Sean Lu
Sean Lu

Sean Lu

元智資管大二。用 $0 成本的工具和自動化,把自己養活。

Sophomore in Information Management at Yuan Ze University, Taiwan. I build tools and automation that cost nothing to run, so I can support myself.

關於我About

我是 Sean,元智大學資訊管理學系大二,預計 2029 年畢業,住在桃園、學校附近。持有 Anthropic Claude 101 認證(2026 年 7 月)。校內參加閱人社和資管系排球隊。

I'm Sean, a second-year Information Management student at Yuan Ze University (元智大學) in Taiwan, graduating in 2029. I live in Taoyuan, near campus. I hold Anthropic's Claude 101 certification (July 2026). On campus I'm in the 閱人社 club and the IM department volleyball team.

正在做的事What I'm working on

目標很直接:在家裡還支持我的這幾年,先做到經濟上自給自足。

The goal is plain: become financially self-sufficient while my family is still supporting me.

技術背景Technical background

我做東西的原則How I build

  1. 全部 $0。免費層、本地模型、瀏覽器端運算。
  2. Everything runs on $0.Free tiers, local models, browser-side compute.
  3. 單檔、無依賴的前端。打開就能用,不需要 build。這個網站就是一個 HTML 檔。
  4. Single-file, dependency-free front ends.Open it and it works. No build step. This site is one HTML file.
  5. 自己不用的工具,不算做完。我只信自己感受過的需求。我曾以為可以先做出來再找需求,後來發現太多東西只有我自己會用。現在只做我真的缺、缺了會去解決的東西。
  6. A tool I don't use myself isn't finished.I only trust demand I've felt. I used to think you could ship first and find demand later; too much of what I built turned out to be useful only to me. Now I build what I actually lack and would otherwise fix by hand.
  7. 有後果的自動化,一定有人工閘門。產生可以自動;發布、付款、寫入都要人點頭。
  8. Consequential automation always has a human gate.Generation can be automatic. Posting, paying, and writing to anything that matters needs a human to say yes.
  9. 最小權限,不硬編碼憑證,程式碼要能被審。
  10. Least privilege, no hardcoded credentials, code that can be audited.

作品Projects

考場筆記 · Personal IELTS Desk Cloudflare Pages · Gemini · Web Speech

繁中 IELTS 自學系統——單字庫、Leitner 五盒複習、AI 模擬題、錯題本、寫作評分、每日規劃。

A Traditional-Chinese IELTS study desk — vocabulary bank, Leitner review, AI mock questions, mistake notebook, band-descriptor marking, daily planner.

問題
市面 IELTS 工具要付費、要帳號、資料不在自己手上。
Problem
Existing IELTS tools cost money, require an account, and keep your data.
解法
全部跑在瀏覽器。API key 存 localStorage,資料可匯出 JSON,雲端同步是選配。
Approach
Everything runs in the browser. The API key lives in localStorage, data exports as JSON, cloud sync is optional.
取捨
瀏覽器端呼叫 Gemini 而不是自架後端——零伺服器成本,代價是使用者要自己申請 key。Leitner 而不是 SM-2——簡單到使用者看得懂自己在哪一盒。
Trade-offs
Calling Gemini client-side instead of running a backend — zero server cost, at the price of users bringing their own key. Leitner instead of SM-2 — simple enough that you can see which box you're in.
學到
動態模型探索比寫死模型名稱耐用;給 Claude Code 的交接包讓後續迭代成本大幅下降。
Learned
Dynamic model discovery outlasts hardcoded model names. A handoff package for Claude Code made later iterations far cheaper.
vid-for-agents Shell · ffmpeg · whisper.cpp

一行指令把任何影片變成取樣畫格 + 本地逐字稿,讓 AI coding agent 能「看」影片。

One command turns any video into sampled frames plus a local transcript, so AI coding agents can read it.

問題
Agent 只能讀文字。影片教學、螢幕錄影對它們是黑盒。
Problem
Agents read text. Video tutorials and screen recordings are a black box to them.
解法
把影片降維成 agent 讀得懂的兩種東西:畫格和文字。
Approach
Reduce the video to the two things an agent can read: frames and text.
取捨
本地 whisper.cpp 而不是雲端語音辨識——慢一點,但不用 key、不上傳、$0。
Trade-offs
Local whisper.cpp instead of cloud speech-to-text — slower, but no key, no upload, $0.
CountAgent Claude Code · iOS Shortcuts

跑在 Claude Code 上的個人記帳 agent。Siri 往檔案追加一行純文字,agent 之後負責解析、分類、去重。

A personal bookkeeping agent on Claude Code. Siri appends one line of plain text; the agent later parses, categorises and dedupes.

問題
記帳 app 的摩擦在輸入。開 app、選類別、填金額,三步就放棄。
Problem
The friction in expense apps is input. Open the app, pick a category, type the amount — three steps and you quit.
解法
輸入端只剩一句話,理解交給 agent 批次處理。
Approach
Input shrinks to one sentence. Understanding is handed to the agent in batches.
取捨
行為寫成自然語言 CLAUDE.md 而不是程式碼——改規則不用改 code,代價是行為不完全確定,所以保留人工審核。
Trade-offs
Behaviour is written as a natural-language CLAUDE.md, not code — rules change without a code change, at the price of non-determinism, so a human review step stays.

這個月This month

2026 年 9 月

September 2026

工作之外Outside work

哲學和知識論。在乎遊戲和電影的敘事品質。理想的一天裡有我的貓。

Philosophy and epistemology. Narrative quality in games and film. My cat is part of the ideal day.

聯絡Contact

合作、專案、或只是想聊聊——直接寫信。

Collaborations, projects, or just a conversation — email works.