custom_prompt
Execute custom prompts for code analysis and generation tasks using local LLM with optional file context support for single or multi-file projects.
Instructions
Universal fallback executor for any custom prompt with optional file context. Uses dynamic token allocation based on your loaded model - can handle everything from quick tasks to comprehensive multi-file analysis. The Swiss Army knife when no other specialized function matches your needs.
WORKFLOW: Flexible analysis and generation for any development task TIP: Provide clear instructions for any analysis or generation task SAVES: Claude context for strategic decisions
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| analysisDepth | No | Level of analysis detail | detailed |
| analysisType | No | Type of analysis to perform | general |
| code | No | The code to analyze (for single-file analysis) | |
| context | No | Optional structured context object for the task | |
| filePath | No | Path to single file to analyze | |
| files | No | Array of specific file paths to include as context | |
| language | No | Programming language (if applicable) | text |
| maxDepth | No | Maximum directory depth for multi-file discovery (1-5) | |
| projectPath | No | Path to project root (for multi-file analysis) | |
| prompt | Yes | The custom prompt/task to send to local LLM | |
| working_directory | No | Working directory context (defaults to current working directory) |
Input Schema (JSON Schema)
{
"properties": {
"analysisDepth": {
"default": "detailed",
"description": "Level of analysis detail",
"enum": [
"basic",
"detailed",
"comprehensive"
],
"type": "string"
},
"analysisType": {
"default": "general",
"description": "Type of analysis to perform",
"enum": [
"general",
"technical",
"creative",
"analytical"
],
"type": "string"
},
"code": {
"description": "The code to analyze (for single-file analysis)",
"type": "string"
},
"context": {
"description": "Optional structured context object for the task",
"type": "object"
},
"filePath": {
"description": "Path to single file to analyze",
"type": "string"
},
"files": {
"description": "Array of specific file paths to include as context",
"type": "array"
},
"language": {
"default": "text",
"description": "Programming language (if applicable)",
"type": "string"
},
"maxDepth": {
"default": 3,
"description": "Maximum directory depth for multi-file discovery (1-5)",
"type": "number"
},
"projectPath": {
"description": "Path to project root (for multi-file analysis)",
"type": "string"
},
"prompt": {
"description": "The custom prompt/task to send to local LLM",
"type": "string"
},
"working_directory": {
"description": "Working directory context (defaults to current working directory)",
"type": "string"
}
},
"required": [
"prompt"
],
"type": "object"
}