oracle

Bundle a prompt with selected repository files into a context-aware payload.

7|12|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/borealBytes/my-farm-advisor --skill oracle-borealbytes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/borealBytes/my-farm-advisor/tree/main/skills/oracle
Command: npx skills add https://github.com/borealBytes/my-farm-advisor --skill oracle-borealbytes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Oracle bundles your prompt + selected files into one “one-shot” request so another model can answer with real repo context (API or browser automation). Treat output as advisory: verify against code + tests.

Core Features & Use Cases

  • Prompt + file bundling: attach selected files to a single prompt payload for richer model context.
  • Engine and session management: choose browser or API engines and manage stored sessions.
  • File attachment patterns: include and exclude paths to control what goes into the bundle.
  • Use cases: code reviews, design explorations, or knowledge gathering across codebases.

Quick Start

Bundle a focused set of project files with your prompt and run oracle to generate context-aware results.

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 with a prompt for code review?

You bundle repository files with a prompt by attaching selected paths into a single context-aware payload. This allows a model to perform code review or architecture exploration using real codebase context.

Can I filter which files are included in the prompt bundling payload?

Yes, you can filter files during prompt bundling by applying include and exclude path patterns. This controls exactly which codebase, docs, or test files go into the model reasoning request.

Does the oracle CLI support dry-runs before sending the bundled prompt?

Yes, the oracle CLI supports dry-runs. You can execute a dry-run to preview the bundled prompt and selected file payload before sending the actual request to the API or browser engine.

What is the best way to manage API and browser engine sessions for codebase analysis?

The best way to manage codebase analysis sessions is using the built-in session management. You choose between browser or API engines and manage stored sessions to maintain context during design explorations.

Are there limitations to using model output for architecture exploration?

The output is advisory and has limitations; you must verify it against your actual code and tests. Treat the context-aware model reasoning as guidance rather than a definitive architectural solution.