The Oracle CLI helps you use an AI model to review, debug, refactor, or design your code. You pick the files and write a short task. The tool bundles them together and sends them to the AI for a second opinion.
It works in two ways. The browser engine runs inside ChatGPT Pro for long thinking. The API engine uses your own OpenAI key. You can preview the token cost before sending anything. This saves time and money.
Use --dry-run to check what will be sent. Use --engine browser for long sessions. The tool stores sessions so you can reattach if it times out. Treat the AI output as advice and always test your code.
Global
mkdir -p ~/.claude/skills/oracleProject
mkdir -p .claude/skills/oracleSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly