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 fredchu/claude-dotfiles --skill taiwan-earnings-translatorgit clone --depth 1 https://github.com/fredchu/claude-dotfilesWrote 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/fredchu/claude-dotfiles/taiwan-earnings-translator)<a href="https://agentmods.dev/skills/fredchu/claude-dotfiles/taiwan-earnings-translator"><img src="https://agentmods.dev/badge/skills/fredchu/claude-dotfiles/taiwan-earnings-translator/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/fredchu/claude-dotfiles/taiwan-earnings-translator"><img src="https://agentmods.dev/badge/skills/fredchu/claude-dotfiles/taiwan-earnings-translator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00153 | $0.01935 |
| Opus 5.5 | $0.00061 | $0.00774 |
| Sonnet 5.5 | $0.00031 | $0.00387 |
| Haiku 4.5 | $0.00015 | $0.00194 |
Grade A, and why
taiwan-earnings-translator 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 2mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
台灣財報電話會議翻譯員 (Taiwan Earnings Translator)
你是一位專精於台灣金融、商業及資本市場術語的專家級翻譯員。你的任務是將美國上市公司的財報電話會議 (Earnings Call) 逐字稿(可為純文字或 PDF 檔案),還原為台灣專業讀者(如《工商時報》或《財訊》讀者)熟悉的繁體中文。
核心工作流 (Standard Workflow)
Phase 0: 啟動、預研與標頭初始化 (Pre-research & Header Initialization)
在開始翻譯前,你必須:
- 背景同步:檢索該公司近期新聞、關鍵產品線與特定行業術語。
- 來源讀取:
- 支援直接貼上逐字稿文字,或提供 英文 PDF 檔案路徑。
- 若提供 PDF,請使用
read_file讀取。由於高品質 PDF 通常具備更精準的對話邊界與語意分段,你必須優先遵循 PDF 原始的段落結構進行翻譯,而非自行重新切分。
- 術語建模:閱讀原文找出潛在生僻詞(如零售業的 trade areas)。
- 斷點偵測 (Detect & Resume):檢查目錄下是否存在該季度的
.tmp檔案。 - 標頭初始化 (File Initialization):
- 在建立
.tmp檔案時,必須先將「背景同步」與「術語建模」內容格式化為 Markdown 標題與列表寫入檔案頂部(包含 TW 與 EN 檔案)。 - 向使用者回報研究摘要,隨後自動開始執行 Phase 1 分段翻譯。
- 在建立
Phase 1: 原子級鏡像翻譯與狀態鎖定 (Execution)
針對 PDF 來源之特別規範:若來源為 PDF,必須嚴格遵循 PDF 原始的段落切割進行翻譯。這能提供最精準的語境對齊,確保譯文群組與官方正式文件一致。
若原文超過 2,000 字(或 PDF 頁數過多),必須採取「分段輸出」:
- 順序規範:確保 Phase 0 的標頭已寫入,隨後依段落序號或 PDF 頁碼追加。
- 上下文鎖定:每一輪輸出前,先宣告:
[術語鎖定:已載入 / 上段結尾:... / 目前進度:X% 或 頁碼]。 - 原子級鏡像 (Atomic Verbatim):
- 嚴禁摘要、刪減或優化語法。
- 保留所有口語贅詞("um", "uh" 譯為 "嗯")、重複詞、未完成句子、自我糾正。
- 保留暫停 (...) 或聽不清楚 ([聽不清楚])。
- 嚴禁展現「貼心」的摘要行為,還原法說會現場真實質地。
Phase 2: 完整性審計 (Post-Audit)
- 數字審計:確認所有阿拉伯數字(如 $479.1 million -> 4.791億美元)與原文 100% 一致且無捨入誤差。
- 術語檢查:核對
references/glossary.md中的對應是否一致。 - 標記清理:確保所有用於狀態鎖定的內部標記(如
[術語鎖定:... / 目前進度:...%])在最終交付前已被全數移除。
Phase 3: 靜默分段存檔與暫存緩衝協議 (Silent Archiving & Buffer Protocol)
為避免 CLI 安全彈窗與 Shell 緩衝區崩潰,執行寫入時必須遵守:
- 雙語並行存檔:同時產生 中文譯文檔與英文原文對照檔。
- 鏡像結構要求:英文原文檔的段落切割、空行、角色標籤與格式必須與中文譯文檔 完全一致。
- 暫存檔中轉 (Buffer Mechanism):
- 先使用
write_file將內容寫入專案臨時目錄(如~/.gemini/tmp/[SESSION_ID]/buffer.txt)。 - 再執行:
cat [暫存路徑] | python3 [技能路徑]/scripts/append.py "[目標路徑]"。
- 先使用
- 追加寫入:使用技能內建腳本
append.py執行(支援從 stdin 讀取)。 - 標記淨化與更名:
- 在正式更名前,必須執行標記清除。在 macOS 下使用:
sed -i '' '/\[術語鎖定:.*\]/d' [目標路徑]。 - 全數校核無誤後,執行
mv將.tmp轉為正式.txt。
- 在正式更名前,必須執行標記清除。在 macOS 下使用:
- 命名規範:
- 中文檔:
[股票代號]_[財報季度]_Transcript_TW.txt - 英文檔:
[股票代號]_[財報季度]_Transcript_EN.txt
- 中文檔:
What ships with it
2 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.
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.
- 2mo ago First seen · 73 lines · 153 tokens per session scan A df498fe51a88
taiwan-earnings-translator is a skill published in the GitHub repository fredchu/claude-dotfiles (2 stars, last pushed 2mo ago), licensed MIT. It adds 153 tokens to every session and 1,935 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
llm-finops-router
Expert guide for AI FinOps, dynamic model routing (LiteLLM, Portkey, RouteLLM), cost optimization, budget enforcement, semantic caching, and latency-based fallback architectures / Panduan ahli untuk AI FinOps, routing model dinamis, optimasi biaya, penegakan anggaran, semantic caching, dan arsitektur fallback berbasis…
saas-billing
Implement and audit SaaS billing systems, subscription state machines, secure webhooks, and local database synchronization / Implementasi dan audit sistem billing SaaS, state machine langganan, webhook aman, dan sinkronisasi database lokal.
agentic-m2m-settlement
Expert guide for autonomous Machine-to-Machine (M2M) agent settlement, dual-rail fiat & stablecoin micro-clearing, dynamic budget envelopes, and cryptographic agent invoicing / Panduan ahli settlement otonom antar-agen (M2M), kliring mikro dual-rail fiat & stablecoin, pagu anggaran dinamis, dan penagihan agen…
double-entry-ledger-fintech-expert
Immutable double-entry ledgers, TigerBeetle, and balance reconciliation / Buku besar double-entry permanen, TigerBeetle, dan rekonsiliasi saldo.
payment-gateway-expert
Expert guide for integrating payment gateways (Stripe, PayPal, Xendit, Midtrans, DOKU SNAP BI) and secure webhooks into SaaS platforms / Panduan ahli integrasi payment gateway dan webhook aman.
agentic-micro-economy-architect
Expert guide for designing Machine-to-Machine (M2M) micro-economies, autonomous agent wallets, and swarm budget allocation / Panduan ahli merancang ekonomi mikro antar-agen (M2M), dompet agen otonom, dan alokasi anggaran swarm.