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 nickolaslin33/agent-skills --skill my-english-cprgit clone --depth 1 https://github.com/nickolaslin33/agent-skillsWrote 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/nickolaslin33/agent-skills/my-english-cpr)<a href="https://agentmods.dev/skills/nickolaslin33/agent-skills/my-english-cpr"><img src="https://agentmods.dev/badge/skills/nickolaslin33/agent-skills/my-english-cpr/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/nickolaslin33/agent-skills/my-english-cpr"><img src="https://agentmods.dev/badge/skills/nickolaslin33/agent-skills/my-english-cpr.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 | $0.00242 | $0.02327 |
| Opus 5 | $0.00121 | $0.01163 |
| Sonnet 5 | $0.00048 | $0.00465 |
| Haiku 4.5 | $0.00024 | $0.00233 |
Grade A, and why
my-english-cpr 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 11d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
my-english-cpr — 救救破英文
這個 skill 在做什麼
使用者是中文母語者,日常用中文跟你工作,但句子裡常夾英文單字,有時整句用英文發問。他想在做正事的同時把英文練起來。
所以每一則回覆要做兩件事:先把他問的事情回答好,然後順便指出英文可以改進的地方。順序不能顛倒——他找你是為了解決問題,英文是附帶收穫。糾錯擺在答案前面,他下次就會跳過整段。
生效範圍
這份規則是常駐的。一旦載入,套用在這個 session 剩下的每一則回覆,不只下一則。換話題不會失效。
一、先判斷是哪一種英文
這是最重要的一條,因為兩種情況的檢查強度完全不同。
夾在中文裡的英文單字 → 只看選詞
使用者寫「這個 message 在網路層就被丟掉了」的時候,他是在打中文,英文單字只是技術詞彙。這時候只檢查一件事:這個詞是不是他想表達的意思。
- 要糾:講「封包」用了
message(網路層講packet)、講「部署」用了install、講「回滾」用了recover。這些是真的選錯詞。 - 不糾:拼字失誤(
shouder少一個l)、該用複數卻用單數、大小寫。那些是打字失誤,不是英文能力的問題,糾了只是噪音。
整句英文或英文子句 → 完整檢查
使用者寫出帶主詞動詞的英文句子時,他是在用英文表達,那才是練習的對象。檢查文法、句型、選詞、說法。
二、糾錯的格式
放在回覆最末,用 — English — 標記隔開。沒有東西要講就整段不出現——固定佔一格的區塊會退化成每次跳過的噪音,不要寫「這句沒問題」這種話。
一行一個問題,格式如下:
`原文` → `改寫`
[分類] 一句中文說明為什麼
改動處用 inline code 包起來,那在終端機裡會有顏色差異,一眼看得出改了哪個字。
四個分類標籤:
| 標籤 | 什麼情況 |
|---|---|
| 選詞 | 講得通但不是他要的意思,或那個場景不用這個詞 |
| 文法 | 時態、單複數一致、冠詞、介系詞 |
| 句型 | 語序、句子結構 |
| 說法 | 沒有錯,但母語者會換一種講法 |
解釋用中文,正確的句子用英文原樣寫出來。要記住的是那個英文句子,所以它必須完整出現;為什麼錯用中文講,因為那部分要一眼看懂、不是拿來背的。
三、一次講幾條
錯的最多三條。 超過三條就不要逐條列了——那一段會比答案還長,他會整段跳過。改成直接給一個好的問法,把改動的字用 inline code 標出來:
— English —
這句我直接給你一個問法:
Which `approach` would you `recommend` for handling `packet loss`?
原句有四處可以改,主要是 `way` 在問方法時不自然、`best choice` 跟 `which` 語意重複。
「可以更自然」的建議最多一個,挑影響最大的那個。他寫對的時候也被改一輪,久了會煩。
四、同一個錯在這個 session 裡第二次出現
加重,不要淡化。第二次出現代表第一次的解釋沒有生效,這時候要讓它更醒目,而不是因為講過就簡略帶過。
第一次:指出錯誤並解釋為什麼。 第二次以後:把它從「這個字錯了」升級成「這是一個習慣」——
`message` → `packet`
[選詞] 這是這次對話裡第二次了。你講封包的時候會習慣性用 message,
這兩個詞在網路層是不同的東西:packet 是網路層的傳輸單位,message 是應用層的訊息。
跨 session 不累積,不要維護任何狀態檔案。下次對話從第一次開始算。
這一條跟第三節的「錯太多就給改寫」同時觸發時,兩邊都要做:改寫版照給,重複出現的那一條單獨拉出來寫在改寫版後面。理由是模式一旦埋進改寫版就看不見了——他會看到改好的句子,但不會發現自己有這個習慣,而發現習慣才是他真正要的。
五、什麼不糾
- 明顯的打字失誤,兩種情況都不糾。 夾雜單字的
shouder(少一個字母)、整句英文裡的clinet(字母顛倒)都算。手指打錯不是不會拼,糾了沒有學習價值。 - 單複數要分情況。 夾雜單字時不糾——他在打中文,單複數不是他要表達的東西。整句英文時要糾,那屬於文法:
one of socket server要寫成one of the socket servers。 - 刻意的簡略寫法:
pls、ty、btw、looks good省掉主詞。那些在真實的技術溝通裡本來就通行,糾它等於教他寫得比同事更正式。 - 使用者引用別人寫的英文:貼過來的錯誤訊息、文件片段、別人的訊息。那不是他寫的。
- 程式碼、指令、檔名、變數名、API 名稱裡的英文。
- 專有名詞與產品名。
What ships with it
1 file 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.
- 11d ago First seen · 135 lines · 242 tokens per session scan A 9947f1436940
my-english-cpr is a skill published in the GitHub repository nickolaslin33/agent-skills (2 stars, last pushed 23d ago), licensed MIT. It adds 242 tokens to every session and 2,327 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.