oracle

Package repository prompts and source files into a single context bundle.

Updated Aug 13, 2025
One-click install
npx skills add https://github.com/JoeyJoziah/investment-analysis-platform --skill oracle-joeyjoziah
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/JoeyJoziah/investment-analysis-platform/tree/main/.claude/skills/oracle
Command: npx skills add https://github.com/JoeyJoziah/investment-analysis-platform --skill oracle-joeyjoziah

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you package a precise prompt together with the exact repository files needed for an AI-assisted investigation, so the model can answer with real code context instead of guesses.

Core Features & Use Cases

  • Context Bundling: Select files, directories, and glob patterns to create a focused analysis bundle.
  • Workflow Guidance: Choose between browser and API engines, run dry-runs, and manage long-running sessions without losing work.
  • Use Cases: Diagnose bugs, plan refactors, review architecture, or prepare high-signal prompts for another model using the smallest necessary file set.

Quick Start

Use the oracle skill to describe your goal, attach the most relevant files, and run a dry-run before sending the request.

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I bundle repository files for AI code analysis?

You package repository prompts and source files into a single context bundle by deliberately selecting targeted file sets, directories, and glob patterns. This ensures the AI receives the exact source code needed for accurate investigations.

What is context bundling for long-running code investigations?

Context bundling is the process of packaging precise prompts alongside relevant source files into a single bundle. It supports long-running code investigations by enabling session reattachment without losing work during architecture reviews or bug diagnostics.

How do I check token limits before sending a prompt to an AI model?

You check token limits before sending a prompt by running a dry-run token check. This workflow step verifies the assembled context bundle size and targeted file set prior to executing the actual request through the API or browser engine.

Can I use browser and API workflows for repository analysis?

Yes, you can use browser and API workflows for repository analysis. The workflow guidance allows you to choose between browser-based reasoning and API engines to execute your context bundle across targeted file sets.

How do I include scripts and references when assembling AI context?

You include scripts, references, and assets when assembling AI context through optional inclusion parameters during file selection. This allows you to append supplementary repository materials to the prompt bundle for more comprehensive analysis.

Why does my AI model guess instead of using my repository code?

Your AI model guesses instead of using your repository code because it lacks direct file context. Bundling your precise prompt with the exact source files ensures the model analyzes the real code context rather than hallucinating answers.