oracle

Guide oracle CLI usage for bundling prompts and files with AI models.

Updated Mar 3, 2026
One-click install
npx skills add https://github.com/hammadparveez/mrhammadclaw --skill oracle-hammadparveez
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/hammadparveez/mrhammadclaw/tree/main/skills/oracle
Command: npx skills add https://github.com/hammadparveez/mrhammadclaw --skill oracle-hammadparveez

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides guidance on effectively using the oracle CLI tool for bundling prompts and files to interact with AI models, ensuring efficient and compliant usage.

Core Features & Use Cases

  • Prompt + File Bundling: Learn how to package your prompts and relevant code files for AI analysis.
  • Engine & Session Management: Understand how to select AI engines (API vs. browser) and manage long-running sessions.
  • File Attachment Patterns: Master the --file argument for including and excluding specific files and directories.
  • Use Case: When debugging a complex issue in your codebase, use this Skill to understand how to bundle your prompt, relevant source files, and error messages to get the best context-aware response from an AI.

Quick Start

Use the oracle CLI to preview the token count for a task by running oracle --dry-run summary -p "<task>" --file "src/**".

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I bundle prompts and code files for AI analysis using a CLI?

To bundle prompts and code files for AI analysis, use the oracle CLI with the --file argument to include specific source files and directories alongside your task prompt. You can preview the token count for this bundled context using the --dry-run summary command.

What is the best way to manage long-running AI sessions when processing code context?

Managing long-running AI sessions involves utilizing the oracle CLI's session management features to maintain context continuity. This approach ensures deterministic task execution by preserving your engine selection and file attachment patterns across multiple interactions.

Can I use API and browser-based AI engines for file bundling and prompt engineering?

Yes, you can use both API and browser-based AI engines for file bundling and prompt engineering. The oracle CLI supports engine selection, allowing you to switch between API interactions and browser-based model access depending on your project requirements.

Do I need to install the oracle CLI binary before bundling files for AI models?

Yes, you must install and configure the oracle CLI binary before bundling files for AI models. The CLI requires proper configuration for API or browser-based model interactions to successfully execute prompt and file bundling tasks.

How do I include and exclude specific files and directories when attaching code context?

To include and exclude specific files and directories when attaching code context, master the --file argument patterns provided by the oracle CLI. This allows precise control over which source files are bundled with your prompt for AI analysis.

Why does previewing token count help with deterministic task execution in developer workflows?

Previewing token count helps with deterministic task execution by allowing you to verify the size of your bundled prompt and files before sending them to the AI model. Running a dry-run summary ensures your developer workflow stays within model limits.