Dangooy/trade-pipeline-skill

최근 기록된 소스 활동: 2026년 7월 26일 06:18

SkillsMP 카탈로그 업데이트: 2026년 11월 2일 18:02

수집된 skills: 2

GitHub 스타: 31
GitHub 포크: 7

AI 어시스턴트로 설치

이 프롬프트를 복사해 사용 중인 AI 어시스턴트에 입력하세요.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/Dangooy/trade-pipeline-skill.

저장소 README

README 원본 파일: README.md

README 원본 보기

README 전체 펼치기

# Trade Pipeline — Trade Documentation Automation Tool **English** | [中文](README_CN.md) | [Русский](README_RU.md) | [Technical Deep-Dive](README_DEV.md) > 📖 **中文用户请点这里：[完整中文文档 → README_CN.md](README_CN.md)** —— 一份询价单，自动生成报价单 / PI / CI / 装箱单，改一处四单联动。 One set of data, auto-generates your Quotation, PI, CI, and Packing List. No more copy-pasting between a dozen Excel files. <img src="cover.png" alt="Trade Pipeline workflow: automatically generating a Quotation, Proforma Invoice, Commercial Invoice, and Packing List from a single customer inquiry" width="800"> --- ## How to use it: an AI Skill This is an **AI Agent Skill** (in SKILL.md format). Once installed, you just talk to it in plain language — "Turn this inquiry into a Quotation," "The customer confirmed, generate the PI/CI/PL" — and the AI handles the whole process. No commands to memorize. SKILL.md is a cross-agent standard — besides Claude Code and WorkBuddy, agents like Codex, Kimi Code, and DeepSeek Harness can load it too. 👉 Install and use it: [with Claude Code](#use-skill) · [with Tencent WorkBuddy](#use-workbuddy) · [other agents](#other-agents) --- ## Does this sound like your week? - Customer sends an inquiry Excel → you manually **copy** product names, specs, and quantities into a Quotation - Customer confirms → you manually **copy the same data again** to make a PI - Goods are ready → you **copy it all again** to make the CI and Packing List - A quantity typo in the PI → the CI, PL, and customs paperwork **all inherit the error**, and you have to hunt them down one by one - Different customers need different PI formats (Russian customers want Russian, European customers want English) → you end up maintaining **several template sets** **Every document is essentially the same data in a different layout**, but you rebuild it from scratch every single time. Trade Pipeline's solution is simple: **maintain a single order record, and generate every document from it automatically. Change one thing, and all four documents update together.** --- ## What it does for you **Automatically turns** a customer's inquiry Excel into the full set of documents: | Document | Description | |------|------| | 📋 **Quotation** | Company letterhead, product line items, unit price column left blank for you to fill in, amount column auto-calculates as you fill | | 📄 **Proforma Invoice (PI)** | Seller/buyer information, payment terms, trade terms | | 📄 **Commercial Invoice (CI)** | Bilingual (Chinese/English) header, shipping marks, shipment info, SAY amount | | 📦 **Packing List (PL)** | Per-carton breakdown, carton count/weight/quantity, pallet summary | **Quotation** — fill in unit prices in the yellow-highlighted column (amounts calculate automatically); write them back to the order record with one click: ![Quotation](docs/2601_quotation.png) **Proforma Invoice (PI)** — seller/buyer header, grouped product rows, payment terms: ![PI](docs/2601_pi.png) **Commercial Invoice (CI)** — bilingual Chinese/English, shipping marks, shipment info, SAY amount in words: ![CI](docs/2601_ci.png) **Packing List (PL)** — grouped line items, carton count/weight/quantity, net/gross weight, pallet summary: ![PL](docs/2601_pl.png) --- ## Who this is for | Your situation | Good fit? | |---|---| | No ERP, running on Excel + email + WeChat | ✅ **Core use case, use it directly** | | Have Yonyou/Kingdee/Wangdiantong, but weak trade-document support | ✅ Good fit, fills the gap on document input/output | | Using an open-source ERP like Odoo / ERPNext | ✅ Can be integrated as an inquiry-parsing module | | Using SAP B1 / NetSuite / Dynamics 365 with a mature setup | ⚠️ Not much added value | | Tens of thousands of orders a year, already on EDI/API integration | ❌ Use an enterprise-grade solution instead | ### Best-fit profile - Annual order volume: **50–500 orders** - Product SKUs: **< 5,000** - Primary markets: **Russia / Eastern Europe / South America / Middle East** - Team size: **1–3 trade sales staff** > **No coding background at all?** That's fine. Once you've read the sections above, you'll know whether this is for you. The install and setup steps involve a bit of command-line work, but no programming knowledge is required — just copy and paste as you go. --- ## How it relates to your ERP Trade Pipeline is **not a replacement for your ERP**. ERPs handle inventory, finance, receivables/payables, and tax — this tool doesn't do any of that, and isn't meant to. What it fills in is the **front and back ends** that ERPs tend to handle poorly: | Where ERPs fall short | How Trade Pipeline fills the gap | |---|---| | Customer inquiry Excels need to be **manually entered** | Automatically extracts product data | | Inconsistent customer name spellings (especially common with Russian customers) that ERPs can't match | 4-layer fault-tolerant matching; if it can't match, it stops and lets you choose | | Every customer wants a different PI/CI format, and changing ERP templates means calling a consultant | Just edit a config file — takes 5 minutes | | Customer reorders rows after exporting the Quotation, and re-importing scrambles all the prices | Every row carries a hidden marker, so reordering rows never breaks anything | | No dedicated field for DIN/ISO/GOST standard numbers | Automatically recognizes and normalizes standard numbers | --- ## What it is not - ❌ **Not an ERP** — doesn't manage inventory, finance, or tax - ❌ **Not an online system** — no accounts, no customer support portal; all data stays on your own computer - ❌ **Not a multi-user collaboration platform** — best suited for teams of 1–3 people - ❌ **Not "AI doing your trade business for you"** — the AI only helps parse messily formatted inquiries; everything else is deterministic, rule-based logic - ❌ **Does not connect directly to customs** — it can prepare the data your customs broker needs, but it cannot submit directly to the Single Window system --- ## To be upfront: what industry this is built for This tool was built **for my own company**, so it's shaped around the characteristics of the **hardware / fastener industry**: - Pricing is **primarily weight-based** (KG / metric ton) - Product specs are relatively fixed (the DIN / ISO / GOST standard-parts world) - Packaging conventions are fairly standardized **If you're also in hardware / fasteners** (bolts, nuts, washers, standard parts, wire products, pipe fittings, flanges, bearings, seals, etc.), you can probably get it running just by updating your company info and the translation tables. **If you're in a different industry**, your specs, pricing basis (per piece / per set / per meter), and weight/packaging logic will all differ, so **this tool won't work out of the box** — you'd need to adapt it, mainly in these three places: | What to change | Where | |---|---| | Product recognition / Chinese-English translation | `understanding/canonicalizer.py` + the translation tables | | Pricing model (if not weight-based) | Pricing-detection logic in `understanding/` | | Document templates (headers, fields, layout) | The individual Writers under `writers/` | The framework itself is solid, but how much adaptation work you need depends on how complex your industry is. > In short: **hardware / fasteners can use it as-is; other industries should treat it as an adaptable foundation.** **Industries that would take more work**: apparel (complex size matrices), electronic components (nested BOMs), bulk commodities (futures-based pricing), cross-border e-commerce (tens of thousands of SKUs) — these require substantial rework, so go in with that expectation. --- ## What's planned for the future | Direction | Description | |------|------| | 🔜 Email assistance | Read customer info and quote history to help draft replies | | 🔜 Follow-up scripts | Generate WhatsApp / WeChat message drafts based on order status | | 🔜 Customs data package | Automatically compile the cargo description, HS codes, package count, and net/gross weight your customs broker needs | | 🔜 L/C review | Automatically cross-check key Letter of Credit terms against order data | | 🔜 Customer profiling | Track each customer's order frequency, value, and product categories | | 🔜 Pricing suggestions | When a new inquiry comes in, automatically reference historical closing prices to suggest a quote | > These are future directions — none of them exist in the current version yet. Items marked 🔜 are not coming immediately. --- <details> <summary>Want to try it? Click here for installation and usage</summary> ## Prerequisites You'll need two things installed on your computer (skip anything you already have): | Software | Purpose | Install guide | |------|------|----------| | **Python 3.12 or later** | Runs this tool | [python.org/downloads](https://www.python.org/downloads/) | | **Git** | Downloads the code | [git-scm.com/downloads](https://git-scm.com/downloads/) | > Not sure if you have them? Open a command line (Windows: press Win+R and type `cmd`; Mac: open "Terminal"), then type `git --version`, followed by `python --version` (**on Mac / Linux use `python3 --version`** — those systems have no bare `python` command). If a version number shows up, you're good. ## Installation <a id="use-skill"></a> ### Install and use it with Claude Code If you haven't used [Claude Code](https://claude.ai/code) before: it's Anthropic's official AI coding / automation tool. Install it once, and you can use it for documents, drafting emails, and organizing data going forward. Once the plugin is installed, **just talk to it in plain language** — no commands to memorize. **Step 1: Clone the repo and install the core engine** ```bash git clone https://github.com/Dangooy/trade-pipeline-skill.git cd trade-pipeline-skill # Create a virtual environment — don't skip this, see the note below python3 -m venv .venv && source .venv/bin/activate # Mac / Linux # Windows PowerShell: py -m venv .venv; .\.venv\Scripts\Activate.ps1 pip install -e . ``` > **Why the virtual environment**: modern macOS (Homebrew) and most Linux distros protect > their system Python — a bare `pip install` is refused with `externally-managed-environment`. > A venv is the officially recommended approach: everything stays inside the project folder > and nothing pollutes your system. > > Once activated your prompt shows `(.venv)`, and both `python` and `pip` resolve to that > environment — **no more `python` vs `python3` guessing**. After closing the terminal, re-run > `source .venv/bin/activate` (Windows: `.\.venv\Scripts\Activate.ps1`) when you come back. **Step 2: Load the plugin in Claude Code** This repo ships with a Claude Code plugin (`.claude-plugin/plugin.json`) containing two Skills: | Skill name | What it does | |---|---| | `trade-pipeline-init` | First-time setup wizard (company info, trade terms, first customer) | | `trade-pipeline-run` | Runs the documentation pipeline / price write-back | Launch Claude Code from within the repo directory, and use the `/plugin` command to load the local repo as a plugin (you'll need to trust this directory the first time). Once loaded, both Skills register automatically. **Step 3: Just talk to it** ```text Initialize configuration → triggers trade-pipeline-init, walks you through your company info step by step Turn examples/sample_inquiry.xlsx into a Quotation → triggers trade-pipeline-run, runs the full pipeline automatically The customer confirmed, write back prices and generate the PI/CI/PL → automatically writes back prices + generates the formal documents ``` > The Skill runs a deterministic engine behind the scenes to generate the documents — you never have to type parameters by hand. Just tell Claude what you need done, and it puts it together. <a id="use-workbuddy"></a> ### Install and use it with Tencent WorkBuddy If you're in China and using [WorkBuddy](https://codebuddy.cn/work) (Tencent's desktop AI agent), it works too — it's compatible with the SKILL.md skill format, so you just copy the skill directory over. > **Prerequisite**: Python 3.11+ and Git must already be installed on your computer. This skill calls the Python engine underneath, so this step can't be skipped. **Windows (PowerShell)** ```powershell # 1. Download the project and install the engine git clone https://github.com/Dangooy/trade-pipeline-skill.git cd trade-pipeline-skill py -m venv .venv; .\.venv\Scripts\Activate.ps1 pip install -e . # 2. Copy both skills into the WorkBuddy skills directory mkdir "$env:USERPROFILE\.workbuddy\skills" -Force Copy-Item -Recurse -Force ".\.claude\skills\trade-pipeline-init" "$env:USERPROFILE\.workbuddy\skills\" Copy-Item -Recurse -Force ".\.claude\skills\trade-pipeline-run" "$env:USERPROFILE\.workbuddy\skills\" ``` **Mac / Linux (Terminal)** ```bash # 1. Download the project and install the engine git clone https://github.com/Dangooy/trade-pipeline-skill.git cd trade-pipeline-skill python3 -m venv .venv && source .venv/bin/activate pip install -e . # 2. Copy both skills into the WorkBuddy skills directory mkdir -p ~/.workbuddy/skills cp -r .claude/skills/trade-pipeline-init ~/.workbuddy/skills/ cp -r .claude/skills/trade-pipeline-run ~/.workbuddy/skills/ ``` Once installed, trigger it manually in a WorkBuddy conversation: ```text @trade-pipeline-run Turn this inquiry into a Quotation ``` > Note: WorkBuddy runs on domestic models (Hunyuan / DeepSeek / GLM, etc.), not Claude. The skill's prompts are written for how Claude interprets instructions, so with a different model, triggering or step comprehension may occasionally be off — it's normal if it doesn't go smoothly the first time. Feel free to file an issue with feedback. <a id="other-agents"></a> ### Other SKILL.md-compatible agents (Codex / Kimi Code / DeepSeek Harness / Pi…) Any agent that supports the SKILL.md format can load these two skills — copy both directories from `.claude/skills/` into your agent's skills directory: | Agent | Skills directory | |---|---| | Claude Code | load via `/plugin` (recommended, see above) | | Codex CLI | `~/.codex/skills/` | | Kimi Code CLI | automatically reads `.claude/skills/` and other agents' skill directories | | DeepSeek Harness | `.dsh/skills/` | | Pi | `~/.pi/agent/skills/` | | Tencent WorkBuddy | `~/.workbuddy/skills/` (see above) | > Two honest caveats: (1) the skill prompts are tuned for how Claude interprets instructions — other models may occasionally mis-trigger or misread a step; (2) `trade-pipeline-init` uses Claude Code's `AskUserQuestion` interaction — other agents fall back to plain dialogue, which works but feels different. Check each agent's official docs for its exact skills directory. ## First-time setup Since your company information gets printed on the Quotation, PI, and CI, you'll need to fill in some basic details before first use. Tell it **"Initialize configuration"** in Claude Code (this triggers `trade-pipeline-init`), and it will ask you for the following, one item at a time: | Info | Used on | Required? | |------|----------|--------| | Company name (Chinese/English) | Header of every document | Yes | | Address | PI/CI header | Yes | | Contact person / email / phone | Quotation and PI | Yes | | Bank details | PI payment info | No (can add later) | | Trade terms | FOB / CIF / DDP / EXW / CFR | Yes | | Currency | USD / CNY / EUR | Yes | | Port of shipment | PI/CI footer | Yes | | First customer | Buyer information | No (can start with a placeholder customer `_new`) | > This information is stored in a file called `config/config.yaml`. YAML is a simple text format you can open and edit with any text editor — it reads like a shopping list, no programming knowledge required. ## Day-to-day use: just talk to Claude Once the plugin is installed, you don't need to memorize any commands — just tell Claude what you need in plain language. Common phrasings: | What you say to Claude | What it does | |---|---| | "Turn this inquiry into a Quotation" (with the Excel attached) | Parses the inquiry → generates a Quotation (for price negotiation with the customer) | | "The customer confirmed, write back prices and generate the PI/CI/PL" | Writes the filled-in unit prices back to the order record → generates the Proforma Invoice / Commercial Invoice / Packing List | | "This is a new customer, use a placeholder identity for the Quotation for now" | Generates the Quotation under a placeholder buyer identity; fill in customer details later | | "The customer name didn't match, help me confirm it" | Lists candidate customers for you to choose from, then continues generating | > **Recommended workflow**: generate the Quotation first to negotiate price, and only write back prices / generate the formal documents (PI/CI/PL) after the customer confirms. > This way you don't have to redo the whole document set repeatedly during the quoting stage. <details> <summary>Developer reference: the underlying CLI commands (what the Skill calls behind the scenes)</summary> ```bash # Phase 1: generate the Quotation only (for price negotiation with the customer) python -m trade_pipeline --input inquiry.xlsx --order 2601 --buyer global_fasteners --quote-only # Phase 2: after customer confirmation, write back prices + generate PI / CI / PL python -m trade_pipeline --price-update output/2601/2601_quotation.xlsx --model output/2601/2601_model.json # Generate everything in one go (for rush orders or demos): python -m trade_pipeline --input inquiry.xlsx --order 2601 --buyer global_fasteners # New customer (use a placeholder identity for now, fill in details later): python -m trade_pipeline --input inquiry.xlsx --order 2601 --buyer _new --quote-only # When the system can't match a customer name, it stops and generates review.json — confirm, then continue: python -m trade_pipeline --input inquiry.xlsx --order 2601 --confirm output/2601/2601_review.json ``` </details> ### Output files ``` output/2601/ ├── 2601_rfq.json # Data extracted from the inquiry ├── 2601_model.json # Order record (every document is generated from this) ├── 2601_quotation.xlsx # Quotation ├── 2601_pi.xlsx # Proforma Invoice ├── 2601_ci.xlsx # Commercial Invoice └── 2601_pl.xlsx # Packing List ``` </details> --- <details> <summary>Technical details (for developers and technical evaluators)</summary> The architecture diagram, 8-step pipeline, key design decisions, full CLI reference, testing approach, and tech stack are all covered in the separate technical deep-dive: 👉 **[README_DEV.md — Technical Deep-Dive](README_DEV.md)** </details> --- ## How this tool came to be I'm not a professional programmer — I work in trade sales at a manufacturing factory, or more precisely, I'm what's called a "second-generation factory owner's kid." Given the limited resources available to me, I really needed a powerful assistant-type tool: an AGENT. The reason this tool exists is simple: **I was spending several hours a week manually producing trade documents, and got sick of it.** Claude Code helped me turn years of accumulated business experience into a working automated system. Here's an example: the first version of the price write-back feature worked by row number — the price on row 3 got written back to row 3. Technically correct. Until one day a customer inserted a few group-header rows into the Quotation, and when I ran the write-back — every price got shifted out of place, and the PI inherited the same errors. I told Claude about the bug, and its first instinct was "exclude header rows during parsing." I said that wouldn't work — there's no predicting how a customer will edit an Excel file. We went back and forth for three rounds, and I finally suggested, "What if every row carried a hidden ID card?" Claude implemented the hidden UUID column approach. **This kind of design doesn't show up in programming tutorials, because it came from a real production bug.** > AI coding tools are at their most powerful when you bring deep domain knowledge — I know exactly what a PI should look like, because I've made hundreds of them by hand. --- ## Where your data lives All customer information, order data, and generated documents **stay on your own computer** — nothing gets uploaded to any server. | File | What it stores | |------|--------| | `config/config.yaml` | Your company info, customer info, trade terms (editable with any text editor) | | `output/order-number/` | Each order's record and its full set of generated documents | This means: - ✅ You have complete control over your data - ✅ You can track every change with Git - ⚠️ You're responsible for your own backups (recommend periodically copying to an external drive or encrypted cloud storage) > ⚠️ **One exception — optional LLM parsing (`--use-llm`)**: the default parser runs **entirely locally, with no network calls**. Only when you explicitly enable `--use-llm` does the tool send the raw inquiry contents (including customer names, products, and quantities) to the Anthropic cloud API to help parse unusual formats. This switch is **off by default and requires an explicit opt-in** — for sensitive or confidential documents, stay on the default local mode. --- ## About the author Built by Yang Tian (Ethan Yang) — factory-side trade practitioner, not a professional programmer. More trade AI skills: [tianji-skills](https://github.com/Dangooy/tianji-skills) (B2B lead research, RFQ intake, document verification). Public profile: [@Dangooy](https://github.com/Dangooy). --- ## License MIT — free to use, free to modify. --- Curious what changed in each release? <a href="https://github.com/Dangooy/trade-pipeline-skill/releases">Release notes</a> (full changelog in CHANGELOG.md) Ran into a problem? <a href="https://github.com/Dangooy/trade-pipeline-skill/issues">File an Issue</a> (no technical background needed — just describe what you saw and what you expected)

저장소 README를 불러오는 중…

이 저장소의 skills

생산, 계획 및 독촉 사무원 소프트웨어 개발자

직업 카테고리 2개 · 100% 분류됨

skill

직업 분류

설명

업데이트

trade-pipeline-run

생산, 계획 및 독촉 사무원

Execute the trade document pipeline (RFQ → Quotation → PI → CI → PL) or price write-back

원문 언어: 영어

2026-07-26

trade-pipeline-init

소프트웨어 개발자

Interactive setup wizard for first-time trade-pipeline configuration

원문 언어: 영어

2026-06-29

수집된 skill 2개 중 2개를 표시합니다.