skills.rest
Lutra23
Lutra23COMMUNITY
Explore all skills by this author →
GitHub

oracle

Bundle prompts and repository files into a single request for model review.

Updated Jan 31, 2026
Search Tags:#debugging#cli#oracle#browser#code-review#prompt-bundling#model-review
One-click install
npx skills add https://github.com/Lutra23/content-workflow --skill oracle-lutra23
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/Lutra23/content-workflow/tree/main/skills/oracle
Command: npx skills add https://github.com/Lutra23/content-workflow --skill oracle-lutra23

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Oracle bundles your prompt + selected files into one “one-shot” request so another model can answer with real repo context (API or browser automation). Treat outputs as advisory: verify against the codebase + tests.

Core Features & Use Cases

  • Bundles your prompt and a tight set of files into a single review bundle for contextual, second-model feedback
  • Supports both API and browser-based reviews to accommodate different workflow preferences
  • Provides guidance for deterministic runs, including previews, dry-runs, and session management to reattach to long-running tasks

Quick Start

Invoke the Oracle CLI to bundle your prompt with a selected file set and start a browser or API review session.

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I bundle prompts and repository files for a model code review?▼

You can bundle prompts and repository files for a model code review by packaging your prompt and a filtered set of files into a single one-shot request, enabling another model to review with full context.

Can I use browser automation for long-running codebase reviews?▼

Yes, you can use browser automation for long-running codebase reviews. The workflow supports both API and browser-based sessions, allowing you to manage and reattach to extended review tasks.

Does the prompt bundling workflow support dry-runs and file filtering?▼

Yes, the prompt bundling workflow supports dry-runs and file filtering. It enforces deterministic workflows with options for previews, dry-runs, and explicit model choices to control the review process.

What is the best way to get second-model feedback on my codebase?▼

The best way to get second-model feedback on your codebase is bundling a tight set of files and your prompt into one advisory request, which you then verify against the codebase and tests.

Do I need to verify outputs from a model review against my codebase?▼

Yes, you need to verify outputs from a model review against your codebase. The generated outputs are advisory and should be checked against the codebase and tests for accuracy.

Related Skills

Explore More Software Engineering Skills→
steipetesteipete
385.7k

oracle

Bundle prompts and files into a single one-shot request for repository-context aware answers.

Community
Advanced
engalarengalar
1

Verify with OQL Skill

Execute OQL queries against a running Mendix application to validate data state.

Community
Intermediate
johnlindquistjohnlindquist
24

packx

Bundles code files into AI-ready context with a 49k token limit.

Community
Advanced
goncalossilvagoncalossilva
24

oracle

Send curated files to an opposite AI model family for code review.

Community
Intermediate