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 forensic-transcript-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/forensic-transcript-translator)<a href="https://agentmods.dev/skills/fredchu/claude-dotfiles/forensic-transcript-translator"><img src="https://agentmods.dev/badge/skills/fredchu/claude-dotfiles/forensic-transcript-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/forensic-transcript-translator"><img src="https://agentmods.dev/badge/skills/fredchu/claude-dotfiles/forensic-transcript-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 | $0.00234 | $0.02621 |
| Opus 5.5 | $0.00094 | $0.01048 |
| Sonnet 5.5 | $0.00047 | $0.00524 |
| Haiku 4.5 | $0.00023 | $0.00262 |
Grade A, and why
forensic-transcript-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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
法證級逐字稿翻譯器 (Forensic Transcript Translator)
五階段流程，將英文 earnings call 逐字稿翻譯為台灣繁體中文，並以獨立審計確保零遺漏。
Phase 0: 結構指紋 → Phase 1: 術語鎖定 → Phase 2: 分段翻譯 → Phase 3: 法證審計 → Phase 4: 組裝輸出
模型路由策略
主對話（Opus 4.6）擔任指揮官，負責流程控制、術語決策、品質判斷。重型工作分派給 subagent：
| Phase | 執行者 | 模型 | 原因 |
|---|---|---|---|
| 0 結構指紋 | Task subagent (Bash) | haiku | 純腳本執行 |
| 1 術語建立 | 主對話自行處理 | opus（當前） | 需要判斷力 |
| 2 分段翻譯 | Task subagent (general-purpose) | sonnet | 翻譯重活，Sonnet 品質足夠且快 |
| 3a 腳本審計 | Task subagent (Bash) | haiku | 純腳本執行 |
| 3b 語意審計 | Task subagent (Explore) | haiku | 比對閱讀，不需生成能力 |
| 3c 問題修復 | 主對話自行處理 | opus（當前） | 需要精準重翻判斷 |
| 4 組裝輸出 | 主對話自行處理 | opus（當前） | 需要統整所有結果 |
Phase 2 的 Task 呼叫範例：
Task(
subagent_type="general-purpose",
model="sonnet",
prompt="你是法證級翻譯員。以下是術語表和翻譯規則...[完整規則]...請翻譯以下段落：[段落內容]"
)
Phase 3b 的 Task 呼叫範例：
Task(
subagent_type="Explore",
model="haiku",
prompt="你是獨立審計員。請比對以下兩份檔案...[EN_PATH]...[TW_PATH]..."
)
Phase 0: 結構指紋提取
- 使用 Read 工具讀取使用者提供的英文逐字稿檔案。
- 將原文存為工作目錄下的暫存檔：
[TICKER]_[QUARTER]_Transcript_EN.tmp。 - 執行結構指紋腳本：
python3 [SKILL_PATH]/scripts/structural_fingerprint.py [EN_TMP_PATH] --json - 記錄指紋結果（段落數、發言者序列、所有數字、字數），後續 Phase 3 比對用。
- 向使用者回報指紋摘要（段落數、發言者人數、數字總量），然後自動進入 Phase 1。
Phase 1: 動態術語表建立
- 載入基底術語表：讀取
references/glossary-base.md。 - 掃描原文，找出基底表中未涵蓋的公司專屬術語（產品名、業務指標、人名職稱）。
- 建立本次翻譯的完整術語表，格式：
## 本次專屬術語
| English | 中文 | 備註 |
|---------|------|------|
| Toast Capital | Toast Capital | 不翻譯 |
| Aman Narang | Aman Narang | CEO |
- 術語表自動生效，不暫停等待使用者確認。
- 自動進入 Phase 2。
Phase 2: 分段翻譯
翻譯原則（不可違反）
- 原子級鏡像：嚴禁摘要、刪減、優化語法。
- 口語贅詞保留："um" → 嗯, "you know" → 你知道的, "uh" → 呃, "well" → 這個, "I mean" → 我的意思是, "sort of" → 算是, "kind of" → 有點, "right?" → 對吧？
- 未完成句子：如實保留，用 ⋯⋯ 表示中斷。
- 自我糾正：如實保留（例："revenue was — sorry, operating income was"）。
- 數字格式：$479.1 million → 4.791億美元, 25% → 25%, 130,000 locations → 13萬個餐廳據點。所有數字加粗。
- 雙語標記：核心術語採「中文 (English)」格式，依術語表執行。
- 台灣在地化：使用台灣金管會與財經媒體慣用語。禁用簡體或港式詞彙。
What ships with it
4 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.
- 1mo ago First seen · 191 lines · 234 tokens per session scan A abbd285b2751
forensic-transcript-translator is a skill published in the GitHub repository fredchu/claude-dotfiles (2 stars, last pushed 2mo ago), licensed MIT. It adds 234 tokens to every session and 2,621 once invoked, about $0.0009 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
chinese-traditional-conversion
A language-conversion skill that changes Simplified Chinese into Traditional Chinese used in Taiwan. It also adapts vocabulary and phrasing for Taiwan.
chinese-content-writing-guideline
Language-specific guidelines for producing high-quality Traditional Chinese (zh-TW) content: script, full-width punctuation, spacing, forms of address, grammar constraints, and Taiwan terminology. Includes the no-calque rule against literal translations of English phrasal verbs such as 折入 for fold in. Use when writing…
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
grilling
A guided questioning process for testing a plan, decision, or idea. It maps dependent choices into a tree and asks only the questions that can be answered at each stage.
company-valuation
Estimate a public company's intrinsic value with DCF, relative (peer multiple), and sum-of-the-parts (SOTP) methods, then blend them into an implied share price with upside/downside vs the market price, a WACC and terminal-growth sensitivity grid, and bull/base/bear scenarios. Use this skill whenever the user asks…
alpha-vantage
Access real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. Use when fetching stock prices (OHLCV), company fundamentals (income statement, balance sheet, cash flow), earnings, options data, market…