oracle

Bundle prompts with project files and globs for AI analysis.

3|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/ybsa/sovereign-kernel --skill oracle-ybsa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/ybsa/sovereign-kernel/tree/main/crates/sk-tools/skills/oracle
Command: npx skills add https://github.com/ybsa/sovereign-kernel --skill oracle-ybsa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines complex coding and problem-solving tasks by intelligently bundling prompts with relevant project files, enabling AI models to understand and act upon code context effectively.

Core Features & Use Cases

  • Contextual AI Interaction: Provides AI models with precise code and documentation context for accurate problem-solving.
  • Automated File Bundling: Selects and bundles necessary files and globs for AI analysis, reducing manual effort.
  • Use Case: Debugging a complex issue in a large codebase by providing the AI with specific source files, error logs, and project structure to pinpoint the root cause and suggest a fix.

Quick Start

Use the oracle skill to preview the token count for a task involving all files in the src directory, excluding test files.

Frequently Asked Questions about oracle

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I provide code context to an AI model for debugging a large codebase?

You can bundle specific source files and globs with your prompt to provide code context for AI analysis. This allows the model to understand the exact project structure and pinpoint the root cause of complex coding issues.

What is the best way to preview token counts before sending project files to an AI?

You can use a dry run to preview the token count for a task involving selected project files and globs. This feature reports file sizes and token usage before submitting the bundled prompt to the model.

Can I use both API and browser engines for AI code analysis?

Yes, the system supports both API and browser engines for model interaction. This allows you to choose your preferred engine to process the bundled code context and generate solutions.

How do I manage AI context when analyzing specific source files and excluding tests?

You can select specific project files and use globs to exclude unnecessary files like tests. This ensures the AI receives only the relevant code context, reducing token usage and improving analysis accuracy.

Do I need to manually select files for AI prompt engineering?

Yes, specific file selection and prompt engineering are required for optimal results. Selecting the necessary files and globs ensures the AI model receives the precise documentation and code context needed for accurate problem-solving.