What Context Needed — Agent Skill by GitHub

From the author

Ask Copilot what files it needs to see before answering a question

— the description by vfaraji89

AutoGineer summary

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

This skill helps users optimize their interactions with an AI agent by proactively identifying which files are required to provide an accurate and informed response. By prompting the agent to analyze the requirements of a specific question, the user can ensure the agent has the necessary context before attempting to solve a problem, reducing hallucinations and improving answer quality.

What it does

Analyzes a user question to determine required codebase context.
Categorizes files into must-see and should-see groups.
Identifies files already provided in the current conversation history.
Highlights specific areas of uncertainty that prevent an accurate answer.
Provides a structured markdown template for the agent's response.

When to use it

When you are unsure which parts of a large codebase are relevant to your question.
Before asking a complex architectural or debugging question.
To prevent the agent from making assumptions based on incomplete information.
When you want to ensure the agent has a complete view of dependencies or related logic.

Advantages

Increases the accuracy of AI-generated responses.
Reduces wasted tokens on irrelevant file analysis.
Helps the user understand the agent's reasoning process.
Creates a clear roadmap for providing necessary context.

Usage examples

“What context do you need to help me refactor the authentication module?”: The agent will list the specific files related to authentication, explain why they are needed, and identify any missing information.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/github/what-context-needed/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip what-context-needed.zip -d .agents/skills

Documentation by vfaraji89

What Context Do You Need?

Before answering my question, tell me what files you need to see.

My Question

Instructions

Based on my question, list the files you would need to examine
Explain why each file is relevant
Note any files you've already seen in this conversation
Identify what you're uncertain about

Output Format

## Files I Need

### Must See (required for accurate answer)
- `path/to/file.ts` — [why needed]

### Should See (helpful for complete answer)
- `path/to/file.ts` — [why helpful]

### Already Have
- `path/to/file.ts` — [from earlier in conversation]

### Uncertainties
- [What I'm not sure about without seeing the code]

After I provide these files, I'll ask my question again.

Files

ATTRIBUTION.mdAdded by AutoGineer1.1 KiB
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md881 B

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.

Discernment Nudge
AnthropicOfficial
A framework for AI agents to append reflective follow-up questions to substantive, high-stakes responses.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0GitHub stars of the source repository188.6k
Grilling
Matt Pocock· Community
A rigorous stress-testing persona that maps decisions into a branching tree to uncover hidden assumptions.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Wayfinder
Matt Pocock· Community
A structured approach to planning and executing complex, multi-session projects using a shared map of decision-based tickets on an issue tracker.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Brainstorming
Jesse Vincent (obra)· Community
A mandatory pre-work framework for clarifying user intent, exploring design approaches, and securing approval before implementation.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository314k
Interview Me
Addy Osmani· Community
A structured interview process to extract and verify a user's true intent before starting any work.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository113.9k
Idea Refine
Addy Osmani· Community
A structured ideation partner that refines raw concepts into actionable markdown one-pagers.
Agent toolingClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository113.9k