What Context Needed
This skill identifies missing contextual information in a conversation to ensure more relevant and complete responses from the AI.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add what-context-needed npx -- -y @trustedskills/what-context-needed
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"what-context-needed": {
"command": "npx",
"args": [
"-y",
"@trustedskills/what-context-needed"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill helps determine the minimum amount of context required for an AI agent to perform a task effectively. It analyzes the complexity and ambiguity of a request, identifying key details that must be provided by the user for accurate execution.
When to use it
- Before delegating a complex task to an AI agent to ensure clarity
- When refining ambiguous instructions to improve results
- To identify missing information in a query before proceeding with automation
Key capabilities
- Analyzes the ambiguity of user input
- Identifies critical context needed for accurate execution
- Helps streamline communication between users and AI agents
Example prompts
- "What details do I need to provide for you to write a Python script that sorts a list?"
- "Can you tell me what information is missing from this request: 'Fix the bug in my code'?"
- "I want to generate a report. What context should I give you first?"
Tips & gotchas
- Use it early in the process to avoid rework later
- Be specific with your query to get precise feedback on required context
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🏢 Official
Published by the company or team that built the technology.