skills.rest
ApiliumCode
ApiliumCodeOFFICIAL
Explore all skills by this author →
WebsiteGitHub

oracle

Bundle prompts and files for oracle CLI AI code analysis.

12|3|Updated Feb 25, 2026
Search Tags:#developer tools#code analysis#prompt engineering#ai coding#llm interaction#oracle cli
One-click install
npx skills add https://github.com/ApiliumCode/mayros --skill oracle-apiliumcode
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/ApiliumCode/mayros/tree/main/skills/oracle
Command: npx skills add https://github.com/ApiliumCode/mayros --skill oracle-apiliumcode

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides best practices for using the oracle CLI, ensuring efficient and effective interaction with AI models for code-related tasks by bundling prompts and files.

Core Features & Use Cases

  • Prompt + File Bundling: Packages prompts and relevant files into single requests for AI models.
  • Engine Selection: Supports both API and browser-based engines for AI interaction.
  • Session Management: Allows for reattaching to long-running or detached AI sessions.
  • Use Case: When debugging a complex issue in a large codebase, use Oracle to bundle your detailed problem description, relevant code files, and error logs into a single request for an AI model to analyze and suggest solutions.

Quick Start

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

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I bundle code files and prompts for AI code analysis?▼

You can bundle code files and prompts by packaging your problem description, relevant source files, and error logs into a single request. This approach ensures the AI model receives full context to suggest accurate solutions.

How do I preview token count before sending a large prompt to an AI model?▼

To preview token count before sending a large prompt, run a dry run command like `oracle --dry-run summary -p "<task>" --file "src/**"`. This estimates the token usage of your bundled files and prompts without executing the actual AI request.

Can I reattach to a detached AI session for long-running code analysis tasks?▼

Reattaching to a detached AI session for long-running code analysis tasks is fully supported through session management. This allows you to reconnect to ongoing AI interactions and retrieve results without losing previous prompt context.

Does the oracle CLI support browser-based engines for AI interaction?▼

The oracle CLI supports both API and browser-based engines for AI interaction. Engine selection allows you to choose between direct API calls or browser-based access depending on your environment and authentication preferences.

Do I need to install any dependencies before using the oracle CLI for prompt engineering?▼

You need the oracle binary installed and configured on your system before using the oracle CLI for prompt engineering. This prerequisite ensures optimal use of the tool's file bundling and session management capabilities.

What is the best way to debug a complex issue in a large codebase using AI?▼

The best way to debug a complex issue in a large codebase using AI is bundling your detailed problem description, relevant code files, and error logs into a single request. This provides the AI with sufficient context to analyze and suggest solutions.

Related Skills

Explore More Software Engineering Skills→
Yapie0Yapie0
55

oracle

Bundle prompts with attached files for AI model context.

Community
Advanced
Jst-Well-DanJst-Well-Dan
8

test-fixing

Group failing tests by error type and module, then fix and verify them.

Community
Advanced
m19803261706m19803261706

cx-fix

Investigate, fix, test, and commit code changes with conventional commits.

Community
Intermediate
nidhalboumaiza-0nidhalboumaiza-0

LLM

Build multi-turn chatbots with the z-ai-web-dev-sdk.

Community
Intermediate