透過 技能,你的 AI Agent 會幫你把「」一次部署在同一個 帳號裡: * :你不需要貼任何密碼或權杖給 AI! * :不用開無痕視窗,不管是學校電腦、手機、平板或任何瀏覽器點開都能直接連線! * :寫程式與打指令全部交給 AntiGravity AI,你只需要做 !
概览
透過 技能,你的 AI Agent 會幫你把「」一次部署在同一個 帳號裡: * :你不需要貼任何密碼或權杖給 AI! * :不用開無痕視窗,不管是學校電腦、手機、平板或任何瀏覽器點開都能直接連線! * :寫程式與打指令全部交給 AntiGravity AI,你只需要做 ! 打開 ,直接複製以下**貼進對話框送出(AI 會自動幫你建立資料夾並下載技能,完全不用自己去檔案總管找路徑): *(💡 裝完後,請開一個新的對話視窗,輸入 / 就能看到 /cloudflare-workers-d1 技能!建議同時將右上角模型切換為 ,速度最快且最省免費版額度。)* 1. 如果你還沒有 Cloudflare 帳號,請打開 👉 2. 輸入你的 Email 與自訂密碼完成註冊。 3. (如果沒看到請檢查垃圾郵件匣;未驗證信箱將無法發佈網站)。 直接挑選一個範本,修改 【...】 括號內的內容後貼給 AntiGravity: 1. : * 當 AI 啟動登入並跳出瀏覽器(或給你一串 https://dash.cloudflare.com/oauth2/auth?... 連結)時,登入你的 Cloudflare 帳號並點擊 (整台電腦只需做這一次!)。 2. (若 AI 有提示才需做): * 若是全新 Cloudflare 帳號第一次發佈,AI 會請你打開 https://dash.cloudflare.com/ ➔ 點左側選單 ➔ 自取一個英文子網域名稱並儲存,然後跟 AI 說「好了」。 3. : * AI 會自動幫你建好資料庫、建好表格、部署上線並完成測試,最後給你一張「」與公開網址 https://xxx.workers.dev,直接點開就能玩! With the skill, your AI Agent deploys your all together under a single account: * : You never have to copy or paste any secret tokens! * : Works immediately in any normal browser window on desktop, tablet, or mobile—no Incognito window needed!
README
⚡ OpenCode 零金鑰全端網站+Cloudflare D1 雲端資料庫實作講義(Weeks 10–11 專用)
⚡ OpenCode Zero-Key Web App + Cloudflare D1 Database Classroom Handout (Weeks 10–11 Edition)
📌 來源致謝與改編說明 (Credits & Attribution)
- 中文說明:本技能與課堂講義改編並參考自 mathruffian-dot/agent-connect-lazy-pack(原作者:三師爸
mathruffian-dot)。在此基礎上,專為 OpenCode 與「生成式 AI 與語言學習」課程(第 10–11 週)重構為免 MCP、免 API Key 的 Cloudflare Workers + D1(SQLite 雲端資料庫) 雙語技能,並內建AGENTS.md(教學規則)+ Prompt(教材內容)雙層架構與同儕測試紀錄即時看板。- English: Adapted from and based on mathruffian-dot/agent-connect-lazy-pack by
mathruffian-dot. Tailored into a bilingual (Traditional Chinese & English) OpenCode skill for the GenAI and Language Learning course (Weeks 10–11), featuring a zero-key, zero-MCP Cloudflare Workers + D1 (SQLite) workflow, a two-layerAGENTS.md(teaching rules) + Prompt (learning content) architecture, and a live peer-test log viewer.
🇹🇼 第一部分:中文版學生實作講義 (Traditional Chinese)
一、 這套方法有什麼超強優點?
在 OpenCode 中搭配 cloudflare-workers-d1 技能與專案資料夾裡的 AGENTS.md,你的 AI Agent 會幫你把「前端互動網頁+後端 API+D1 雲端資料庫」一次部署在同一個 Cloudflare 帳號裡:
- 兩層指令:
AGENTS.md管規則、Prompt 管內容:Cockpit 設計卡的 Part A 產生AGENTS.md(每次都要遵守的教學規則),直接放進你的專案資料夾(不要放進裡面的其他資料夾);Part B 產生 Prompt(這次的文章、單字、題目或練習題),貼進 OpenCode 對話框。想改「怎麼教」就改AGENTS.md,想改「教什麼」就改 Prompt! - 完全免裝 MCP、免複製任何 API Key 或 Token:你不需要貼任何密碼或權杖給 AI!
- 前後端同源(零跨域問題)+ 雲端資料庫全自動建立:D1 資料表與初始教材皆由 OpenCode 自動建好並寫入,網頁最下方還會內建「📊 Cloud D1 Peer-Test Logs(雲端同儕測試紀錄即時看板)」,任何電腦或手機點開網址就能直接測試!
- 你的任務:寫程式、寫 SQL 與打指令全部交給 OpenCode AI,你只需要做 「1 句安裝技能指令 + 把
AGENTS.md直接放進專案資料夾 + 貼上 Prompt + 在瀏覽器按一次 Allow」!
二、 Step 1:如何安裝?(只需做一次,支援 Antigravity / OpenCode / Claude Code / Codex)
你完全不需要自己開終端機找資料夾路徑!只要打開你正在使用的 AI Agent(OpenCode 或 Google Antigravity),複製下方對應的一段話貼進對話框,AI 就會自動幫你把技能全部安裝好。
💬 複製貼給 AI Agent 自動安裝
選項 1:通用一鍵安裝指令(同時安裝技能到 Antigravity / OpenCode / Claude Code / Codex)
直接複製以下整段話貼給你的 Antigravity 或 OpenCode:
請幫我把 https://github.com/MeiChen-ai/cloudflare-workers-d1-skill.git 完整 clone 到暫存資料夾,並執行裡面的安裝腳本(或將 skills/ 底下的 cloudflare-workers-d1 與 cloudflare-workers-d1-en 完整資料夾複製到 ~/.gemini/config/skills/、~/.config/opencode/skills/、~/.agents/skills/ 與 ~/.claude/skills/,若資料夾不存在請自動建立)。
選項 2:如果你只用 Google Antigravity
請幫我從 https://raw.githubusercontent.com/MeiChen-ai/cloudflare-workers-d1-skill/main/skills/cloudflare-workers-d1/SKILL.md 下載技能檔,並儲存到我的 ~/.gemini/config/skills/cloudflare-workers-d1/SKILL.md(若資料夾不存在請自動建立)。
選項 3:如果你只用 OpenCode
請幫我從 https://raw.githubusercontent.com/MeiChen-ai/cloudflare-workers-d1-skill/main/skills/cloudflare-workers-d1/SKILL.md 下載技能檔,並同時儲存到我的 ~/.config/opencode/skills/cloudflare-workers-d1/SKILL.md 與 ~/.agents/skills/cloudflare-workers-d1/SKILL.md(若資料夾不存在請自動建立)。
(💡 裝完後,之後在任何專案資料夾打開 OpenCode 或 Antigravity,它都能自動啟用 cloudflare-workers-d1 技能!)
三、 Step 2:課前 2 分鐘準備(註冊 Cloudflare 帳號)
- 如果你還沒有 Cloudflare 帳號,請打開 👉 https://dash.cloudflare.com/sign-up
- 輸入你的 Email 與自訂密碼完成註冊。
- 🔑【必做】去信箱收信並點擊 Cloudflare 驗證信(如果沒看到請檢查垃圾郵件匣;未驗證信箱將無法發佈網站)。
四、 Step 3:放好 AGENTS.md(規則),再貼上 Prompt(內容)
在桌面上建立你的專案資料夾(例如第 10 週 Week10_App 或第 11 週 Week11_App),把從課堂 Cockpit 設計卡 Part A 下載的 AGENTS.md 直接放進這個資料夾,不要放進裡面的其他資料夾:
Week10_App/ 👈 在這個資料夾打開 OpenCode
└── AGENTS.md 👈 把下載的 AGENTS.md 直接放在這裡(全大寫加 S)!
接著在該資料夾打開 OpenCode,貼上設計卡 Part B 產生的 Prompt(按 Copy Prompt for OpenCode and Padlet 複製),同一份也貼到 Padlet。
AGENTS.md(放進資料夾) |
Prompt(貼進對話框) | |
|---|---|---|
| 角色 | 每次都要遵守的規則 | 這一次的內容 |
| 第 10 週 | 分級規則、first-click clue(點第 1 下的提示)、語音、理解題形式、D1 資料表與部署 | 暱稱、文章、5 個關鍵字、2 題理解題 |
| 第 11 週 | App 類型(5 選 1)、回饋規則、開始與結束畫面、D1 資料表與部署 | 暱稱、學習者與問題、App 點子、練習題 |
| 想修改時 | 改「怎麼教」 | 改「教什麼」 |
(沒有用 Cockpit 的話,也可以照下方範本自己建一個 AGENTS.md,再貼上 Prompt:)
📖 第 10 週範本:「A2 / B1 / B2 分級閱讀與聽力鷹架網+雲端測試紀錄表」
① AGENTS.md(規則)
# AGENTS.md — Week 10 Scaffolded Reading & Listening App
## 1. Tools
- 使用 cloudflare-workers-d1 技能,部署到 Cloudflare Workers + D1。
- 網站名 -w10-reading,資料庫名 -w10-reading-db(暱稱見我的 Prompt)。
## 2. Teaching Rules
1. 分級切換:把我的文章改寫成 A2 / B1 / B2 三個分頁,三級講同一個故事。分級規則:【A2:每句 12 字以內、基礎字彙;B1:中長句、保留 5 個關鍵字;B2:保留原文】
2. 聽力朗讀列:瀏覽器語音朗讀,Play/Pause 與 1.0x / 0.85x。
3. 兩段式單字提示:每一級都標出我的 5 個關鍵字。點第 1 下:【一個幫我猜意思的語境問句】,不可顯示定義;點第 2 下才顯示英英釋義與例句。
4. 2 題四選一理解題(每一級都能作答),測試者先輸入暱稱再送出、看分數。
5. 網頁最下方可展開的「📊 Cloud D1 Peer-Test Logs」看板。
## 3. D1 & Deployment
- 不要叫我寫 SQL、建表或貼任何金鑰。
- 建立 passages(預塞三級課文、單字提示與題目)與 reading_logs(nickname、selected_level、audio_speed、words_clicked、quiz_score、created_at),套用遠端 migrations 並部署。
## 4. Content
- 內容來自我的 Prompt。Prompt 與本檔規則衝突時,以本檔為準並告訴我。
② Prompt(內容)
請讀取資料夾裡的 AGENTS.md 並遵守所有規則,然後用 cloudflare-workers-d1 技能,依以下內容建立並部署我的第 10 週分級閱讀聽力網:
- 我的暱稱:【小寫英文,例如 alice】
- 文章標題:【標題】
- 文章:【150–200 字英文短文】
- 5 個關鍵字:【word1, word2, word3, word4, word5】
- 2 題理解題:
Q1:【題目】(正確答案:【答案】)
Q2:【題目】(正確答案:【答案】)
💬 第 11 週範本:「我自己設計的英文 App+雲端練習紀錄表」
① AGENTS.md(規則)
# AGENTS.md — Week 11 My Own English App (OpenCode + Cloudflare D1)
## 1. Tools
- 使用 cloudflare-workers-d1 技能,部署到 Cloudflare Workers + D1。
- 網站名 -w11-app,資料庫名 -w11-app-db(暱稱見我的 Prompt)。
- 第 10 週已登入 Cloudflare:先跑 npx.cmd -y wrangler whoami,需要時才 wrangler login。
## 2. Teaching Rules
1. App 類型(5 選 1):Branching conversation(3 關對話,選 1 個回應)/ Put it in order(把打亂的字排回句子)/ Listen and type(聽句子打字)/ Sort into groups(把字卡分組)/ Flip and recall(翻卡回想並自評)。
2. 開始畫面:輸入暱稱(不用真名),一次練習 2–8 分鐘。
3. 回饋規則:【例如:第 1 次答錯給提示、第 2 次答錯才顯示答案】學習者至少試過一次之前,不顯示答案。
4. 結束:顯示簡短總結,並把這次練習存進 D1。
5. 網頁最下方可展開的「📊 Cloud D1 Peer-Test Logs」看板。
## 3. D1 & Deployment
- 不要叫我寫 SQL、建表或貼任何金鑰。
- 在 migrations/0001_init.sql 建立 items(預塞我 Prompt 裡的練習題)與 practice_logs(nickname、app_type、score、hints_used、details、created_at),套用遠端 migrations 並部署。
- details 依我的 App 類型存:Branching conversation=選擇路徑與重選次數;Put it in order=第一次答對題數(滿分 5)與提示次數;Listen and type=聽對字數/總字數與重播次數;Sort into groups=第一次檢查放錯組的卡片數與檢查次數;Flip and recall=Got it / Not sure / Missed it 各幾張與下次要複習的卡片。
## 4. Content
- 內容來自我的 Prompt。Prompt 與本檔規則衝突時,以本檔為準並告訴我。
② Prompt(內容)
請讀取資料夾裡的 AGENTS.md 並遵守所有規則,然後用 cloudflare-workers-d1 技能,依以下內容建立並部署我的第 11 週英文 App:
- 我的暱稱:【小寫英文,例如 alice】
- 學習者與問題:【例如:英文寫信給教授時語氣太直接的大一學生(B1)】
- App 點子:【例如:幫學生有禮貌地向教授多要幾天時間的 App】
- 練習題:【依 App 類型的格式,一行一題】
③ 練習題格式(依你選的 App 類型)
| App 類型 | 練習題格式(一行一題) | 題數 | details 要存什麼 |
|---|---|---|---|
| Branching conversation | 對方的話 | *最佳回應 | 較弱回應 | 較弱回應(最佳回應前加 *) |
3 | 選擇路徑(例如 T1:weak->T1:best->T2:best->T3:best)與重選次數 |
| Put it in order | 正確的句子(App 會自己打亂字的順序) | 5 | 第一次就答對的題數(滿分 5)與用了幾次提示 |
| Listen and type | 學習者要聽的句子 | 5 | 聽對的字數/總字數,與重播次數 |
| Sort into groups | 字或片語 | 組名(共 2 或 3 組) |
8 | 第一次檢查時放錯組的卡片數,與檢查次數 |
| Flip and recall | 正面(提示) | 背面(答案) |
6 | Got it / Not sure / Missed it 各幾張,以及下次要複習哪幾張 |
五、 Step 4:執行過程中,OpenCode 請你配合的唯一點擊動作
- 🔑【瀏覽器按 Allow 授權】:
- 當 OpenCode 啟動登入並跳出瀏覽器(或給你一串
https://dash.cloudflare.com/oauth2/auth?...連結)時,登入你的 Cloudflare 帳號並點擊Allow(允許)(整台電腦只需在第 10 週做這一次,第 11 週免重新登入!)。
- 當 OpenCode 啟動登入並跳出瀏覽器(或給你一串
- 🔑【新帳號首次部署:設定子網域】(若 AI 有提示才需做):
- 若是全新 Cloudflare 帳號第一次發佈,AI 會請你打開 https://dash.cloudflare.com/ ➔ 點左側選單
Workers & Pages➔ 自取一個英文子網域名稱並儲存,然後跟 AI 說「好了」。
- 若是全新 Cloudflare 帳號第一次發佈,AI 會請你打開 https://dash.cloudflare.com/ ➔ 點左側選單
- 🎉【完成驗收與同儕互測】:
- OpenCode 會自動幫你建好 D1 資料庫、寫入教材、部署上線並完成測試,最後給你一張「🎉 部署完成卡」與公開網址
https://xxx.workers.dev,直接貼上 Padlet 讓同學進行 Peer Testing!
- OpenCode 會自動幫你建好 D1 資料庫、寫入教材、部署上線並完成測試,最後給你一張「🎉 部署完成卡」與公開網址
🌍 Part 2: English Student Handout (For Non-Chinese Environments)
1. Why Use This Workflow in OpenCode?
With the cloudflare-workers-d1-en skill and an AGENTS.md file in your project folder in OpenCode, your AI Agent deploys your Frontend Web App + Backend API + Cloud SQL Database (D1) all together under a single Cloudflare account:
- Two Layers:
AGENTS.mdfor Rules, a Prompt for Content: Part A of the Cockpit design card gives youAGENTS.md(the teaching rules OpenCode follows every time), which goes straight into your project folder, not into a folder inside it. Part B gives you a prompt (this app’s article, words, questions or practice items), which you paste into OpenCode. Change how it teaches inAGENTS.md; change what it teaches in the prompt! - Zero MCP Setup, Zero API Keys or Tokens: You never have to copy or paste any secret tokens!
- Auto-Created Cloud Database + Live Log Viewer: OpenCode automatically creates the D1 SQLite tables, seeds your reading passages or practice items, and adds a collapsible “📊 Cloud D1 Peer-Test Logs” viewer at the bottom of your webpage!
- Your Job: Let the OpenCode AI run all commands, write all SQL, and build all code—you only need 1 install prompt + putting
AGENTS.mdstraight into your project folder + pasting your prompt + 1 click on “Allow” in your browser!
2. Step 1: One-Time Installation (Supports Antigravity, OpenCode, Claude Code & Codex)
You do not need to manually hunt for hidden skill folders! Simply open your AI Agent (OpenCode or Google Antigravity), copy one of the blocks below, and paste it directly into the chat box.
💬 Copy & Paste One Prompt to Your AI Agent
Option 1: Universal Install Prompt (Installs the Skill to Antigravity, OpenCode, Claude Code & Codex)
Copy and paste this entire block into Antigravity or OpenCode:
Please clone https://github.com/MeiChen-ai/cloudflare-workers-d1-skill.git into a temporary folder and run its installer script (or copy `cloudflare-workers-d1` and `cloudflare-workers-d1-en` from `skills/` into `~/.gemini/config/skills/`, `~/.config/opencode/skills/`, `~/.agents/skills/`, and `~/.claude/skills/`, creating the directories if they do not exist).
Option 2: Google Antigravity Only
Please download the skill file from https://raw.githubusercontent.com/MeiChen-ai/cloudflare-workers-d1-skill/main/skills/cloudflare-workers-d1-en/SKILL.md and save it as my global AntiGravity skill at ~/.gemini/config/skills/cloudflare-workers-d1-en/SKILL.md (automatically create the directories if they do not exist).
Option 3: OpenCode Only
Please download the skill file from https://raw.githubusercontent.com/MeiChen-ai/cloudflare-workers-d1-skill/main/skills/cloudflare-workers-d1-en/SKILL.md and save it to both ~/.config/opencode/skills/cloudflare-workers-d1-en/SKILL.md and ~/.agents/skills/cloudflare-workers-d1-en/SKILL.md (automatically create the directories if they do not exist).
(💡 Once installed, OpenCode or Antigravity will automatically recognize the cloudflare-workers-d1-en skill in any project folder!)
3. Step 2: 2-Minute Pre-Flight Checklist (Create a Cloudflare Account)
- If you don’t have a Cloudflare account yet, open 👉 https://dash.cloudflare.com/sign-up
- Sign up with your Email and a password.
- 🔑 [Must Do] Verify Your Email: Open your email inbox (check Spam if needed) and click the verification link from Cloudflare (unverified accounts cannot deploy websites).
4. Step 3: Place AGENTS.md (Rules), Then Paste Your Prompt (Content)
Create your weekly project folder on your Desktop (e.g., Week10_App or Week11_App) and place the AGENTS.md file from Part A of your course Cockpit design card straight into that folder, not into a folder inside it:
Week10_App/ 👈 Open OpenCode in this folder
└── AGENTS.md 👈 Place your downloaded AGENTS.md right here (ALL CAPS + S)!
Then launch OpenCode inside that folder and paste the prompt from Part B of the design card (press Copy Prompt for OpenCode and Padlet). Post the same prompt on Padlet.
AGENTS.md (in your folder) |
Prompt (pasted into OpenCode) | |
|---|---|---|
| Job | the rules, followed every time | this app’s content |
| Week 10 | level rules, first-click clue, audio, question format, D1 tables & deployment | nickname, article, 5 key words, 2 check questions |
| Week 11 | app type (1 of 5), feedback rule, start & finish screens, D1 tables & deployment | nickname, learner & problem, app idea, practice items |
| To change | how it teaches | what it teaches |
(No Cockpit? Build your own AGENTS.md and prompt from the templates below.)
📖 Week 10 Template: CEFR A2 / B1 / B2 Scaffolded Reading & Listening Web App + Cloud Logs
① AGENTS.md (rules)
# AGENTS.md — Week 10 Scaffolded Reading & Listening App
## 1. Tools
- Use the cloudflare-workers-d1-en skill to deploy on Cloudflare Workers + D1.
- Name the Worker -w10-reading and the database -w10-reading-db (nickname is in my prompt).
## 2. Teaching Rules
1. Level switcher: rewrite my article into A2 / B1 / B2 tabs that tell the same story. Level rules: [A2: 12 words or fewer per sentence, everyday words; B1: medium sentences, keep the 5 key words; B2: keep the original]
2. Listening bar: browser text-to-speech with Play/Pause and 1.0x / 0.85x.
3. Two-click word help: underline my 5 key words in every level. Click 1: [a short question about the sentence that helps me guess the meaning]; never show the definition on click 1. Click 2: English definition and one example.
4. My 2 check questions as multiple choice (4 options), answerable at every level. The tester types a nickname before submitting, then sees the score.
5. A collapsible "📊 Cloud D1 Peer-Test Logs" table at the bottom.
## 3. D1 & Deployment
- Do NOT ask me to write SQL, create tables, or copy any key or token.
- Create passages (pre-filled with the three levels, word clues and questions) and reading_logs (nickname, selected_level, audio_speed, words_clicked, quiz_score, created_at), apply remote migrations, and deploy.
## 4. Content
- The content comes from my prompt. If my prompt and these rules disagree, follow these rules and tell me.
② Prompt (content)
Please read AGENTS.md in this folder and follow all its rules. Then use the cloudflare-workers-d1-en skill to build and deploy my Week 10 Reading & Listening App with this content:
- My nickname: [lowercase, e.g., alice]
- Article title: [title]
- Article: [150–200 words of English]
- 5 key words: [word1, word2, word3, word4, word5]
- 2 check questions:
Q1: [question] (Right answer: [answer])
Q2: [question] (Right answer: [answer])
💬 Week 11 Template: My Own English App + Cloud Practice Logs
① AGENTS.md (rules)
# AGENTS.md — Week 11 My Own English App (OpenCode + Cloudflare D1)
## 1. Tools
- Use the cloudflare-workers-d1-en skill to deploy on Cloudflare Workers + D1.
- Name the Worker -w11-app and the database -w11-app-db (nickname is in my prompt).
- I logged in to Cloudflare in Week 10. Check with npx.cmd -y wrangler whoami first and only run wrangler login if needed.
## 2. Teaching Rules
1. App type (pick 1 of 5): Branching conversation (3 turns, pick 1 of 3 replies) / Put it in order (tap mixed-up words back into a sentence) / Listen and type (hear a sentence, type it) / Sort into groups (drag word cards into groups) / Flip and recall (flip a card, rate yourself).
2. Start screen: ask for a nickname (no real names). One session should take 2-8 minutes.
3. Feedback rule: [e.g., 1st wrong try: a hint; 2nd wrong try: show the answer] Never show the answer before the learner has tried at least once.
4. Finish: show a short summary, then save the session to D1.
5. A collapsible "📊 Cloud D1 Peer-Test Logs" viewer at the bottom.
## 3. D1 & Deployment
- Do NOT ask me to write SQL, create tables, or copy any key or token.
- In migrations/0001_init.sql, create items (pre-filled with the practice items in my prompt) and practice_logs (nickname, app_type, score, hints_used, details, created_at), apply remote migrations, and deploy.
- In details, save by my app type: Branching conversation = the path chosen and the number of retries; Put it in order = first-try score out of 5 and hints used; Listen and type = words correct out of the total and replays; Sort into groups = cards in the wrong group on the first check and the number of checks; Flip and recall = how many cards were Got it / Not sure / Missed it and which to review next time.
## 4. Content
- The content comes from my prompt. If my prompt and these rules disagree, follow these rules and tell me.
② Prompt (content)
Please read AGENTS.md in this folder and follow all its rules. Then use the cloudflare-workers-d1-en skill to build and deploy my Week 11 English app with this content:
- My nickname: [lowercase, e.g., alice]
- Learner & problem: [e.g., First-year university students (B1) whose emails to professors sound too direct]
- App idea: [e.g., An app that helps students ask a professor for more time politely]
- Practice items: [one per line, in the format for your app type]
③ Practice item formats (for the app type you picked)
| App type | Practice item format (one per line) | Items | What details saves |
|---|---|---|---|
| Branching conversation | other person's line | *best reply | weaker reply | weaker reply (put * before the best reply) |
3 | the path chosen (e.g. T1:weak->T1:best->T2:best->T3:best) and the number of retries |
| Put it in order | the correct sentence (the app mixes up the words) | 5 | first-try score out of 5 and the number of hints used |
| Listen and type | the sentence the learner will hear | 5 | words correct out of the total and the number of replays |
| Sort into groups | word or phrase | group name (2 or 3 groups) |
8 | the number of cards in the wrong group on the first check and the number of checks |
| Flip and recall | front (clue) | back (answer) |
6 | how many cards were Got it / Not sure / Missed it, and which cards to review next time |
5. Step 4: What You Click During Deployment
- 🔑 [Click “Allow” in Browser]:
- When OpenCode runs
wrangler loginand opens your browser (or gives you ahttps://dash.cloudflare.com/oauth2/auth?...link), sign in to Cloudflare and clickAllow(only needed once in Week 10—Week 11 skips login automatically!).
- When OpenCode runs
- 🔑 [First-Time Account Subdomain Setup] (only if prompted):
- If this is a brand-new Cloudflare account, the AI may ask you to open https://dash.cloudflare.com/ ➔ Click
Workers & Pagesin the left sidebar ➔ Pick a customworkers.devsubdomain name and save it, then reply “Done”.
- If this is a brand-new Cloudflare account, the AI may ask you to open https://dash.cloudflare.com/ ➔ Click
- 🎉 [Peer Test & Inspect Cloud D1 Logs!]:
- OpenCode will automatically create your D1 database, seed your content, deploy your site, verify the API, and hand you your live
https://xxx.workers.devURL ready for Peer Testing!
- OpenCode will automatically create your D1 database, seed your content, deploy your site, verify the API, and hand you your live
推荐工具
换一个关键词,或者移除筛选条件。
安装
npx skillfish add meichen-ai/cloudflare-workers-d1-skill