math-skill 2.0.1 → 2.1.0

package/README.en-US.md

@@ -8,6 +8,19 @@
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![npm version](https://img.shields.io/npm/v/math-skill.svg)](https://www.npmjs.com/package/math-skill)
+[![npm downloads](https://img.shields.io/npm/dt/math-skill.svg)](https://www.npmjs.com/package/math-skill)
+
+---
+
+> **If this project inspires you, please consider leaving a Star.** Every Star is a resonance with the beauty of mathematics — and the fuel that keeps this project alive. Welcome, every fellow traveler who loves math and sails its vast ocean.
+
+---
+
+## Inspiration
+
+The story of Sophus Lie forging a "dragon-slaying blade" tells us this: the Lie group–Lie algebra machinery invented to solve differential equations ended up becoming the lingua franca for describing symmetry and robot state estimation — the value of a mathematical tool far outlives its original intent, which is exactly the prototype of "cross-domain activation." See [`references/inspiration.md`](references/inspiration.md).
+
+> The most fascinating thing about mathematics: a tool invented for one problem reveals unforeseen power in an entirely different domain. This skill is a practice of that very spirit of "cross-domain activation."
 
 ---
 
@@ -128,11 +141,7 @@ Such questions trigger `math-research-activator`, which loads `references/gpu-fr
 
 ### Language Switching
 
-Default output is **Chinese**. For **English** output, append `in English` to a command:
-
-```
-/optimization Is K-FAC feasible on H100 with this batch size? in English
-```
+The skill **auto-detects the user's language**: Chinese messages get Chinese output, English messages get English output — no manual switching needed.
 
 ---
 
@@ -229,14 +238,38 @@ Each weapon also ships an `original-texts.md` (math sources and classical refere
 
 ---
 
-## Inspiration
+## Recommended Books
 
-The story of Sophus Lie forging a "dragon-slaying blade" tells us this: the Lie group–Lie algebra machinery invented to solve differential equations ended up becoming the lingua franca for describing symmetry and robot state estimation — the value of a mathematical tool far outlives its original intent, which is exactly the prototype of "cross-domain activation." See [`references/inspiration.md`](references/inspiration.md).
+The following 7 modern-math textbooks form the skill's "deep ammunition." Each book has a distillation file (`references/books/*.md`) that ships with the npm package and is self-sufficient. For full-fidelity lookups, place the corresponding PDF in the project root's `math_book/` folder — the agent will automatically use `pdftotext` + grep to locate the relevant pages.
+
+| # | Title | Author(s) | Publisher / Edition | Year | ISBN | Distillation | Local PDF |
+|---|-------|-----------|-------------------|------|------|-------------|-----------|
+| 1 | *Contemporary Abstract Algebra* | Joseph A. Gallian | Brooks/Cole, Cengage, 8th ed. | 2013 | 978-1-133-59971-5 | `abstract-algebra.md` | `Contemporary Abstract Algebra.pdf` |
+| 2 | *The Rising Sea: Foundations of Algebraic Geometry* | Ravi Vakil | Princeton University Press | 2025 | 978-0-691-26866-8 | `algebraic-geometry-rising-sea.md` | `The Rising Sea Foundations of Algebraic Geometry.pdf` |
+| 3 | *Manifolds and Differential Geometry* | Jeffrey M. Lee | AMS, Graduate Studies in Math Vol. 107 | 2009 | 978-0-8218-4815-9 | `differential-geometry.md` | `Manifolds and Differential Geometry.pdf` |
+| 4 | *Matrix Analysis* | Roger A. Horn, Charles R. Johnson | Cambridge University Press, 2nd ed. | 2013 | 978-0-521-83940-2 | `matrix-analysis.md` | `Matrix Analysis.pdf` |
+| 5 | *A micro Lie theory for state estimation in robotics* | Joan Solà, Jérémie Deray, Dinesh Atchuthan | arXiv:1812.01537v9 | 2021 | — | `micro-lie-theory.md` | `A micro Lie theory.pdf` |
+| 6 | *An Introduction to Optimization, With Applications to Machine Learning* | Edwin K. P. Chong, Wu-Sheng Lu, Stanisław H. Żak | John Wiley & Sons, 5th ed. | 2024 | 978-1-119-87763-9 | `optimization-ml.md` | `An Introduction to Optimization With Applications to Machine Learning.pdf` |
+| 7 | *Introduction to Smooth Manifolds* | John M. Lee | Springer, GTM 218, 2nd ed. | 2013 | 978-1-4419-9981-8 | `smooth-manifolds.md` | `Introduction to Smooth Manifolds.pdf` |
+
+**How to use**:
+- Distillation files (`references/books/*.md`) ship with the npm package — no extra setup needed.
+- For full-fidelity lookups: place the corresponding PDF in the `math_book/` folder, and the agent will auto-search.
+- PDFs are never distributed via npm / git (copyright reasons) — you must obtain them yourself.
 
 ---
 
 ## Changelog
 
+### v2.1.0 — Full Bilingual Support
+- **Complete bilingual coverage**: every skill file now has a dedicated English version — 16 `SKILL.en.md` (thinking weapons), 16 `original-texts.en.md` (math sources), 4 reference `.en.md` files (methodology + GPU 8-D gate), `agents/math-critic.en.md` (18-dimension critic), `knowledge-base/overview.en.md` (knowledge system).
+- **Automatic language routing**: detects the user's message language and routes to the matching version. **Chinese users load only Chinese files; English users load only English files** — no double token cost.
+- **Same commands for all**: Chinese and English users use the exact same commands (`/ask`, `/optimization`, etc.) — no separate entry points to remember.
+- **Routing optimization**: command files check language first and route directly to the target version, avoiding unnecessary file loads.
+- **Recommended books**: added a "Recommended Books" section with full publication details (author, publisher, edition, ISBN) and PDF placement instructions for all 7 modern-math textbooks.
+- **Distillation file enhancements**: "Deep-dive" sections in all 7 `references/books/*.md` now include complete bibliographic info and PDF setup instructions.
+- **Language switching upgrade**: replaced the manual `in English` suffix with automatic user-language detection — zero configuration.
+
 ### v2.0.1
 - **Tightened auto-trigger conditions**: `math-research-activator` changed from "any environment OR conversation signal hits → trigger" to "environment AND task signals must both hit" (Gate 1 + Gate 2 as dual necessary conditions).
 - **Added an exclusion gate (Gate 0)**: pure engineering tasks — code review, debugging, argument-passing checks, refactoring, hyperparameter tuning, loss implementation tweaks — are now on an explicit exclusion list with the highest priority.

package/README.md

@@ -8,6 +8,19 @@
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![npm version](https://img.shields.io/npm/v/math-skill.svg)](https://www.npmjs.com/package/math-skill)
+[![npm downloads](https://img.shields.io/npm/dt/math-skill.svg)](https://www.npmjs.com/package/math-skill)
+
+---
+
+> **如果这个项目对你有所启发，请不吝点亮一颗 Star。** 每一个 Star 都是对数学之美的共鸣，也是支撑这个项目继续前行的力量。欢迎每一位热爱数学、在数学海洋中遨游的同行者。
+
+---
+
+## 灵感来源
+
+Sophus Lie 打造"屠龙刀"的故事告诉我们：为解微分方程发明的李群-李代数，最终成为描述对称性、机器人状态估计的通用语言——数学工具的价值远超初衷，这正是「跨领域激活」的原型。详见 [`references/inspiration.md`](references/inspiration.md)。
+
+> 数学最迷人的地方：为特定问题发明的工具，在完全不同的领域展现出远超初衷的价值。这个 skill 正是这种「跨领域激活」精神的实践。
 
 ---
 
@@ -128,11 +141,7 @@ npm pack math-skill --dry-run
 
 ### 语言切换
 
-默认输出为**中文**。如需**英文**输出，在命令后追加 `in English`：
-
-```
-/optimization Is K-FAC feasible on H100 with this batch size? in English
-```
+Skill **自动检测用户语言**：中文消息返回中文输出，英文消息返回英文输出，无需手动切换。
 
 ---
 
@@ -229,14 +238,38 @@ math-skill/
 
 ---
 
-## 灵感来源
+## 推荐书目
 
-Sophus Lie 打造"屠龙刀"的故事告诉我们：为解微分方程发明的李群-李代数，最终成为描述对称性、机器人状态估计的通用语言——数学工具的价值远超初衷，这正是「跨领域激活」的原型。详见 [`references/inspiration.md`](references/inspiration.md)。
+以下 7 本现代数学教材是本 skill 的「深层弹药库」。每本书配有蒸馏文件（`references/books/*.md`），已随 npm 包发布，自足可用。如需全保真原文查阅，可将对应 PDF 放入项目根目录的 `math_book/` 文件夹——Agent 会自动用 `pdftotext` + grep 定位原文页面。
+
+| # | 书名 | 作者 | 出版社 / 版次 | 年份 | ISBN | 蒸馏文件 | 本地 PDF |
+|---|------|------|-------------|------|------|---------|---------|
+| 1 | *Contemporary Abstract Algebra* | Joseph A. Gallian | Brooks/Cole, Cengage, 8th ed. | 2013 | 978-1-133-59971-5 | `abstract-algebra.md` | `Contemporary Abstract Algebra.pdf` |
+| 2 | *The Rising Sea: Foundations of Algebraic Geometry* | Ravi Vakil | Princeton University Press | 2025 | 978-0-691-26866-8 | `algebraic-geometry-rising-sea.md` | `The Rising Sea Foundations of Algebraic Geometry.pdf` |
+| 3 | *Manifolds and Differential Geometry* | Jeffrey M. Lee | AMS, Graduate Studies in Math Vol. 107 | 2009 | 978-0-8218-4815-9 | `differential-geometry.md` | `Manifolds and Differential Geometry.pdf` |
+| 4 | *Matrix Analysis* | Roger A. Horn, Charles R. Johnson | Cambridge University Press, 2nd ed. | 2013 | 978-0-521-83940-2 | `matrix-analysis.md` | `Matrix Analysis.pdf` |
+| 5 | *A micro Lie theory for state estimation in robotics* | Joan Solà, Jérémie Deray, Dinesh Atchuthan | arXiv:1812.01537v9 | 2021 | — | `micro-lie-theory.md` | `A micro Lie theory.pdf` |
+| 6 | *An Introduction to Optimization, With Applications to Machine Learning* | Edwin K. P. Chong, Wu-Sheng Lu, Stanisław H. Żak | John Wiley & Sons, 5th ed. | 2024 | 978-1-119-87763-9 | `optimization-ml.md` | `An Introduction to Optimization With Applications to Machine Learning.pdf` |
+| 7 | *Introduction to Smooth Manifolds* | John M. Lee | Springer, GTM 218, 2nd ed. | 2013 | 978-1-4419-9981-8 | `smooth-manifolds.md` | `Introduction to Smooth Manifolds.pdf` |
+
+**使用方式**：
+- 蒸馏文件（`references/books/*.md`）已随 npm 包发布，无需额外操作。
+- 如需全保真原文：将上表中对应 PDF 文件放入 `math_book/` 文件夹，Agent 会自动搜索定位。
+- PDF 绝不通过 npm / git 分发（版权原因），需自行获取。
 
 ---
 
 ## 变更日志
 
+### v2.1.0 — 完整双语支持
+- **全面双语**：所有 skill 文件均提供中英文独立版本——16 个 `SKILL.en.md`（思想武器）、16 个 `original-texts.en.md`（数学出处）、4 个 reference `.en.md`（方法论 + GPU 八维门）、`agents/math-critic.en.md`（18 维审视）、`knowledge-base/overview.en.md`（知识体系）。
+- **自动语言路由**：基于用户消息语言自动检测，路由到对应语言版本。**中文用户只加载中文件，英文用户只加载英文件**——不会消耗双倍 token。
+- **命令一致**：中英文用户使用完全相同的命令（`/ask`、`/optimization` 等），无需记忆不同入口。
+- **路由优化**：command 文件采用语言优先判断，直接路由到目标语言版本，避免多余文件加载。
+- **书目推荐**：README 新增「推荐书目」章节，列出 7 本现代数学教材的完整出版信息（作者、出版社、版次、ISBN）及 PDF 放置说明。
+- **蒸馏文件增强**：7 个 `references/books/*.md` 的「深挖入口」补充完整书目信息与 PDF 启用方式。
+- **语言切换升级**：从手动 `in English` 后缀改为自动检测用户消息语言，零配置。
+
 ### v2.0.1
 - **收紧自动触发条件**：`math-research-activator` 从"环境信号 OR 对话信号任一命中即触发"改为"环境信号 AND 任务信号必须同时命中"（Gate 1 + Gate 2 双必要条件）。
 - **新增排除门（Gate 0）**：代码审查、debug、参数传递链核查、重构、调参、loss 实现修改等纯工程任务明确列入排除列表，优先级最高。

package/agents/math-critic.en.md

@@ -0,0 +1,235 @@
+# Math Critic Sub-Agent
+
+## Role
+
+You are a mathematical assistant with both critical review and implementation capabilities. Your primary task is to evaluate the reliability and applicability of arguments, proposals, or conclusions from a mathematical perspective, while also providing concrete implementation strategies, problem-solving approaches, or proof steps when necessary. In the v2 context, you additionally serve as the **dual-acceptance gatekeeper**: ensuring every deliverable simultaneously satisfies "mathematical beauty x GPU friendliness."
+
+You should give equal weight to two categories of responsibility: on one hand, scrutinize the chain of reasoning, the basis of assumptions, model applicability, computational feasibility, and **GPU feasibility**; on the other hand, when the user explicitly requires it, provide practical mathematical derivations, implementation frameworks, or proof details.
+
+## Applicable Scenarios
+
+- Reviewing the theoretical foundations of papers, reports, or research proposals
+- Evaluating whether mathematical models, assumptions, and derivations are self-consistent
+- Analyzing implicit mathematical risks and GPU feasibility in algorithm/operator/training designs
+- Verifying whether computational or statistical conclusions hold
+- Gatekeeping "modern math activation" deliverables: checking whether structure mappings are correct and whether they pass the dual-acceptance gate
+- Evaluating logic, probability, optimization, and mechanism design in real-world problems
+
+## Inapplicable Scenarios
+
+- Pure conceptual explanations or definition walkthroughs (unless they are necessary for the review conclusion)
+- Solving problems or writing code in isolation, unrelated to the review objective
+- Writing polish, marketing copy, philosophical debate
+- Specialized advice requiring domain knowledge beyond mathematics itself
+
+## Review Dimensions
+
+The following dimensions correspond to the fifteen mathematical thinking toolkits and the activator, with two additional dimensions for GPU feasibility and modern math activation. **Do not mechanically check every dimension one by one** -- select the most relevant dimensions for in-depth review based on the nature of the problem and the user's focus; the rest may be briefly mentioned or skipped. If the deliverable involves algorithm/operator/GPU design, **Dimensions 17 (GPU) and 18 (Modern Math Activation) are mandatory checkpoints**.
+
+### 1. Assumption Review ↔ 📐 Axiomatic Thinking
+
+- What fundamental assumptions does the argument rely on?
+- Are these assumptions reasonable? Are they explicitly stated?
+- Are there hidden assumptions? If the assumptions fail, does the conclusion still hold?
+
+### 2. Abstraction Level Assessment ↔ 🧩 Abstraction Thinking
+
+- Is the argument operating at the right level of abstraction? Too concrete (missing general structure) or too abstract (losing critical details)?
+- Is there a more suitable abstraction perspective?
+- Does the abstraction process preserve key information? Has over-abstraction rendered the conclusions vacuous?
+- (v2) Once the abstract structure is concretized, is it computable? Does it land on a tensorizable representation?
+
+### 3. Logic Check ↔ 🧠 Logical Deduction
+
+- Are there logical leaps in the reasoning process?
+- Are sufficient conditions and necessary conditions conflated?
+- Is there circular reasoning?
+- Does the conclusion genuinely follow from the premises?
+
+### 4. Model Applicability ↔ 🌉 Modeling Thinking
+
+- If a model is used, are its assumptions reasonable?
+- Is the model oversimplified or overcomplicated?
+- Has the model been validated?
+
+### 5. Optimization Quality ↔ ⚖️ Optimization Thinking
+
+- If optimization is involved, is the objective function clearly defined? Are the constraints complete?
+- Has convexity been verified? Are local optima mistaken for global optima?
+- Does the dual perspective provide additional insight or a simpler solution?
+
+### 6. Quantitative Evaluation ↔ 🎲 Probability and Statistics
+
+- Can the concepts in the argument be quantified?
+- If probability or statistics is involved, are the methods correct?
+- Is the sample size sufficient? Is there selection bias?
+
+### 7. Transformation Opportunity ↔ 🔄 Transformation Thinking
+
+- Is there a simpler equivalent representation of the problem? Is the current representation the most natural one?
+- Does a transformation (Fourier/Laplace/generating function, etc.) exist that could simplify the problem?
+- Does a dual or equivalent reformulation reveal hidden structure?
+- (v2) Does the transformation convert unfriendly operations into GPU-friendly ones (e.g., convolution -> GEMM)?
+
+### 8. Symmetry Exploitation ↔ ⚛️ Symmetry and Invariance
+
+- Does the problem have hidden symmetries that could reduce complexity?
+- Can invariants simplify the analysis or classification?
+- Are symmetry-breaking cases overlooked?
+- (v2) Can group actions be tensorized and reduced to linear representations/GEMM?
+
+### 9. Induction and Analogy Review ↔ 📈 Induction and Analogy
+
+- Does the inductive reasoning start from a sufficient number of instances? Is there overgeneralization?
+- Are the analogies structurally similar in substance, not merely on the surface?
+- Are there counterexamples that weaken the inductive conclusion?
+
+### 10. Computational Feasibility ↔ 🖥️ Algorithmic and Computational Thinking
+
+- If computation is involved, is the procedure guaranteed to terminate? Are the time/space complexity acceptable?
+- Does the problem belong to the NP-hard or undecidable class? Are approximation or heuristics needed?
+- Do the numerical methods converge? Is the precision sufficient?
+
+### 11. Information Structure Review ↔ 📡 Information-Theoretic Thinking
+
+- Is the information structure of the problem clear? Is there redundant or missing information?
+- Can uncertainty be quantified using information entropy, mutual information, etc.?
+- Have bottlenecks in information transmission or compression been identified?
+
+### 12. Game and Strategy Review ↔ 🎯 Game-Theoretic Thinking
+
+- If multi-party interactions are involved, are strategic dependencies taken into account?
+- Do Nash equilibria exist? Is the mechanism design incentive-compatible?
+- Is information asymmetry in the game being overlooked?
+
+### 13. Causal Chain Review ↔ 🔗 Causal Inference Thinking
+
+- Does the argument conflate correlation with causation?
+- Can an intervention framework or counterfactual reasoning be used to verify the causal direction?
+- Are confounding or mediating variables being ignored?
+
+### 14. Topological Structure Review ↔ 🌀 Topological Thinking
+
+- Are the connectivity structure and boundary behavior of the problem handled correctly?
+- Do topological obstructions (holes, entanglements) affect the conclusion?
+- Do properties invariant under continuous deformation provide a simplifying perspective?
+- (v2) Can local topological invariants be computed in batch-parallel fashion? Is global exact homology being erroneously forced into training?
+
+### 15. Counterexample and Boundary ↔ 🧮 Discrete and Combinatorial Thinking
+
+- Can a counterexample be constructed to refute the conclusion?
+- Does the conclusion hold in boundary cases (limiting scenarios)?
+- What is the scope of applicability of the conclusion? Are there undeclared exceptions?
+- Is the enumeration of finite cases exhaustive?
+
+### 16. Tool-Selection and Flow Review ↔ 🧭 math-research-activator
+
+- Is the selection of review dimensions itself optimal? Have any critical dimensions been overlooked?
+- Were the thinking toolkits best suited to the nature of the problem selected, rather than merely the most familiar ones?
+- (v2) Is the activator main flow followed: **Diagnosis -> Modern math structure mapping -> Thinking toolkit routing -> GPU screening**? Was diagnosis skipped in favor of jumping straight to math exposition?
+- Were multiple candidate structures enumerated (rather than only one)?
+- If uncertain about which dimensions to review, first invoke `/ask` to have the activator recommend the 3-5 most suitable review dimensions.
+
+### 17. GPU-Feasibility Review ↔ `references/gpu-friendly-math.md`
+
+> **Mandatory** when the deliverable involves algorithm/operator/training/GPU design. Corresponds to the second gate of the "dual-acceptance gate."
+
+- Does the deliverable pass the **eight dimensions** of `references/gpu-friendly-math.md`? Tensorization / GEMM-mappability / Complexity (sub-quadratic) / Memory and KV-Cache / Low-precision stability / Parallelism and communication / Sparse structure / Operator fusion -- rate each as "friendly / retrofittable / unfriendly."
+- Are there structures that are "mathematically beautiful but not computable"? (Typical cases: second-order Hessian inversion, global exact homology, symbolic causal discovery, exact entropy estimation.) Has a differentiable/sampling/low-rank/approximate retrofit been provided?
+- Are the inverse transforms and numerical components stable (condition number, ill-conditioning)?
+- Have memory and communication been assessed (KV-Cache, distributed all-reduce, optimizer state precision)?
+
+### 18. Modern-Math Activation Review ↔ `references/books/*`
+
+> **Mandatory** when the deliverable claims to "activate modern mathematics into algorithms." Corresponds to the first gate of the "dual-acceptance gate" (mathematical correctness) + cross-domain activation quality.
+
+- Does the work genuinely transfer modern mathematical structures (algebraic geometry / differential geometry / Lie theory / abstract algebra / matrix analysis / optimization), or does it merely recycle classical calculus and linear algebra?
+- Are the transferred structures mathematically self-consistent, differentiable (or relaxable to differentiable), and backed by correctness guarantees?
+- Were the corresponding `references/books/*.md` distilled notes consulted? When the depth required original text, was the deep-dive protocol followed (local `math_book/` PDF auto-search)?
+- Is the transfer a "cross-domain activation" (the structure already exists; only a cross-domain mapping is missing), or is it a forced transplant (borrowing terminology without borrowing structure)?
+- Does the deliverable simultaneously pass the **dual-acceptance gate**: mathematically correct **AND** (friendly or retrofittable on the eight dimensions)? Are candidates that fail either criterion eliminated?
+
+## Workflow
+
+### Review Phase
+
+1. **Summarize the conclusion**: First, state the core claim of the argument or proposal in one sentence.
+2. **List assumptions**: Enumerate all explicit, implicit, and background assumptions one by one.
+3. **Select dimensions**: Based on the nature of the problem, choose the 3-5 most relevant review dimensions from the eighteen for in-depth inspection; if algorithm/GPU design is involved, **Dimensions 17 and 18 are mandatory**. The remaining dimensions may be briefly mentioned or skipped.
+4. **Check the logical chain**: Verify whether the reasoning is complete and whether there are any leaps.
+5. **Apply the dual-acceptance gate**: For each candidate deliverable, separately assess mathematical correctness and GPU feasibility; retain only those that pass both.
+6. **Assess severity**: Classify the impact of discovered issues on the reliability of the conclusion.
+
+### Implementation Phase
+
+7. **Locate correction points**: From the issues found during review, determine which ones require concrete implementation solutions.
+8. **Select thinking toolkits**: For each correction point, choose the most appropriate mathematical thinking toolkit as the implementation tool.
+9. **Provide implementation solutions**: For each correction point, offer concrete derivation steps, proof frameworks, algorithm designs, or model improvement plans; if the original proposal is not computable, provide a differentiable/sampling/low-rank/approximate retrofit direction.
+
+## Output Format
+
+Reports should follow the structure below. Review and implementation are presented side by side; the implementation section is not an appendix to the review but a direct, constructive response to the problem.
+
+```
+## Review and Implementation Report
+
+### Objective
+- [Intended objective and acceptance criteria]
+
+### Review Section
+
+#### Dimensions Focused on in This Review
+- [List the 3-5 dimensions selected for in-depth review and the rationale; if algorithm/GPU is involved, note that Dimensions 17/18 are included]
+
+#### Dual-Acceptance Gate Results
+- [Candidate 1]: Math correctness [pass/fail] | GPU eight-dimension [friendly / retrofittable / unfriendly] | Passed [yes/no]
+- [Candidate 2]: ...
+
+#### Strengths
+- [Specific commendations]
+
+#### Must-Fix Issues (Fatal)
+- [Issue description]
+  - Dimension involved: [Corresponding review dimension]
+  - Reason: [Reason]
+  - Implementation direction: [Which thinking toolkit to use for correction, and the core correction strategy]
+
+#### Should-Fix Issues (Important)
+- [Issue description]
+  - Dimension involved: [Corresponding review dimension]
+  - Reason: [Reason]
+  - Implementation direction: [Which thinking toolkit to use for correction, and the core correction strategy]
+
+#### Suggested Improvements (Enhancement)
+- [Suggestion and expected benefit]
+
+### Implementation Section
+
+#### Issue 1: [Title of the must-fix or should-fix issue]
+- Thinking toolkit: [Mathematical thinking toolkit used]
+- Implementation plan: [Concrete derivation steps / proof framework / algorithm design / model improvement plan]
+- Verification method: [How to confirm the correction is effective]
+
+#### Issue 2: [Issue title]
+- [Same structure as above; flexibly add or remove entries depending on the number of issues]
+
+### Thinking Toolkit Index
+- [The thinking toolkits actually used in this review and implementation, and where each was applied]
+
+### Overall Assessment
+- [Whether the objective was met + primary correction path + dual-acceptance gate result]
+```
+
+Notes:
+- The "Implementation direction" in the review section is a brief pointer; the "Implementation plan" in the implementation section is the full elaboration. The two correspond but do not repeat.
+- If a particular issue requires no in-depth implementation (e.g., a pure logical leap that only needs to be pointed out), the implementation section may omit that entry.
+- The "Thinking toolkit index" summarizes the thinking toolkits actually deployed in this review, not a mechanical listing of all of them.
+- The selection of review dimensions varies by problem -- when reviewing paper assumptions, axiomatic thinking is central; when evaluating algorithms, algorithmic/computational thinking + GPU feasibility is central. There is no need to start from assumptions every time.
+
+## Principles
+
+- **Rigorous but not harsh**: Point out problems while providing constructive improvement suggestions.
+- **Specific but not trivial**: Describe issues concretely; avoid vague generalities.
+- **Fair but uncompromising**: Zero tolerance for logical errors, but remain open to innovative ideas.
+- **Dual-gate, no compromise**: Deliverables that are mathematically beautiful but not computable must be marked "unfriendly" and require retrofitting; they must not be approved.
+- **Cross-domain activation first**: Encourage the transfer of modern mathematical structures into algorithm design, but require that the transfer borrows structure, not merely terminology.

package/agents/math-critic.md

@@ -1,5 +1,7 @@
 # 数学审视子 Agent / Math Critic Sub-Agent
 
+> **语言路由**：若用户消息为英文，请读取并遵循 `math-critic.en.md`（同目录），以英文输出审视报告。
+
 ## 角色
 
 你是一个兼具审查与实现能力的数学助手。主要任务是从数学角度评估论点、方案或结论的可靠性与适用性，同时在必要时提供具体的实现思路、解题方案或证明步骤。在 v2 语境下，你还兼任**双验收门把关人**：确保每个产出同时满足「math beautiful × GPU friendly」。

package/commands/abstraction.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when extracting mathematical structures, finding cross-domain commonalities, building general theories, or finding transferable abstract structures for algorithm/operator design. Routes to ../skills/abstraction/SKILL.md.
 ---
 
-读取并遵循 `../skills/abstraction/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/abstraction/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/abstraction/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/algorithmic-thinking.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when a problem needs finite-step solving, algorithm design with complexity/tractability/parallelism analysis, termination/correctness proofs, or designing executable algorithms/operators for GPU. Routes to ../skills/algorithmic-thinking/SKILL.md.
 ---
 
-读取并遵循 `../skills/algorithmic-thinking/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/algorithmic-thinking/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/algorithmic-thinking/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/ask.md

@@ -5,9 +5,7 @@ description: |
   English: Manually invoke the math research activator (weapon selector): when you explicitly want to activate modern mathematics into algorithm/GPU design. Note: pure engineering tasks (debugging, code review, refactoring, tuning) are not suitable for this command.
 ---
 
-读取并遵循 `../skills/math-research-activator/SKILL.md`。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/math-research-activator/SKILL.en.md`；否则读取并遵循 `../skills/math-research-activator/SKILL.md`，按其操作规程输出。
 
 当前问题：
 $ARGUMENTS

package/commands/axiomatization.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when auditing assumptions, building axiom systems, discovering contradictions, verifying consistency/independence/completeness, or defining axioms/invariants for algorithms/operators and checking computability. Routes to ../skills/axiomatization/SKILL.md.
 ---
 
-读取并遵循 `../skills/axiomatization/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/axiomatization/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/axiomatization/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/causal-inference.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when handling correlation≠causation, intervention/counterfactual/do-calculus/causal DAG/confounder/effect estimation, or introducing explicit causal assumptions for interpretability/OOD generalization/DGP modeling. Routes to ../skills/causal-inference/SKILL.md.
 ---
 
-读取并遵循 `../skills/causal-inference/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/causal-inference/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/causal-inference/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/discrete-combinatorial.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when needing to count/enumerate/find patterns in finite structures, handling graph theory/combinatorial structures/generating functions/recurrences, or designing combinatorial schemes for sparse/routing/topological structures. Routes to ../skills/discrete-combinatorial/SKILL.md.
 ---
 
-读取并遵循 `../skills/discrete-combinatorial/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/discrete-combinatorial/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/discrete-combinatorial/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/game-theory.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when optimal strategy depends on others' choices, needing Nash equilibrium/game analysis/mechanism design, or designing strategies for multi-agent/adversarial training/routing games. Routes to ../skills/game-theory/SKILL.md.
 ---
 
-读取并遵循 `../skills/game-theory/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/game-theory/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/game-theory/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/induction-analogy.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when finding patterns from data, doing mathematical induction proofs (weak/strong/structural/transfinite), transferring structures across domains by analogy, or borrowing structures from other fields for algorithm/operator design. Routes to ../skills/induction-analogy/SKILL.md.
 ---
 
-读取并遵循 `../skills/induction-analogy/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/induction-analogy/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/induction-analogy/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/information-theory.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when measuring information value as "information = reduction of uncertainty," computing entropy/mutual information/KL divergence/channel capacity, or designing information criteria for compression/quantization/routing. Routes to ../skills/information-theory/SKILL.md.
 ---
 
-读取并遵循 `../skills/information-theory/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/information-theory/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/information-theory/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/logic-deduction.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when checking proof rigor, doing formal/predicate logic analysis, finding logical loopholes, or doing formal derivation and proof verification for algorithm correctness and invariants. Routes to ../skills/logic-deduction/SKILL.md.
 ---
 
-读取并遵循 `../skills/logic-deduction/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/logic-deduction/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/logic-deduction/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/modeling.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when translating real-world problems into math, building predictive/explanatory models, doing dimensional analysis and model selection, or building computable models for algorithms/operators. Routes to ../skills/modeling/SKILL.md.
 ---
 
-读取并遵循 `../skills/modeling/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/modeling/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/modeling/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/optimization.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when a problem involves trade-offs and extrema under constraints, needs Lagrangian/KKT/duality analysis, or chooses optimization methods for algorithm/operator/training design. Routes to ../skills/optimization/SKILL.md.
 ---
 
-读取并遵循 `../skills/optimization/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/optimization/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/optimization/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/probability-statistics.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when quantifying uncertainty, doing Bayesian inference/hypothesis testing/regression/experimental design, or designing probabilistic mechanisms for random algorithms/sampling/quantization/training dynamics. Routes to ../skills/probability-statistics/SKILL.md.
 ---
 
-读取并遵循 `../skills/probability-statistics/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/probability-statistics/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/probability-statistics/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/symmetry-invariance.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when doing group theory/invariant/Noether's theorem/symmetry-breaking analysis, or designing equivariance/conservation/invariant structures for algorithms. Routes to ../skills/symmetry-invariance/SKILL.md.
 ---
 
-读取并遵循 `../skills/symmetry-invariance/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/symmetry-invariance/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/symmetry-invariance/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/topological-thinking.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when doing topological data analysis/persistent homology/homology and fundamental group computation, or designing connectivity/robustness/cohomology-consistency criteria for algorithms. Routes to ../skills/topological-thinking/SKILL.md.
 ---
 
-读取并遵循 `../skills/topological-thinking/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/topological-thinking/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/topological-thinking/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS

package/commands/transformation.md

@@ -5,9 +5,7 @@ description: |
   English: Trigger when a problem is intractable in its current form and needs a transform into an equivalent simpler problem, or when finding a more GPU-friendly equivalent representation for algorithm/operator design. Routes to ../skills/transformation/SKILL.md.
 ---
 
-读取并遵循 `../skills/transformation/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
-
-如果输入包含 "in English"，请使用英文输出；否则使用中文输出。
+若用户消息为英文，读取并遵循 `../skills/transformation/SKILL.en.md`，按其操作规程输出；否则读取并遵循 `../skills/transformation/SKILL.md`，按其操作规程输出（用于算法/算子/GPU 设计时含 [GPU 可行性] 项）。
 
 当前问题：
 $ARGUMENTS