Auto Quotation System

Overview

Use this skill to turn historical quotation files and a new requirement document into a structured quotation draft. Prefer module-level estimation, explicit assumptions, and stable JSON output over a single total-price guess.

This skill is intended to run in both macOS and Windows/OpenClaw environments. Avoid hard-coded local paths, prefer python over platform-specific launchers in documentation, and prefer the native DOCX renderer when cross-platform stability matters.

Workflow

1. Normalize the input

Follow this decision order:

1. If the user provides markdown or a plain-text requirement document, use it directly.
2. If the user provides a mind-map image or a screenshot embedded in a document, first transcribe it into structured markdown with a multimodal step.
3. If the user provides a DOCX requirement file, extract or summarize the requirement text before pricing.

Do not estimate directly from an unreadable image. First convert the mind map into a text outline with modules, features, and notable dependencies.