordinating subagents and maintaining a persistent knowledge wiki.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Ask Matt
Matt Pocock· Community
A central routing skill that helps you identify the correct agent skill or workflow for your current situation.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Claude Handoff
Matt Pocock· Community
Seamlessly transfer your current conversation context to a new background agent.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Executing Plans
Jesse Vincent (obra)· Community
Execute implementation plans inline without subagents, maintaining rigorous progress tracking and verification.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository314k
Using Superpowers
Jesse Vincent (obra)· Community
A mandatory protocol for AI agents to identify and invoke relevant skills before performing any task or responding to user input.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository314k