prompt
Prompt rewriting tool: rewrites user natural language into structured high-quality prompts directly usable for image/video/audio/Agent generation.
Prompt rewriting tool: rewrites user natural language into structured high-quality prompts directly usable for image/video/audio/Agent generation.
Overview
| Field | Value |
|---|---|
| Model ID | prompt |
| CLI | dlazy prompt |
| MCP | prompt (Claude Code surfaces this as mcp__dlazy__prompt) |
| Type | text |
| Execution | Returns synchronously |
| Batch | Supports --batch <n> parallel fan-out |
Parameters
| Arg | Type | Required | Notes |
|---|---|---|---|
input | string | Yes | Input Text |
language | string | No | Language; default "en-US" |
type | "agent" | "image" | "video" | "audio" | "3d" | Yes | Type |
inputParams | string | No | Input Parameters |
models | array<string> | No | Model IDs |
--input @file.jsonor--input '{...}'can supply all args at once; flags take precedence over--inputkeys.
CLI Examples
dlazy prompt --help
dlazy prompt --input "value" --type "agent"
dlazy prompt --input "value" --type "agent" --dry-run
dlazy prompt --input "value" --type "agent" --batch 4MCP
MCP is consumed by AI clients, not handwritten. Once dLazy is registered as an MCP server the tool appears in the client's tool list — Claude Code surfaces it as mcp__dlazy__prompt; generic clients (e.g. OpenClaw) call it as prompt.
See MCP setup for how to add the server.
Output
{
"outputs": [
{ "type": "json", "id": "o_...", "value": { /* tool-specific payload */ } }
]
}Structured payloads are returned as json outputs; the inner shape is tool-specific.
fun-asr
Alibaba Bailian Fun-ASR recording transcription. Supports Chinese, English and other languages, with auto language detection and speaker diarization. Suitable for subtitles, transcription, and meeting notes.
rename
File renaming assistant tool: generates clearer new filenames based on file content and user intent, suitable for asset organization and batch naming.