One-click install
npx skills add https://github.com/xcriminal1/Xcriminal-bot --skill oracle-xcriminal1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/xcriminal1/Xcriminal-bot/tree/main/skills/oracle
Command: npx skills add https://github.com/xcriminal1/Xcriminal-bot --skill oracle-xcriminal1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Bundles your prompt with selected repository files to provide context for model responses.

Core Features & Use Cases

  • Bundled prompts: Combine prompt + files into a single request to preserve repo context.
  • File selection: Flexible file globs and explicit file lists to include exactly what is needed.
  • Engine and session control: Choose API or browser engines and manage long-running sessions for iterative analyses.

Quick Start

Attach a focused prompt and the relevant files from your project to enable contextual answers.

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I bundle prompt and repository files together for code analysis?

You can include specific repository files in your prompt context by using flexible file globs or explicit file lists. This file selection mechanism attaches exactly the needed project source files and tests to your prompt bundle.

Can I manage long-running sessions for iterative architecture reviews?

Yes, you can manage long-running sessions for iterative architecture reviews using session slugs. This session management capability allows you to maintain continuous context across multiple prompt bundles during extended code analysis tasks.

Does oracle CLI support selecting between API and browser engines?

Yes, oracle CLI supports engine selection between API and browser engines. You can choose the appropriate engine to run your tasks based on whether you need automated API responses or browser-driven execution for your project analysis.

What is the best way to provide source file context to model responses?

The best way to provide source file context to model responses is by bundling your prompt with selected repository files. This approach ensures the model has direct access to relevant code and tests during long-think code analysis and architecture reviews.