Bundle prompts with selected files and directories into a single LLM request.
npx skills add https://github.com/elizaOS/eliza --skill oracle-elizaos
Please help me install this Agent Skill. Skill: oracle Source: https://github.com/elizaOS/eliza/tree/main/packages/skills/skills/oracle Command: npx skills add https://github.com/elizaOS/eliza --skill oracle-elizaos
This Skill helps developers get accurate answers by providing AI models with the necessary context from their codebase, overcoming the limitations of LLMs not having direct access to project files.
Use the oracle CLI to preview the token count for a task involving all files in the src directory, excluding test files.
High-intent search queries and answers about installing and using this skill.
To provide codebase context to an LLM, you bundle prompts with selected files and directories into a single request. This allows the AI to understand specific code files and deliver context-aware answers for debugging or explanations.
You can include or exclude specific files when prompting an LLM by using glob patterns. This filters your source files, ensuring only relevant code context is bundled into the request for targeted solutions.
Yes, you can use prompt templating for complex codebase analysis tasks. This feature structures your contextual prompts, allowing you to manage file inclusion and session management for interacting with models like GPT-5.2 Pro.
Contextual prompting works with both API and browser engines for LLMs. This support allows you to interact with models like GPT-5.2 Pro directly, managing your code context and sessions across different interaction methods.
LLMs give inaccurate answers when debugging because they lack direct access to your project files. Bundling relevant source files and error messages into the prompt provides the necessary codebase awareness for targeted solutions.
The best way to preview the token count for a codebase prompt is using the CLI. It calculates the size of your bundled files and directories, ensuring your contextual request fits within the LLM's context limits.
YH-05Scan codebases and update Markdown documentation with directory trees and dependency diagrams.
PatkikIdentify and fix issues in AI-generated Laravel code through targeted feedback.
sarathi-aimlBundle prompts and files into a single contextual request for AI answers.
brikkoAIBundle repository files and prompts into a single request for second AI models.
