skills.rest
chebizarro
chebizarroCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

oracle

Bundle prompts with project files for AI-driven code analysis.

Updated Mar 2, 2026
Search Tags:#developer tools#debugging#context#ai#llm#code
One-click install
npx skills add https://github.com/chebizarro/swarmstr --skill oracle-chebizarro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/chebizarro/swarmstr/tree/main/skills/oracle
Command: npx skills add https://github.com/chebizarro/swarmstr --skill oracle-chebizarro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines complex coding tasks by allowing AI models to understand and reason about your project's codebase, providing context-aware solutions and code generation.

Core Features & Use Cases

  • Codebase Contextualization: Bundles prompts with selected files to provide AI with relevant project context.
  • Multi-Engine Support: Works with various AI engines (browser-based like GPT-5.2 Pro, or API-based for others).
  • Session Management: Supports long-running tasks with session reattachment and slugging for readability.
  • Use Case: Debugging a complex issue by providing the AI with specific source files and error messages to generate a patch plan and tests.

Quick Start

Use the oracle skill to preview the token count for a task involving all files in the src directory, excluding test files.

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I provide AI with codebase context for code analysis and problem-solving?▼

You provide codebase context for AI code analysis by bundling your text prompts with specified project files. This allows the AI model to reason about your source code and generate context-aware solutions.

Can I estimate token counts before sending project files to an LLM?▼

Yes, you can estimate token counts before sending project files to an LLM by using a dry-run analysis. This previews the token count for your task, allowing precise context selection and exclusion patterns.

Does AI code analysis work with both browser-based and API-based LLM engines?▼

AI code analysis works with both API-based and browser-based LLM engines. This multi-engine support allows you to choose your preferred AI engine for generating patches and debugging code.

How do I manage long-running AI tasks for debugging complex codebase issues?▼

You manage long-running AI tasks for debugging complex issues using session management features. This includes session reattachment and slugging for readability, ensuring you can track extended problem-solving processes.

What is the best way to select specific source files for AI-driven code debugging?▼

The best way to select specific source files for AI-driven code debugging is through file globbing and exclusion patterns. This precise context selection ensures the AI only receives relevant project files.

Related Skills

Explore More Software Engineering Skills→
lawvablelawvable
630

xlsx-processing-openai

Automates spreadsheet processing using Python libraries and AI-guided prompts.

Official
Advanced
outfitter-devoutfitter-dev
2

cli-testing

Run automated Navigator CLI tests with bun and navigator-server.

Official
Intermediate
steipetesteipete
385.7k

oracle

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

Community
Advanced
gonzalezpazmonicagonzalezpazmonica
47

context-optimized-dev

Manage AI context window usage and define sub-agent delegation patterns.

Community
Advanced