auto-quotation-system
Build a reusable quotation workflow for software projects from markdown requirements, feature outlines, or mind-map screenshots that have been transcribed into text. Use when Codex needs to mine historical quotation DOCX files, normalize pricing inputs, estimate module-level effort, generate a quotation draft in markdown and JSON, or prepare the workflow for later migration into OpenClaw.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/549800894/auto-quotation-system-openclawAuto 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:
- If the user provides markdown or a plain-text requirement document, use it directly.
- 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.
- 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.
Use this normalized structure:
- Project name
- Delivery channels
- Business goal
- Feature list
- Non-functional requirements
- Assumptions and exclusions
Read references/quotation-data-model.md when you need the exact input and output shape.
2. Build or refresh the historical quotation corpus
When the task needs historical calibration, run:
python scripts/extract_docx_corpus.py \
--input-dir /path/to/history-docx-dir \
--output /path/to/work/quotation-corpus.json
This script extracts:
- Paragraph text
- Table rows
- Section labels
- Image counts
- Domain hints
- Top keywords per document
Use the corpus to find similar past quotations, common section layouts, and common delivery boundaries. Treat the historical documents as calibration data, not as exact truth to copy.
3. Generate a quotation draft
After the requirement is normalized, run:
python scripts/generate_quote_draft.py \
--input /path/to/requirement.md \
--project-name "项目名称" \
--vendor-name "深圳市小程序科技有限公司" \
--quote-date "2026-04-07" \
--tax-note "含税 1 个点普票" \
--corpus /path/to/work/quotation-corpus.json \
--sample-library assets/seed-quote-sample-library.json \
--profiles assets/seed-quote-calibration-profiles.json \
--rate-cards assets/seed-domain-rate-cards.json \
--output-md /path/to/work/quote.md \
--output-json /path/to/work/quote.json \
--output-docx /path/to/work/quote.docx \
--docx-renderer auto
The generator currently produces:
- Requirement summary
- Module-level quotation detail
- Role-based effort summary
- Suggested payment schedule
- Delivery boundaries
- Similar historical cases
- Open questions
The generator uses a hybrid estimation strategy:
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-549800894-auto-quotation-system-openclaw": {
"enabled": true,
"auto_update": true
}
}
}