oracle

Bundle prompts with selected files for AI model analysis.

Updated Feb 1, 2026
One-click install
npx skills add https://github.com/NJUxlj/openclaw --skill oracle-njuxlj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/NJUxlj/openclaw/tree/main/skills/oracle
Command: npx skills add https://github.com/NJUxlj/openclaw --skill oracle-njuxlj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the process of providing code context to AI models, enabling them to understand and analyze your codebase more effectively, reducing the need for manual context-switching and information gathering.

Core Features & Use Cases

  • Context Bundling: Combines prompts with selected files into a single request for AI models.
  • Engine Flexibility: Supports both API and browser-based AI engines for diverse use cases.
  • Session Management: Allows reattachment to long-running or detached AI sessions, preserving context.
  • Use Case: Debugging a complex issue by providing the relevant source files and error messages to an AI for analysis and suggested solutions.

Quick Start

Use the oracle skill to preview the token count for a task using 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 source code files with prompts for AI model analysis?

To bundle source files for AI analysis, you specify the relevant code using glob patterns. The system combines your prompt and selected files into a single request, enabling the AI to understand your codebase context.

Can I use browser-based AI engines instead of an API for code context analysis?

Yes, code context analysis supports both API and browser-based AI engines. This engine flexibility allows you to choose your preferred environment for processing prompts and analyzing source files.

How do I manage long-running AI sessions for complex code analysis tasks?

You manage long-running AI sessions using built-in session management. This feature allows you to reattach to detached or ongoing tasks, preserving the code context and conversation history for continuous problem-solving.

Does this code context bundling approach work with specific file glob patterns?

Yes, code context bundling requires specifying files via glob patterns. By defining these patterns, you precisely target the source files needed for the AI model to analyze and solve your coding issues.

What is the best way to provide code context to an LLM for debugging complex issues?

The best way to provide code context for debugging is bundling error messages and relevant source files into a single prompt. This gives the LLM the exact context needed to analyze the issue and suggest solutions.

Why does my AI model fail to understand my codebase without manual context switching?

AI models fail without context because they lack access to your local codebase. Bundling prompts with selected files directly provides the necessary code context, reducing manual information gathering and context-switching.