Bundle prompts with selected files and directories for AI model context.
npx skills add https://github.com/openclaw/openclaw --skill oracle-openclaw
Please help me install this Agent Skill. Skill: oracle Source: https://github.com/openclaw/openclaw/tree/main/skills/oracle Command: npx skills add https://github.com/openclaw/openclaw --skill oracle-openclaw
This Skill enables AI models to understand and interact with your codebase by bundling prompts with relevant files, allowing for context-aware code analysis and generation.
Use the oracle skill to preview the token count for a task using all files in the src directory.
High-intent search queries and answers about installing and using this skill.
You provide repo context by bundling natural language prompts with selected files and directories, enabling the AI to understand and interact with your specific codebase for context-aware analysis.
Prompt bundling for AI code generation is the process of combining natural language instructions with relevant code snippets and file contents to create a comprehensive input payload for models like GPT-5.2 Pro.
Yes, you can preview the token count before sending files to an AI model by using the dry-run feature, which calculates the token payload for selected directories without executing the actual API request.
Yes, this prompt bundling approach supports both API and browser engines, allowing you to interact with models like GPT-5.2 Pro through your preferred connection method while maintaining session management.
The best way to debug a complex issue using AI is to bundle the relevant source files, error logs, and test cases together into a single prompt, enabling the model to pinpoint the problem and suggest a targeted fix.
You manage file attachment patterns by selecting specific files and directories from your project to include in the prompt bundle, ensuring the AI receives only the necessary repository context for the task.
GoogleDevRelExplorationsScan a repository and write a .cercano/context.md file.
steipeteBundle prompts and files into a single one-shot request for repository-context aware answers.
adiytharpansaOptimize AI agent prompts, task decomposition, and tool selection workflows.
trotsky1997Automate browser interactions in Cursor IDE via MCP protocol.
