Loading...
Loading...
This expert prompt generates fully valid, customized opencode.json files for OpenCode AI agents, supporting custom prompts, model overrides, additional agents, and extra settings with precise structure from official docs.
You are an expert OpenCode configuration engineer. Your task is to generate a complete, valid JSON file for the opencode.json config based on the following specifications.
Key guidelines:
- Use the exact structure shown in OpenCode docs: root object with 'agent' key containing sub-objects for each agent.
- For prompts, use the '{file:./prompts/[FILENAME].txt}' format with relative paths.
- Paths are relative to the config file location.
- Include model overrides if specified.
- Ensure JSON is valid, properly indented, and ready to save as opencode.json.
- Support global and project-specific configs.
Specifications:
- Agent name: [AGENT_NAME] (e.g., 'review', 'plan', 'implement')
- Custom system prompt file: [PROMPT_FILE_PATH] (e.g., './prompts/code-review.txt')
- Model override: [MODEL_NAME] (e.g., 'claude-3-5-sonnet-20240620' or leave empty for default)
- Additional agents: [ADDITIONAL_AGENTS] (JSON-like list of other agents, e.g., {'plan': {'model': 'gpt-4o-mini'}} or 'none')
- Other config options: [EXTRA_CONFIG] (e.g., custom settings or 'none')
Output ONLY the complete JSON config in a code block, no explanations.
Example output structure:
{
"agent": {
"[AGENT_NAME]": {
"prompt": "{file:[PROMPT_FILE_PATH]}",
"model": "[MODEL_NAME]"
}
}
}This prompt generates a comprehensive Markdown roadmap for building professional, interactive, agentic CLI coding tools with stunning TUIs, inspired by Claude Code and Aider. Customize placeholders and feed to an AI for an executable build plan.
Generate ultra-detailed, canonical image prompts for Simpsons characters like Ralph Wiggum, optimized for AI generators like Midjourney or DALL-E, ensuring faithful 2D cel-shaded portraits with no background.
Generate a comprehensive, step-by-step Markdown tutorial for building a production-ready Flask web app using a strict 3-layer architecture (presentation, business logic, data), fully customizable for any app functionality.
This reusable prompt template enhances raw AI skill descriptions into clear, structured, markdown-formatted documentation with actionable instructions, examples, and SEO optimization for maximum usability.
Transform vague AI skill descriptions into clear, structured, and professional documentation with this expert prompt template designed for technical writers and prompt engineers.
A professional prompt template for thorough AI-powered code reviews, assessing readability, performance, security, best practices, bugs, and design with scored feedback, detailed breakdowns, refactored code, and prioritized fixes.