Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Moksa1123/taiwan-ecommerce-toolkit --skill taiwan-invoicegit clone --depth 1 https://github.com/Moksa1123/taiwan-ecommerce-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/moksa1123/taiwan-ecommerce-toolkit/taiwan-invoice)<a href="https://agentmods.dev/skills/moksa1123/taiwan-ecommerce-toolkit/taiwan-invoice"><img src="https://agentmods.dev/badge/skills/moksa1123/taiwan-ecommerce-toolkit/taiwan-invoice/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/moksa1123/taiwan-ecommerce-toolkit/taiwan-invoice"><img src="https://agentmods.dev/badge/skills/moksa1123/taiwan-ecommerce-toolkit/taiwan-invoice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Output Handling · line 311 Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00086 | $0.05296 |
| Opus 5 | $0.00043 | $0.02648 |
| Sonnet 5 | $0.00017 | $0.01059 |
| Haiku 4.5 | $0.00009 | $0.00530 |
Grade A, and why
taiwan-invoice scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taiwan E-Invoice Development Skill
此技能涵蓋台灣電子發票 API 整合開發，包含綠界 (ECPay)、速買配 (SmilePay)、光貿 (Amego)、ezPay (藍新集團) 與 PayNow (立吉富) 五家服務商。
快速導覽
相關文件
使用此技能時，請參考專案中的 API 規格文件：
references/ECPAY_API_REFERENCE.md- 綠界 API 規格references/SMILEPAY_API_REFERENCE.md- 速買配 API 規格references/AMEGO_API_REFERENCE.md- 光貿 API 規格references/EZPAY_API_REFERENCE.md- ezPay 簡單付 API 規格（藍新金流集團）references/PAYNOW_API_REFERENCE.md- 立吉富 PayNow API 規格（含 POS 機批次取號流程）- EXAMPLES.md - 程式碼範例集
智能工具
scripts/search.py- BM25 搜索引擎（查詢 API、錯誤碼、欄位映射）scripts/recommend.py- 加值中心推薦系統scripts/generate-invoice-service.py- 服務代碼生成器scripts/persist.py- 持久化配置工具（MASTER.md 生成）data/- CSV 數據檔（providers, operations, error-codes, field-mappings, tax-rules, troubleshooting, reasoning）
何時使用此技能
- 開發電子發票開立功能
- 整合台灣電子發票服務商 API
- 實作 B2C（二聯式）或 B2B（三聯式）發票
- 處理發票列印、作廢、折讓等功能
- 處理加密簽章（AES、MD5）
- 解決發票 API 整合問題
智能搜索與推薦
搜索引擎 (search.py)
使用 BM25 算法在資料庫中搜索相關資訊：
# 搜索加值中心
python scripts/search.py "ecpay" --domain provider
# 搜索錯誤碼
python scripts/search.py "10000016" --domain error
# 搜索欄位映射
python scripts/search.py "MerchantID" --domain field
# 搜索稅務規則
python scripts/search.py "B2B 稅額計算" --domain tax
# 搜索疑難排解
python scripts/search.py "列印空白" --domain troubleshoot
# JSON 輸出
python scripts/search.py "折讓" --format json
搜索域：
| 域 | 說明 | CSV 檔案 |
|---|---|---|
provider |
加值中心比較 | providers.csv |
operation |
API 操作端點 | operations.csv |
error |
錯誤碼查詢 | error-codes.csv |
field |
欄位映射 | field-mappings.csv |
tax |
稅務計算規則 | tax-rules.csv |
troubleshoot |
疑難排解 | troubleshooting.csv |
reasoning |
推薦決策規則 | reasoning.csv |
推薦系統 (recommend.py)
根據需求自動推薦最適合的加值中心：
# 高交易量電商
python scripts/recommend.py "電商 高交易量 穩定"
# → 推薦 ECPay (市佔率高，穩定性佳)
# 快速整合需求
python scripts/recommend.py "簡單 快速 小型專案"
# → 推薦 SmilePay (整合最簡單)
# API 設計優先
python scripts/recommend.py "API 設計 MIG標準"
# → 推薦 Amego (MIG 4.0 最新標準)
# JSON 輸出
python scripts/recommend.py "穩定 文檔完整" --format json
What ships with it
34 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CLAUDE.md 4.6 KB
- data/carrier-types.csv 354 B
- data/error-codes.csv 6.5 KB
- data/field-mappings.csv 4.4 KB
- data/operations.csv 3.9 KB
- data/providers.csv 3.9 KB
- data/reasoning.csv 6.6 KB
- data/tax-rules.csv 1.3 KB
- data/troubleshooting.csv 5.8 KB
- EXAMPLES.md 23 KB
- examples/ecpay-invoice-example.py 20 KB runs code
- examples/ezpay-invoice-example.py 15 KB runs code
- examples/opay-invoice-example.py 11 KB runs code
- examples/paynow-invoice-example.py 12 KB runs code
- examples/sunpay-invoice-example.py 12 KB runs code
- README.md 4.5 KB
- references/AMEGO_API_REFERENCE.md 28 KB
- references/ECPAY_API_REFERENCE.md 18 KB
- references/EZPAY_API_REFERENCE.md 40 KB
- references/MOF_EINVOICE_API_REFERENCE.md 15 KB
- references/OPAY_API_REFERENCE.md 24 KB
- references/PAYNOW_API_REFERENCE.md 23 KB
- references/SMILEPAY_API_REFERENCE.md 26 KB
- references/SUNPAY_API_REFERENCE.md 15 KB
- references/VAC_LANDSCAPE.md 7.3 KB
- scripts/core.py 12 KB runs code
- scripts/error_handler.py 13 KB runs code
- scripts/generate-invoice-service.py 24 KB runs code
- scripts/persist.py 9.3 KB runs code
- scripts/recommend.py 13 KB runs code
- scripts/search.py 8.0 KB runs code
- scripts/test_recommend.py 4.0 KB runs code
- scripts/test_search.py 4.2 KB runs code
- scripts/test-invoice-amounts.py 3.5 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 514 lines · 86 tokens per session scan A 78c20015da4d
taiwan-invoice is a skill published in the GitHub repository Moksa1123/taiwan-ecommerce-toolkit (47 stars, last pushed 24d ago), licensed MIT. It adds 86 tokens to every session and 5,296 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.