Does Oracle support browser-based models?

Yes, it features a browser engine mode specifically designed for human-in-the-loop workflows with models like GPT-5.2 Pro in ChatGPT.

What does the Oracle skill do in Claude Code?

Oracle bundles your prompt and selected codebase files into a single request so a second AI model can provide a high-context review or validation.

Can I resume a review if the connection drops?

Absolutely. Oracle stores sessions in a local directory, allowing you to list and reattach to existing IDs without re-running the prompt.

Is my sensitive data protected?

Oracle allows you to explicitly exclude files using '!' patterns and encourages redacting secrets like .env files before bundling context.

How does Oracle handle large codebases?

It uses smart globbing and .gitignore support to filter files, includes a 1MB per-file cap, and provides dry-run token reports to help you stay within model limits.

Oracle Code Reviewer

Name: Oracle Code Reviewer
Author: xiaxingxiaowei1983

byxiaxingxiaowei1983

0•

협업 도구

Bundles repository context into high-fidelity prompts for second-model code reviews and architectural cross-validation.

Oracle is a specialized CLI-driven skill that allows Claude to package specific project files and directories into a single 'one-shot' request for review by secondary AI models. By utilizing either API connections or browser automation, it facilitates deep-dive debugging, complex refactoring, and design checks that benefit from a second opinion. It features robust session management, token budget monitoring, and smart context filtering to ensure that external models receive the most relevant information without exceeding limits or compromising security.

주요 기능

01Session Persistence: Stores and reattaches to long-running review sessions to prevent work loss.

02Token Budgeting: Provides dry-runs and file reports to estimate token usage before execution.

03Smart Filtering: Respects .gitignore and automatically excludes build artifacts and dependency folders.

040 GitHub stars

05Multi-Engine Execution: Seamlessly switches between API-based reviews and browser automation.

06Context Bundling: Packages prompts with files, directories, and globs into a single request.

사용 사례

01Cross-validating major architectural refactors with secondary high-reasoning models.

02Deep debugging of repository-wide issues by providing full context to a 'human-in-the-loop' browser session.

03Generating comprehensive patch plans and test cases by feeding context-rich prompts to specialized LLMs.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add xiaxingxiaowei1983/openclaw oracle

For use in Claude.ai and ChatGPT