oracle

Bundle prompts with files and directories into single AI model requests.

1|1|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/Rlier/clawdbot --skill oracle-rlier
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/Rlier/clawdbot/tree/main/skills/oracle
Command: npx skills add https://github.com/Rlier/clawdbot --skill oracle-rlier

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines complex development tasks by bundling prompts with relevant code and documentation, enabling AI models to provide context-aware solutions and insights.

Core Features & Use Cases

  • Contextual Code Analysis: Provides AI with specific code files and directories for accurate analysis and suggestions.
  • Prompt + File Bundling: Packages prompts with selected files into a single request for models.
  • Use Case: Debugging a complex issue by providing the AI with the relevant 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 using all files in the src directory.

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I bundle prompts with specific code files for AI context-aware analysis?

You can bundle prompts with specific code files by packaging them into a single request for AI models. This provides the AI with relevant source files and directories to deliver context-aware code analysis and solutions.

What is the best way to provide AI with my project structure and error logs for debugging?

The best way to debug complex issues is bundling prompts with your project structure, error logs, and relevant files into a single request. This allows the AI to pinpoint the root cause and suggest accurate fixes.

Can I use API and browser engines to interact with models like GPT-5.2 Pro for long-running sessions?

Yes, you can use both API and browser engines to interact with models like GPT-5.2 Pro. The approach supports handling long-running sessions and file attachments for extended code analysis tasks.

How do I preview the token count for an AI task using all files in a directory?

You can preview the token count for a task by bundling prompts with all files in a specified directory. This packages the selected files into a single request, allowing you to check the token size before sending it to the AI model.

Does bundling documentation with code improve AI-generated solutions?

Yes, bundling documentation with code files significantly improves AI-generated solutions. Providing this combined context allows the AI to understand project structure and dependencies, resulting in more accurate and context-aware insights.