oracle

Bundle prompts and selected files into a one-shot review request.

Updated Feb 4, 2026
One-click install
npx skills add https://github.com/SennTse/openclaw-backup --skill oracle-senntse
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/SennTse/openclaw-backup/tree/main/skills/oracle
Command: npx skills add https://github.com/SennTse/openclaw-backup --skill oracle-senntse

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Bundle your prompt and selected files into a single one-shot request so another model can review with repo context.

Core Features & Use Cases

  • Bundles prompt + files into a review-friendly payload.
  • Supports browser or API runs for debugging, refactors, design checks, or cross-validation.
  • Manages sessions, attachments, and token budgets for long-running tasks.

Quick Start

Describe your task to the CLI, attach the minimal set of files with --file patterns, and run the browser workflow using GPT‑5.2 Pro for context-rich review.

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I bundle files and prompts for a cross-model code review?

You can bundle selected files and prompts into a single one-shot request for code review by using CLI file selection patterns to attach repo context for another model to evaluate.

What is a one-shot prompt bundle for model reviews?

A one-shot prompt bundle is a single payload combining your prompt and selected files with YAML frontmatter, enabling another model to review your code with full repository context.

Can I run cross-validation checks on local projects using a browser workflow?

Yes, cross-validation checks on local or hosted projects support both browser and API runs, allowing you to send bundled repo context to another model for debugging or design checks.

How do I manage token budgets for long-running code review sessions?

You can manage token budgets and attachments through built-in session management, ensuring long-running code review tasks stay within model limits while maintaining necessary file context.

Does the prompt bundling workflow require specific dependencies?

No specific dependencies are required to bundle prompts for model reviews; the workflow operates standalone to package your files and descriptions for cross-validation or refactoring tasks.

What's the best way to format a prompt bundle for a design check?

The best way to format a prompt bundle for a design check is enforcing YAML frontmatter with name and description fields, then attaching the minimal set of files using file pattern selection.