oracle

Bundle prompts and files into one-shot requests for oracle CLI sessions.

5|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/JansenAnalytics/claudex --skill oracle-jansenanalytics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/JansenAnalytics/claudex/tree/main/skills/oracle
Command: npx skills add https://github.com/JansenAnalytics/claudex --skill oracle-jansenanalytics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Oracle bundles your prompt + selected files into a single one-shot request so another model can answer with full repo context, helping ensure outputs are advisory and verifiable against code and tests.

Core Features & Use Cases

  • Prompt + file bundling: Attach files to prompts to provide precise context and reduce back-and-forth.
  • Engine selection & sessions: Manage engine choices and maintain persistent sessions for long-running tasks.
  • Attachment & preview workflows: Configure previews, dry-runs, and session reattachment for reliability.
  • Use Case: When debugging a large codebase, attach relevant files and run with a browser-enabled GPT model to preserve context across steps.

Quick Start

Invoke oracle with a clear task and attach the relevant project files to start a persistent, browser-based session

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I bundle multiple prompt files for a CLI session?

You can bundle multiple prompt files for a CLI session by attaching the selected files directly to your prompt, creating a single one-shot request that provides full repository context to the model.

How do I maintain persistent CLI sessions for long-running tasks?

Persistent CLI sessions for long-running tasks are maintained through session management and reattachment features, allowing you to preserve context and reattach to previous browser-based sessions across execution steps.

Can I use a browser-enabled GPT model to debug a large codebase?

Yes, you can use a browser-enabled GPT model to debug a large codebase by attaching relevant project files and running a persistent session, which preserves context across debugging steps.

What is the best way to construct deterministic prompts for file-rich tasks?

The best way to construct deterministic prompts for file-rich tasks is to apply prompt engineering best practices, bundling your prompt with structured file attachments to ensure outputs are advisory and verifiable against code and tests.

How do dry-runs and preview workflows improve CLI file attachments?

Dry-runs and preview workflows improve CLI file attachments by allowing you to configure and validate the bundled request beforehand, ensuring reliability and safe handling of sensitive data before execution.

Do I need to configure engine selection for browser-based CLI tasks?

Configuring engine selection for browser-based CLI tasks is required to manage engine choices and maintain persistent sessions, ensuring the selected model handles long-running, file-rich requests appropriately.