skills.rest
AmirulAndalib
AmirulAndalibCOMMUNITY
Explore all skills by this author โ†’
GitHub

oracle

Bundles prompts and selected files for second-model code review via Oracle CLI.

Updated Jun 19, 2026
Search Tags:#code review#debugging#refactoring#second opinion#oracle cli#token preview#gpt-5.5-pro
One-click install
npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill oracle-amirulandalib
Or copy as Structured Prompt for Agentโ–ผ
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/AmirulAndalib/Vilvona-AI/tree/main/skills/oracle
Command: npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill oracle-amirulandalib

SYSTEM DOCUMENTATION & REQUIREMENTS

๐Ÿ’ก This Skill requires @steipete/oracle.

What problem does it solve? Getting a second opinion on code from another AI model usually means manually copying files, pasting context, and losing track of long-running sessions. This Skill automates bundling a prompt with the right files and sending it through the Oracle CLI for review, debugging, refactoring, or design feedback. ## Core Features & Use Cases - Dry-run token previews: Check payload size and token spend with --dry-run summary --files-report before spending anything. - Dual engines: Use the browser engine for long ChatGPT Pro runs or the API engine when OPENAI_API_KEY or Azure config is available. - Session management: Reattach to detached or timed-out runs stored in ~/.oracle/sessions instead of blindly re-running. - Use Case: You hit a stubborn bug in your TypeScript backend. You run Oracle with a tight file set (src/** minus tests), preview the token cost, then launch a browser-engine run with gpt-5.5-pro to get an independent debugging pass. ## Quick Start Ask the assistant to run an Oracle second-model review of the src directory with a dry-run token preview first, then execute the full run in browser mode.

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I get a second AI model to review my code?โ–ผ

Use the Oracle CLI to bundle a prompt with selected files and send them to another model in one pass. Run `oracle --engine browser --model gpt-5.5-pro -p "<task>" --file "src/**"` for a browser-based review run.

How to check token cost before running an AI code review?โ–ผ

Run Oracle with `--dry-run summary --files-report` along with your prompt and file globs. This previews the payload and token spend without consuming any tokens, so you can trim the file set first.

Oracle CLI browser engine vs API engine, which should I use?โ–ผ

Use the browser engine for long ChatGPT Pro runs with GPT or Gemini models. Use `--engine api` when OPENAI_API_KEY or Azure config is set, or when you need Claude, Grok, Codex, or multi-model runs.

What happens when an Oracle CLI run times out or detaches?โ–ผ

Do not re-run; the session is stored under ~/.oracle/sessions. List recent runs with `oracle status --hours 72` and reattach with `oracle session <id> --render` to retrieve the result.

How do I exclude test files when attaching code to a prompt?โ–ผ

Pass negated globs to `--file`, for example `--file "src/**" --file "!src/**/*.test.ts"`. Oracle honors .gitignore, skips node_modules and build dirs by default, and rejects files over 1 MB.

Related Skills

Explore More Software Engineering Skillsโ†’
Hyeonjun0527Hyeonjun0527
1

refactor-repo

Scan multi-module codebases to identify and prioritize refactoring targets.

Community
Intermediate
hadpadrahulhadpadrahul

gsd-audit-fix

Automate code quality issue detection, classification, and test-verified fixes.

Community
Advanced
gaebalaigaebalai
2

pr-quality-gate

Run automated quality checks on pull requests before submission.

Community
Intermediate
AevonixAevonix

opencode

Delegate coding tasks to an autonomous OpenCode CLI agent.

Official
Advanced