@thuanphan2208/paper-pilot 1.0.0 → 1.0.2

package/.claude/skills/paper-review/SKILL.md

@@ -11,7 +11,7 @@ You are a paper reviewer giving constructive feedback to a first-time student re
 
 **This skill works on any section.** The user invokes it as `/paper:review <section>` (e.g., `/paper:review intro`).
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 

package/.claude/skills/paper-teach-abstract/SKILL.md

@@ -11,7 +11,7 @@ You are teaching a first-time student researcher how to write the **Abstract**.
 
 **Teaching mode only** — recommend `/paper:write abstract` at the end.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 

package/.claude/skills/paper-teach-conclusion/SKILL.md

@@ -11,7 +11,7 @@ You are teaching a first-time student researcher how to write the **Conclusion**
 
 **Teaching mode only** — recommend `/paper:write conclusion` at the end.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 

package/.claude/skills/paper-teach-experiment/SKILL.md

@@ -11,7 +11,7 @@ You are teaching a first-time student researcher how to write the **Experiments*
 
 **Teaching mode only** — recommend `/paper:write experiment` at the end.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 

package/.claude/skills/paper-teach-intro/SKILL.md

@@ -11,7 +11,7 @@ You are teaching a first-time student researcher how to write the **Introduction
 
 **Teaching mode only** — do NOT write their Introduction here. When done, recommend `/paper:write intro`.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 
@@ -24,7 +24,7 @@ Read `paper/context.yaml` if it exists. Use the user's topic, field, and paper_t
 ## Structure to Teach
 
 ```
-INTRODUCTION = 4 BLOCKS
+INTRODUCTION = 5 BLOCKS
 ══════════════════════════════════════════════════════════
 
   Block 1: BACKGROUND / HOOK          (~1–2 paragraphs)
@@ -34,14 +34,22 @@ INTRODUCTION = 4 BLOCKS
   └─────────────────────────────────────────────────┘
            │
            ▼
-  Block 2: PROBLEM STATEMENT          (~1 paragraph)
+  Block 2: PROBLEM STATEMENT + GAP    (~1 paragraph)
   ┌─────────────────────────────────────────────────┐
   │ What exactly is the problem?                    │
   │ Why are current approaches insufficient?        │
+  │ (Gap = what existing work has NOT addressed)    │
   └─────────────────────────────────────────────────┘
            │
            ▼
-  Block 3: CONTRIBUTIONS              (~1 paragraph + list)
+  Block 3: RESEARCH QUESTION          (~1–2 sentences)
+  ┌─────────────────────────────────────────────────┐
+  │ The specific question this paper sets out to    │
+  │ answer — must be Specific, Feasible, Measurable │
+  └─────────────────────────────────────────────────┘
+           │
+           ▼
+  Block 4: CONTRIBUTIONS              (~1 paragraph + list)
   ┌─────────────────────────────────────────────────┐
   │ "The main contributions of this paper are:"     │
   │ • Contribution 1                                │
@@ -50,7 +58,7 @@ INTRODUCTION = 4 BLOCKS
   └─────────────────────────────────────────────────┘
            │
            ▼
-  Block 4: PAPER STRUCTURE            (~1 paragraph)
+  Block 5: PAPER STRUCTURE            (~1 paragraph)
   ┌─────────────────────────────────────────────────┐
   │ "The rest of this paper is organized as..."     │
   │ Section 2: ..., Section 3: ..., ...             │
@@ -104,7 +112,96 @@ Teach one block at a time. After each block's explanation and generic example, g
 
 ---
 
-### Block 3: Contributions — The Most Important Block
+### Block 3: Research Question
+
+**Principle**: The Research Question (RQ) is the specific question your paper sets out to answer. It appears right after the gap — bridging the problem and your contributions. A good RQ has exactly 3 properties:
+
+```
+3 TÍNH CHẤT CỦA MỘT RESEARCH QUESTION TỐT
+══════════════════════════════════════════════════════════
+
+  1. SPECIFIC (Cụ thể)
+  ─────────────────────────────────────────────────────
+  RQ phải hỏi về một đối tượng, bối cảnh, hoặc
+  hiện tượng RÕ RÀNG — không hỏi chung chung.
+
+  ❌ Vague:   "How can we improve security?"
+  ✅ Specific: "How vulnerable are Random Forest and
+               DNN-based IDS models to FGSM and PGD
+               adversarial attacks on network traffic?"
+
+  Kiểm tra: Nếu 10 researcher đọc RQ, họ có đồng ý
+  về ý nghĩa của nó không? Nếu không → còn vague.
+
+  ──────────────────────────────────────────────────────
+
+  2. FEASIBLE (Khả thi)
+  ─────────────────────────────────────────────────────
+  RQ phải trả lời được trong phạm vi thời gian,
+  nguồn lực, và dữ liệu bạn có.
+
+  ❌ Not feasible: "What is the best AI model for all
+                   cybersecurity tasks?"
+                   (quá rộng, không có đáp án dứt khoát)
+  ✅ Feasible:     "Does adversarial training reduce
+                   attack success rate on CICIDS2017
+                   by more than 20%?"
+                   (có thể đo được trong 8 tuần)
+
+  Kiểm tra: Bạn có dataset, công cụ, và thời gian
+  để trả lời câu hỏi này không?
+
+  ──────────────────────────────────────────────────────
+
+  3. MEASURABLE (Đo lường được)
+  ─────────────────────────────────────────────────────
+  Câu trả lời cho RQ phải là một kết quả CÓ THỂ
+  QUAN SÁT hoặc ĐO ĐẾM — không phải ý kiến.
+
+  ❌ Not measurable: "Is AI useful in SOC?"
+                     (useful = chủ quan, không đo được)
+  ✅ Measurable:     "To what extent do adversarial
+                     attacks degrade F1-score of
+                     ML-based IDS on CICIDS2017?"
+                     (F1-score = con số cụ thể)
+
+  Kiểm tra: Câu trả lời của bạn sẽ là số, tỉ lệ,
+  bảng so sánh, hay taxonomy? Nếu có → measurable.
+```
+
+**Các mẫu câu mở đầu RQ theo loại paper:**
+
+```
+  Empirical / new-method:
+  "To what extent does [method] improve [metric]
+   compared to [baseline] on [dataset]?"
+  "How effective is [approach] at [task] under
+   [condition]?"
+
+  Evaluation / framework:
+  "How vulnerable are [AI models] to [attack types]
+   in the context of [domain]?"
+  "What factors determine the adversarial robustness
+   of [system] against [threat]?"
+
+  Review / survey:
+  "What methods have been proposed for [task], and
+   what are their key limitations?"
+
+  Theoretical / framework:
+  "What framework can systematically evaluate
+   [property] of [system] in [context]?"
+```
+
+**Personalized example**: Dựa vào `research_questions` trong context.yaml, hiển thị RQ hiện tại của user và đánh giá theo 3 tiêu chí Specific / Feasible / Measurable. Nếu thiếu tiêu chí nào, đề xuất cách cải thiện.
+
+**Nếu user muốn xem thêm ví dụ**: Cung cấp thêm 2–3 RQ mẫu từ các paper thật trong lĩnh vực gần với topic của user.
+
+**Checkpoint**: "Nhìn vào RQ của bạn — nó đã Specific, Feasible, và Measurable chưa? Thử tự chấm điểm từng tiêu chí."
+
+---
+
+### Block 4: Contributions — The Most Important Block
 
 **Principle**: Reviewers often read the contributions list *before* reading the rest of the paper. This is your paper's "promise" — be specific, concrete, and honest.
 
@@ -144,7 +241,7 @@ The main contributions of this paper are as follows:
 
 ---
 
-### Block 4: Paper Structure
+### Block 5: Paper Structure
 
 **Principle**: One short paragraph, fixed formula, no creativity needed. Just list your sections.
 
@@ -161,6 +258,9 @@ The main contributions of this paper are as follows:
 |---------|-----|
 | Opening too vague | Start with a specific statistic, event, or real-world impact |
 | No clear problem statement | Write a dedicated paragraph naming the limitation of existing work |
+| Missing Research Question | Add 1–2 sentences after the gap: "This raises the question: ..." |
+| RQ too broad | Apply Specific + Feasible + Measurable check — narrow scope |
+| RQ not measurable | Rewrite so the answer is a number, ratio, table, or taxonomy |
 | Vague contributions | Each bullet: method/action + what it does + concrete result |
 | Missing paper structure | Use the template, just fill in your section names |
 | Contributions don't match paper type | Use the format that fits: empirical, review, or theoretical |

package/.claude/skills/paper-teach-method/SKILL.md

@@ -11,7 +11,7 @@ You are teaching a first-time student researcher how to write the **Methodology*
 
 **Teaching mode only** — recommend `/paper:write method` at the end.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 

package/.claude/skills/paper-teach-related/SKILL.md

@@ -11,7 +11,7 @@ You are teaching a first-time student researcher how to write the **Related Work
 
 **Teaching mode only** — recommend `/paper:write related` at the end.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 
@@ -146,7 +146,7 @@ Opening sentence:
 
 **Personalized example**: Generate a sample theme grouping structure for the user's specific topic and field.
 
-**Checkpoint**: "How many papers have you read so far? Try grouping them into 2–3 themes — what patterns do you see?"
+**Checkpoint**: "Thử nhìn vào các papers bạn đang có hoặc dự định tìm — bạn thấy chúng có thể nhóm thành 2–3 theme nào không? Mô tả ngắn gọn là được."
 
 ---
 

package/.claude/skills/paper-teach-results/SKILL.md

@@ -11,7 +11,7 @@ You are teaching a first-time student researcher how to write the **Results** se
 
 **Teaching mode only** — recommend `/paper:write results` at the end.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 

package/.claude/skills/paper-write-abstract/SKILL.md

@@ -9,7 +9,7 @@ metadata:
 
 You are helping a student write their **Abstract** — the last section to write, though it appears first. Synthesize from completed sections automatically, adapt the formula to paper type, then confirm with the user.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 

package/.claude/skills/paper-write-conclusion/SKILL.md

@@ -9,7 +9,7 @@ metadata:
 
 You are helping a student write their **Conclusion** section. This is shorter but must be distinct from the abstract — it reflects on what was proven, not just what was done.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 

package/.claude/skills/paper-write-experiment/SKILL.md

@@ -9,7 +9,7 @@ metadata:
 
 You are helping a student write their **Experiments** section. This section must be detailed enough that another researcher can reproduce the experimental setup exactly.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 

package/.claude/skills/paper-write-intro/SKILL.md

@@ -9,7 +9,7 @@ metadata:
 
 You are helping a student write their **Introduction** section via guided Q&A. Read context, ask questions, then write the draft.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 
@@ -29,7 +29,7 @@ Check if `paper/context.yaml` exists and read it.
 
 ## Step 2: Q&A (ask one at a time, wait for each answer)
 
-Tell the user: "I'll ask you 5 questions to gather enough information to write your Introduction. Short answers are fine — I'll expand them when writing."
+Tell the user: "I'll ask you 6 questions to gather enough information to write your Introduction. Short answers are fine — I'll expand them when writing."
 
 **Q1**: "What is the problem your paper addresses? Describe it briefly."
 *(Example: "Phishing websites trick users into giving away passwords, and current detection systems are too slow to catch newly created ones.")*
@@ -41,30 +41,51 @@ Tell the user: "I'll ask you 5 questions to gather enough information to write y
 *(Example: "Most systems use blacklists — databases of known bad URLs. But these lists take hours to update, so brand-new phishing sites slip through for hours before being blocked.")*
 *(If the user is unsure, prompt: "Think about what tools or methods exist today. What can they NOT do?")*
 
-**Q4**: "What are your main contributions? List 2–3 specific points."
+**Q4**: "What is your Research Question — the specific question your paper sets out to answer?"
+
+If `research_questions` already exists in context.yaml, show it and ask: "Is this still your RQ, or would you like to refine it?"
+
+If missing or user is unsure, guide them:
+> "Try filling in one of these templates:
+> - 'To what extent does [your method] improve [metric] compared to [baseline] on [dataset]?'
+> - 'How vulnerable are [AI models] to [attack types] in the context of [domain]?'
+> - 'What framework can systematically evaluate [property] of [system]?'"
+
+Then validate the RQ against 3 criteria before accepting:
+- **Specific**: Is it about a clearly defined object/context?
+- **Feasible**: Can it be answered with available data and time?
+- **Measurable**: Will the answer be a number, ratio, table, or taxonomy?
+
+If any criterion fails, suggest a refined version and confirm with the user.
+
+**Q5**: "What are your main contributions? List 2–3 specific points."
 *(Example: "1) We propose PhishGuard, a real-time URL classifier using 48 features. 2) We achieve 97.4% F1 on 30,000 URLs, beating the best baseline by 5.3%. 3) We identify the top 10 features most predictive of phishing.")*
 *(Guide if stuck: "Start with: 'We propose...', 'We demonstrate...', 'We achieve...'")*
 
-**Q5**: Read the outline from `context.yaml` (sections_status keys) and confirm with the user:
+**Q6**: Read the outline from `context.yaml` (sections_status keys) and confirm with the user:
 "Based on your plan, your paper has these sections: [list from context.yaml]. Should I use this structure for the paper structure paragraph, or would you like to adjust it?"
 
 ---
 
 ## Step 3: Write Draft
 
-After all Q&A, write a complete Introduction following the 4-block structure. Adapt language and framing to the user's field and paper_type.
+After all Q&A, write a complete Introduction following the 5-block structure. Adapt language and framing to the user's field and paper_type.
 
 **Block 1 — Background (2–3 sentences):**
 - Open with the scale, impact, or significance of the problem domain
 - Narrow from broad context to the specific problem
 - Use numbers or statistics if the user provided them
 
-**Block 2 — Problem Statement (2–3 sentences):**
+**Block 2 — Problem Statement + Gap (2–3 sentences):**
 - State the specific problem clearly
 - Explain the limitations of existing approaches (from Q3)
-- End with a motivating statement: "This motivates the need for [approach]."
+- End with the gap: "However, no existing work has systematically addressed [missing piece]."
+
+**Block 3 — Research Question (1–2 sentences):**
+- Transition naturally from the gap: "This raises the question: ..." or "To address this gap, this paper asks: ..."
+- Write the validated RQ from Q4 verbatim — do not paraphrase or soften it
 
-**Block 3 — Contributions (1 sentence + bullet list):**
+**Block 4 — Contributions (1 sentence + bullet list):**
 
 Adapt the format to paper_type and contribution_type:
 
@@ -92,7 +113,7 @@ The main contributions of this paper are as follows:
 • We discuss implications for [theory / practice / policy].
 ```
 
-**Block 4 — Paper Structure (1 paragraph):**
+**Block 5 — Paper Structure (1 paragraph):**
 "The rest of this paper is organized as follows. Section 2 [reviews / describes / ...]. Section 3 [describes / presents / ...]. [Continue per outline.] Section N concludes the paper."
 
 ---

package/.claude/skills/paper-write-method/SKILL.md

@@ -9,7 +9,7 @@ metadata:
 
 You are helping a student write their **Methodology** section. Read context, conduct Q&A, then write a draft tailored to the paper type.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 

package/.claude/skills/paper-write-related/SKILL.md

@@ -9,7 +9,7 @@ metadata:
 
 You are helping a student write their **Related Work** section. Read context, conduct Q&A about papers they've read, then write a thematically organized draft.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---
 
@@ -26,11 +26,40 @@ Check `paper/context.yaml`. If missing, ask the user to run `/paper:plan` first.
 
 ## Step 2: Q&A (one at a time, wait for each answer)
 
-Tell the user: "I need to know about the papers you've read to write your Related Work. Answer as best you can — if you haven't read many papers yet, I'll help you think through what to look for."
+Tell the user: "Before we start writing, let me recommend the types of papers you should look for based on your topic."
 
-**Q1**: "List 5–10 related papers you've read or know of. Format: [Author(s), year — brief description or method name]"
-*(Example: "Zhang et al. 2020 — SVM with URL features; Google Safe Browsing 2022 — blacklist API; Li et al. 2021 — LSTM on HTML content")*
-*(If few papers: "Search Google Scholar for '[your topic] survey' or '[your topic] review' filtered to last 5 years. Aim for at least 8 papers.")*
+**Q1 — Paper Recommendation (không hỏi user có bao nhiêu bài)**
+
+Dựa vào `topic`, `field`, `contribution_type`, và `research_questions` từ context.yaml, generate một danh sách recommend theo format:
+
+```
+PAPERS BẠN NÊN TÌM
+════════════════════════════════════════════════════════
+
+  Nhóm 1 — [Theme 1 liên quan đến topic]
+  Tìm: "[keyword search query]" trên Google Scholar
+  Cần: 3–5 papers, ưu tiên sau [năm hiện tại - 3]
+  Mục đích: Làm background cho phần [problem/gap]
+
+  Nhóm 2 — [Theme 2: existing methods/approaches]
+  Tìm: "[keyword search query]"
+  Cần: 4–6 papers
+  Mục đích: Nhóm paper chính để critique limitations
+
+  Nhóm 3 — [Theme 3: most related to your method]
+  Tìm: "[keyword search query]"
+  Cần: 3–5 papers
+  Mục đích: Positioning — chứng minh bạn khác họ ở đâu
+
+  Tổng recommend: 10–16 papers
+  → Dùng Google Scholar Operators để tìm nhanh
+  → Lưu vào Zotero, dùng /paper:cite để chèn sau
+```
+
+Sau khi show recommendation, hỏi:
+"Bạn đã tìm được paper nào chưa? Nếu có, list ra để mình map vào các nhóm trên. Nếu chưa, tìm theo gợi ý trên rồi quay lại."
+
+Khi user đã có papers, tiếp tục Q2.
 
 **Q2**: "How would you group those papers into 2–3 themes or categories? What patterns do you see?"
 *(Example: "Group 1: blacklist-based — PhishTank, Safe Browsing. Group 2: ML with URL features — Zhang, Li, Kim. Group 3: deep learning on page content — Chen, Wang.")*
@@ -71,4 +100,101 @@ Ask: "Shall I save this draft to `paper/sections/02-related-work.md`?"
 
 If yes, save and update context.yaml: `related_work: draft`.
 
-"Draft saved! Continue with `/paper:teach method` or review this section with `/paper:review related`."
+"Draft saved! Use `/paper:cite` để chèn citation vào bài, sau đó quay lại đây để mình đánh giá references."
+
+---
+
+## Step 5: Reference Quality Evaluation
+
+Chạy bước này sau khi user đã chèn citation (qua `/paper:cite`). User có thể trigger bằng cách paste draft đã có citation vào, hoặc mention "đã cite xong".
+
+Đọc toàn bộ draft Related Work đã có citation và đánh giá theo 3 tiêu chí:
+
+### Tiêu chí 1 — Độ phủ (Coverage)
+
+```
+KIỂM TRA ĐỘ PHỦ
+════════════════════════════════════════════════════════
+
+  Mỗi factual claim phải có ít nhất 1 citation.
+  Scan từng câu có dạng:
+  • "X has been shown to..."      → cần cite
+  • "Studies indicate that..."    → cần cite
+  • "X achieves Y% accuracy..."   → cần cite
+  • "X is widely used in..."      → cần cite
+
+  Câu KHÔNG cần cite:
+  • Kết quả của chính paper này
+  • Câu chuyển tiếp
+  • Common knowledge quá phổ biến
+```
+
+Nếu có claim thiếu citation → list ra và recommend paper bổ sung:
+
+```
+THIẾU CITATION
+════════════════════════════════════════════════════════
+
+  Claim: "[câu cụ thể]"
+  → Cần: 1–2 papers về [chủ đề]
+  → Search: "[suggested query]" on Google Scholar
+  → Loại paper phù hợp: [survey / empirical / benchmark]
+```
+
+### Tiêu chí 2 — Tính thuyết phục (Persuasiveness)
+
+Đánh giá từng nhóm theme:
+
+```
+ĐÁNH GIÁ TỪNG NHÓM
+════════════════════════════════════════════════════════
+
+  Nhóm [Theme 1]:  X papers
+  → Đủ thuyết phục? [Yes / Borderline / No]
+  → Lý do: [giải thích]
+
+  Nhóm [Theme 2]:  X papers
+  → Đủ thuyết phục? [...]
+
+  Positioning:     X papers
+  → Đủ để claim novelty? [Yes / No]
+```
+
+**Ngưỡng tối thiểu:**
+- Mỗi theme: ≥ 2 papers (1 paper = không đủ để generalize)
+- Positioning paragraph: ≥ 1 paper trực tiếp so sánh với approach của bạn
+- Tổng Related Work: ≥ 10 papers (conference), ≥ 20 (journal)
+
+### Tiêu chí 3 — Redundancy (Dư thừa)
+
+Nếu có papers bị cite nhưng không đóng góp gì vào argument:
+
+```
+NÊN BỎ BỚT
+════════════════════════════════════════════════════════
+
+  Paper: [tên]
+  Lý do nên bỏ: Nội dung trùng với [paper khác] /
+                Không support claim cụ thể nào /
+                Quá cũ và đã có paper mới hơn thay thế
+```
+
+### Kết luận đánh giá
+
+Sau khi phân tích xong, xuất ra **Reference Quality Report**:
+
+```
+REFERENCE QUALITY REPORT
+════════════════════════════════════════════════════════
+
+  Tổng citations hiện tại: X
+  
+  ✅ Đủ: [list các nhóm đã đủ]
+  ⚠️ Thiếu: [list claim cần thêm paper + gợi ý tìm]
+  ❌ Nên bỏ: [list papers dư thừa + lý do]
+
+  Sau khi bổ sung/bỏ: ước tính X papers
+  → Đủ thuyết phục cho [venue từ context.yaml]? [Yes/No]
+
+  Next: `/paper:review related` để review toàn diện hơn.
+```

package/.claude/skills/paper-write-results/SKILL.md

@@ -9,7 +9,7 @@ metadata:
 
 You are helping a student write their **Results** section. Push the user to go beyond reporting numbers — analysis and interpretation are what make results compelling.
 
-**English only** — Respond in English regardless of what language the user writes in.
+**Language** — Always respond in the same language the user writes in. If they write in Vietnamese, respond in Vietnamese. If English, respond in English.
 
 ---