ask-gemini
Analyze files, execute scripts, and request AI insights using model selection, sandbox mode, and structured edits. Supports file inclusion (@ syntax) and safe code testing in an isolated environment.
Instructions
model selection [-m], sandbox [-s], and changeMode:boolean for providing edits
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| changeMode | No | Enable structured change mode - formats prompts to prevent tool errors and returns structured edit suggestions that Claude can apply directly | |
| chunkCacheKey | No | Optional cache key for continuation | |
| chunkIndex | No | Which chunk to return (1-based) | |
| model | No | Optional model to use (e.g., 'gemini-2.5-flash'). If not specified, uses the default model (gemini-2.5-pro). | |
| powershellPath | No | Optional custom PowerShell executable path (e.g., 'C:\Windows\System32\WindowsPowerShell\v1.0\powershell.exe' or 'pwsh'). If not specified, auto-detects available PowerShell. | |
| prompt | Yes | Analysis request. Use @ syntax to include files (e.g., '@largefile.js explain what this does') or ask general questions | |
| sandbox | No | Use sandbox mode (-s flag) to safely test code changes, execute scripts, or run potentially risky operations in an isolated environment |