math-skill 3.0.0 → 3.1.0

package/references/books/smooth-manifolds.md

@@ -1,4 +1,4 @@
-# 🌐 光滑流形 / Smooth Manifolds
+# 光滑流形 / Smooth Manifolds
 
 > **书目**：John M. Lee, *Introduction to Smooth Manifolds*, 2nd Edition. Graduate Texts in Mathematics 218, Springer, 2013. ISBN 978-1-4419-9981-8 / DOI 10.1007/978-1-4419-9982-5. MSC 53-01 / 58-01 / 57-01.
 > **定位**：把"局部像欧氏空间、整体可弯曲"的对象（manifold）配上微积分（切空间、向量场、微分形式、流、李导数），是 **流形优化、隐空间几何、可微结构** 的数学母体。
@@ -16,7 +16,7 @@
 - **Ch 7 Lie Groups**：既是群又是流形（SO(n), U(n), GL(n), Stiefel…），李代数 = 单位元处切空间。→ 正交/酉权重约束、等变。
 - **Ch 8–9 Vector Fields / Integral Curves and Flows**：向量场、积分曲线、流（flow，单参数微分同胚群）、李导数与李括号 [X,Y]。→ **Neural ODE / 扩散 / 连续归一化流** 的母结构。
 - **Ch 10–12 Vector Bundles / Cotangent Bundle / Tensors**：丛、余向量场（1-form）、拉回（pullback）、张量。→ 梯度的真身是余向量。
-- **Ch 13 Riemannian Metrics**：每点内积、长度/距离/体积、切-余切同构（musical ♯/♭，升降指标）。→ **自然梯度 / 黎曼优化的度量来源**。
+- **Ch 13 Riemannian Metrics**：每点内积、长度/距离/体积、切-余切同构（musical (sharp)/(flat)，升降指标）。→ **自然梯度 / 黎曼优化的度量来源**。
 - **Ch 14–16 Differential Forms / Orientations / Integration**：k-形式、楔积、外微分 d（d²=0）、定向、体积形式、流形上积分与变量替换。→ 归一化流的 log-det-Jacobian = 体积形式拉回。
 - **Ch 17–18 De Rham Cohomology / de Rham Theorem**：闭形式模去恰当形式 = 从微分数据读出的拓扑不变量。→ 全局障碍 / 上同调正则。
 - **Ch 19–22 Distributions & Foliations / Exponential Map / Quotient Manifolds / Symplectic Manifolds**：可积分布（Frobenius）、指数映射（retraction 原型）、商流形（Grassmann 等）、辛形式与 Hamilton 流。→ retraction、商空间约束、辛积分器 / HMC。
@@ -25,8 +25,8 @@
 
 ## 可迁移到 AI/Infra 的核心结构
 
-- **切空间 = 参数/隐空间的局部线性化（local linearization）**。`df_p: T_pM → T_{f(p)}N` 就是 Jacobian / pushforward；反向传播 = 沿复合映射做 pushforward（链式法则的几何版）。一切一阶方法都活在切空间里。
-- **梯度是余向量（covector），不是向量**。autodiff 给出的是 1-form（余切空间元素）；要变成可下降的方向（切向量）必须用 **度量升指标**（♯）。欧氏度量 → 普通梯度；Fisher 度量 → 自然梯度（natural gradient）。**这是自然梯度 / 镜像下降的流形根因**。
+- **切空间 = 参数/隐空间的局部线性化（local linearization）**。`df_p: T_pM → T_{f(p)}N` 就是 Jacobian / pushforward（前推，对应 JVP / 前向模式 AD）；反向传播 = 余切丛上的拉回（pullback on cotangent bundle，VJP = 向量-Jacobian 积 = 余向量的拉回），即沿复合映射做 pullback（链式法则的几何版）。一切一阶方法都活在切空间里。
+- **梯度是余向量（covector），不是向量**。autodiff 给出的是 1-form（余切空间元素）；要变成可下降的方向（切向量）必须用 **度量升指标**（(sharp)）。欧氏度量 → 普通梯度；Fisher 度量 → 自然梯度（natural gradient）。**这是自然梯度 / 镜像下降的流形根因**。
 - **约束集 = 子流形（submanifold）**。正则水平集定理：当 g 是 submersion 时 `g(x)=c` 的解集是光滑子流形；约束优化 = 在子流形上做无约束优化。
 - **李群 = 可微的对称群**。SO(n)/U(n)/Stiefel/Grassmann 都是流形；其李代数（如反对称矩阵 so(n)）是线性空间，用 `exp` 映射回群 → **把"约束权重"重参数化为"无约束李代数 + exp"**。
 - **流（flow）= 时间参数化的微分同胚族**。学一个向量场 + 沿它积分 = Neural ODE / 连续归一化流 / 扩散采样。流的可逆性、保体积性直接对应模型性质。
@@ -57,11 +57,11 @@
 
 逐维对照：
 
-- **维度 1–2 张量化 / GEMM**：切空间运算（pushforward/pullback、Jacobian-向量积、把梯度投影到切空间）**天然是 batched GEMM** ✅——反向传播本就是 pushforward，这部分对 GPU 极友好。**但** retraction/exp 多半要 QR、特征分解、矩阵指数或小矩阵求逆：QR/eig **不是干净的 GEMM**，是带串行依赖的分解（cuSOLVER 批量小矩阵尚可，大矩阵 O(n³) 且并行差）→ **可改造** 而非天然友好。
-- **维度 3 复杂度**：测地线距离、平行移动、一般 `log|det J|` 都是 O(n³) 起。**改造**：限定有闭式测地线的流形（球面/双曲/SO(3)）；归一化流用三角/耦合层让 log-det 退化成对角和（O(n)）。
-- **维度 5 低精度**：⚠️ **最大坑**。矩阵 `exp / log / sqrt`、特征分解、SPD 的仿射不变度量在 bf16/fp16 下 **灾难性不稳定**，常静默地需要 fp32/fp64。流形原语经常"表面能跑、数值早已发散"。
-- **维度 6 并行与通信**：scaling-and-squaring 的平方链、ODE 积分步、Householder/QR 都有 **串行递推**，难跨 SM/设备 overlap。反例向好：显式辛积分器（leapfrog）高并行 ✅。
-- **维度 4/7/8 显存 / 稀疏 / 融合**：李代数/旋转参数化若限制在 **小矩阵或块对角**（如逐头旋转、SO(3) 的 Rodrigues 闭式），可融进 kernel、走 Tensor Core；大稠密流形算子则要物化大中间张量。
+- **D1–D2** 切空间运算（pushforward/pullback、Jacobian-向量积、把梯度投影到切空间）**天然是 batched GEMM** [v]——反向传播本就是 pullback（VJP），这部分对 GPU 极友好。**但** retraction/exp 多半要 QR、特征分解、矩阵指数或小矩阵求逆：QR/eig **不是干净的 GEMM**，是带串行依赖的分解（cuSOLVER 批量小矩阵尚可，大矩阵 O(n³) 且并行差）→ **可改造** 而非天然友好。
+- **D3 复杂度**：测地线距离、平行移动、一般 `log|det J|` 都是 O(n³) 起。**改造**：限定有闭式测地线的流形（球面/双曲/SO(3)）；归一化流用三角/耦合层让 log-det 退化成对角和（O(n)）。
+- **D5 低精度**：[~] **最大坑**。矩阵 `exp / log / sqrt`、特征分解、SPD 的仿射不变度量在 bf16/fp16 下 **灾难性不稳定**，常静默地需要 fp32/fp64。流形原语经常"表面能跑、数值早已发散"。
+- **D6 并行与通信**：scaling-and-squaring 的平方链、ODE 积分步、Householder/QR 都有 **串行递推**，难跨 SM/设备 overlap。反例向好：显式辛积分器（leapfrog）高并行 [v]。
+- **D4/D7/D8 显存 / 稀疏 / 融合**：李代数/旋转参数化若限制在 **小矩阵或块对角**（如逐头旋转、SO(3) 的 Rodrigues 闭式），可融进 kernel、走 Tensor Core；大稠密流形算子则要物化大中间张量。
 
 **结论与改造手法（呼应 gpu-friendly-math.md 工具箱）**：
 
@@ -73,11 +73,11 @@
 
 ## 该调用哪个思想透镜
 
-- **optimization（⚖️ 优化思想）**：主武器——约束下寻最优、黎曼/流形优化、retraction 选型。
-- **symmetry（⚛️ 对称与不变性）**：李群、等变、商流形、群作用下的不变量。
+- **variational（变分透镜）**：主透镜——约束下寻最优、黎曼/流形优化、retraction 选型。
+- **symmetry（对称与不变性）**：李群、等变、商流形、群作用下的不变量。
 - **duality（对偶透镜）**：坐标卡变换、pushforward/pullback、归一化流的变量替换、微分同胚。
-- **topological-thinking（🌀 拓扑思想）**：de Rham 上同调、全局障碍、隐空间的"洞"与连通性。
-- **abstraction（🧩 抽象化思想）**：从高维杂乱的环境数据中抽出"局部线性 + 光滑拼接"的流形骨架（流形假设）。
+- **topological（拓扑透镜）**：de Rham 上同调、全局障碍、隐空间的"洞"与连通性。
+- **categorical（范畴化透镜）**：从高维杂乱的环境数据中抽出"局部线性 + 光滑拼接"的流形骨架（流形假设）。
 
 ## 反模式
 
@@ -90,7 +90,7 @@
 
 ## 深挖入口
 
-> **📖 书目信息**：John M. Lee, *Introduction to Smooth Manifolds*, 2nd Edition, Graduate Texts in Mathematics 218, Springer, 2013. ISBN 978-1-4419-9981-8.
+> **书目信息**：John M. Lee, *Introduction to Smooth Manifolds*, 2nd Edition, Graduate Texts in Mathematics 218, Springer, 2013. ISBN 978-1-4419-9981-8.
 >
 > **启用方式**：将 `Introduction to Smooth Manifolds.pdf` 放入项目根目录的 `math_book/` 文件夹，Agent 即可自动搜索原文。PDF 不随 npm/git 分发（版权原因），需自行获取。
 
@@ -98,7 +98,7 @@
 
 - **Ch 3 Tangent Vectors** — 切空间、微分/pushforward、切丛：局部线性化与反传的几何原型。
 - **Ch 11 The Cotangent Bundle** — 余向量场（1-form）、`df` 作为余向量、pullback：梯度真身 = 余向量。
-- **Ch 13 Riemannian Metrics** — 度量、切-余切同构（♯/♭）、距离：自然梯度 / 黎曼优化的根。
+- **Ch 13 Riemannian Metrics** — 度量、切-余切同构（(sharp)/(flat)）、距离：自然梯度 / 黎曼优化的根。
 - **Ch 9 Integral Curves and Flows** — 流、积分曲线、李导数/李括号：Neural ODE / 扩散 / 保结构动力学。
 - **Ch 20 The Exponential Map** — 指数映射：retraction 原型，也是 GPU 可行性的主瓶颈。
 

package/references/gpu-friendly-math.en.md

@@ -1,9 +1,35 @@
 # GPU-Friendly Math Checklist
 
 > This file is the **single source of truth** for the "GPU-feasibility" acceptance gate.
-> The activator, the 15 thinking lenses, `books/*.md`, and `../agents/math-critic.md` all reference this file; no duplicate definitions elsewhere.
->
-> This file is the single source of truth for the "GPU-feasibility" acceptance gate. The activator, the 15 thinking lenses, the book references, and the math-critic all point here.
+> The activator, the 15 thinking lenses, `books/*.md`, and `../agents/math-critic.en.md` all reference this file; no duplicate definitions elsewhere.
+
+## Eight-Dimension Abbreviations
+
+| Abbrev. | Full Name |
+|---------|-----------|
+| D1 | Tensorization |
+| D2 | GEMM-mappability |
+| D3 | Complexity |
+| D4 | Memory & KV-Cache |
+| D5 | Low-precision stability |
+| D6 | Parallelism & communication |
+| D7 | Sparse structure |
+| D8 | Operator fusion |
+
+## Quantitative Checklist
+
+When evaluating each dimension, provide concrete numbers rather than just labels:
+
+| Dimension | Quantitative Questions to Answer |
+|-----------|--------------------------------|
+| D1 Tensorization | What are the tensor shapes of core operations? Where is the batch dimension? |
+| D2 GEMM-mappability | How many GEMM/matmul operations? What are the (M,N,K) dimensions of each? |
+| D3 Complexity | Total FLOPs? Ratio vs. baseline (standard attention/MLP)? |
+| D4 Memory | Peak memory (bytes)? Is an n×n matrix materialized? KV-Cache overhead? |
+| D5 Low-precision | Numerical error magnitude under bf16/fp8? Mixed-precision strategy needed? |
+| D6 Parallelism | Theoretical parallelism degree? Communication volume (bytes/step)? All-reduce required? |
+| D7 Sparsity | Sparsity ratio (%)? Sparse format (CSR/BSR/block-sparse)? Dedicated kernel available? |
+| D8 Operator Fusion | Number of fusible kernels? Reduction in kernel launches and memory transfers after fusion? |
 
 ## Core Proposition
 
@@ -18,7 +44,7 @@ Many "beautiful on paper" modern mathematical structures cannot run at high perf
 
 For any candidate structure (operator, attention variant, routing mechanism, regularization term, compression scheme…) rate each dimension as `Friendly / Retrofittable / Unfriendly` and provide adaptation recommendations.
 
-| # | Dimension | Key Question | Friendly ✅ | Unfriendly ❌ |
+| # | Dimension | Key Question | Friendly [v] | Unfriendly [x] |
 |---|-----------|-------------|------------|--------------|
 | 1 | **Tensorization** | Can it be expressed as dense tensor operations, avoiding element-wise irregular control flow? | Batched tensor algebra | Scalar loops, data-dependent branches |
 | 2 | **GEMM-mappability** | Can it be reduced to matrix multiplication / batched GEMM / convolution to fully utilize Tensor Cores? | Expressible as a GEMM chain | Irregular computations that cannot be expressed as matrix operations |
@@ -53,13 +79,13 @@ Common techniques for transforming "beautiful but non-computable" into "both bea
 
 ## Worked Example: Tropical Sheaf Attention
 
-Drawn from the auto-research directions cited in `agentic-workflow.md`, demonstrating how a **candidate design enters the 8-dimension verification**:
+Drawn from the auto-research directions cited in `agentic-workflow.en.md`, demonstrating how a **candidate design enters the 8-dimension verification**:
 
 | Component | Mathematical Source | GPU Friendliness |
 |-----------|-------------------|-----------------|
-| Tropical Gating | Tropical semiring, piecewise-linear | Replaces Top-K: element-wise max-plus — dim 1 ✅ Tensorization / dim 2 ❌ Not a Tensor Core GEMM (runs on CUDA cores) / dim 3 ✅ Per-token gating only, sub-quadratic (min-plus matmul is APSP-hard, not sub-quadratic); sub-differentiable, kinks require LogSumExp smoothing (smoothing recovers standard softmax) |
-| Cellular Sheaf Diffusion | Algebraic geometry / topology (sheaves, restriction maps) | Each edge is a low-rank linear transform = small GEMM (dim 2/4) |
-| Čech Cohomology Regularization | Algebraic topology (first cohomology $H^1$) | Local, inexpensive; serves as an algebraic criterion for hallucination (dim 3/8) |
-| Low-Rank Basis KV Compression (Plücker/Grassmannian perspective) | Projective geometry | Store the basis rather than Plücker coordinates (the latter expands when low-rank); block-summary candidate — compression ratio / error / throughput must be benchmarked (dim 4) |
+| Tropical Gating | Tropical semiring, piecewise-linear | Replaces Top-K: element-wise max-plus — D1[v] / D2[x] Not a Tensor Core GEMM (runs on CUDA cores) / D3[v] Per-token gating only, sub-quadratic (min-plus matmul is APSP-hard, not sub-quadratic); sub-differentiable, kinks require LogSumExp smoothing (smoothing recovers standard softmax) |
+| Cellular Sheaf Diffusion | Algebraic geometry / topology (sheaves, restriction maps) | Each edge is a low-rank linear transform = small GEMM (D2/D4) |
+| Čech Cohomology Regularization | Algebraic topology (first cohomology $H^1$) | Local, inexpensive; serves as an algebraic criterion for hallucination (D3/D8) |
+| Low-Rank Basis KV Compression (Plücker/Grassmannian perspective) | Projective geometry | Store the basis rather than Plücker coordinates (the latter expands when low-rank); block-summary candidate — compression ratio / error / throughput must be benchmarked (D4) |
 
 Do not treat the table above as validated conclusions. The correct approach is to enter each component into the test plan: prove or estimate complexity, measure peak memory and throughput, check bf16/fp8 stability, and confirm whether it can be mapped to GEMM / batched GEMM / fused kernels. Only after both empirical benchmarks and theoretical derivations pass should a component be labeled "math beautiful × GPU friendly."

package/references/gpu-friendly-math.md

@@ -7,6 +7,34 @@
 >
 > This file is the single source of truth for the "GPU-feasibility" acceptance gate. The activator, the 15 thinking lenses, the book references, and the math-critic all point here.
 
+## 八维缩写速查
+
+| 缩写 | 全称 |
+|------|------|
+| D1 | 张量化 |
+| D2 | GEMM 可映射 |
+| D3 | 复杂度 |
+| D4 | 显存与 KV-Cache |
+| D5 | 低精度稳定 |
+| D6 | 并行与通信 |
+| D7 | 稀疏结构 |
+| D8 | 算子融合 |
+
+## 量化检查清单
+
+评估每个维度时，应填写具体数值而非仅给标签：
+
+| 维度 | 需回答的量化问题 |
+|------|----------------|
+| D1 张量化 | 核心操作的 tensor shape 是什么？batch 维在哪？ |
+| D2 GEMM 可映射 | 操作可分解为几次 GEMM/matmul？每次的 (M,N,K) 是多少？ |
+| D3 复杂度 | FLOPs 总量？与 baseline (标准 attention/MLP) 的比值？ |
+| D4 显存 | 峰值显存 (bytes)？是否物化 n×n 矩阵？KV-Cache 额外开销？ |
+| D5 低精度 | bf16/fp8 下的数值误差量级？是否需要混合精度策略？ |
+| D6 并行 | 理论并行度？通信量 (bytes/step)？是否需要 all-reduce？ |
+| D7 稀疏 | 稀疏度 (%)？稀疏格式 (CSR/BSR/block-sparse)？是否有专用 kernel？ |
+| D8 算子融合 | 可融合的 kernel 数？融合后减少的 kernel launch 次数和显存搬运量？ |
+
 ## 核心命题 / Core Proposition
 
 **数学美 ≠ 可算。** 一个结构要真正进入现代 GPU 集群的训练与推理，必须同时满足两件事：
@@ -20,7 +48,7 @@
 
 对任何候选结构（算子、注意力变体、路由、正则项、压缩方案……）逐项评 `友好 / 可改造 / 不友好`，并给出改造建议。
 
-| # | 维度 | 关键问题 | 友好 ✅ | 不友好 ❌ |
+| # | 维度 | 关键问题 | 友好 [v] | 不友好 [x] |
 |---|------|---------|--------|----------|
 | 1 | **张量化 / Tensorization** | 能否表达为稠密张量运算，避免逐元素不规则控制流？ | 批量张量代数 | 标量循环、数据相关分支 |
 | 2 | **GEMM 可映射 / GEMM mappability** | 能否落到 矩阵乘 / batched GEMM / 卷积，吃满 Tensor Core？ | 可写成 GEMM 链 | 无法矩阵化的不规则运算 |
@@ -59,9 +87,9 @@
 
 | 组件 | 数学来源 | GPU 友好性 |
 |------|---------|-----------|
-| 热带门控 Tropical Gating | 热带半环分段线性 | 替代 Top-K：逐元素 max-plus——dim 1 ✅ 张量化 / dim 2 ❌ 非 Tensor Core GEMM（落 CUDA core）/ dim 3 ✅ 仅逐 token 门控亚二次（min-plus matmul 则 APSP-hard 非亚二次）；次可微，折点需 LogSumExp 软化（软化退回标准 softmax）|
-| 胞腔层扩散 Cellular Sheaf Diffusion | 代数几何/拓扑（层、限制映射）| 每边低秩线性变换 = 小 GEMM（维度 2/4）|
-| Čech 上同调正则 | 代数拓扑（一阶上同调 H¹）| 局部、廉价；作幻觉的代数判据（维度 3/8）|
-| 低秩基底 KV 压缩（Plücker/Grassmannian 视角） | 射影几何 | 存基底而非 Plücker 坐标（后者低秩时反扩张）；块摘要候选，压缩率/误差/吞吐需实测（维度 4）|
+| 热带门控 Tropical Gating | 热带半环分段线性 | 替代 Top-K：逐元素 max-plus——D1[v] / D2[x] 非 Tensor Core GEMM（落 CUDA core）/ D3[v] 仅逐 token 门控亚二次（min-plus matmul 则 APSP-hard 非亚二次）；次可微，折点需 LogSumExp 软化（软化退回标准 softmax）|
+| 胞腔层扩散 Cellular Sheaf Diffusion | 代数几何/拓扑（层、限制映射）| 每边低秩线性变换 = 小 GEMM（D2/D4）|
+| Čech 上同调正则 | 代数拓扑（一阶上同调 H¹）| 局部、廉价；作幻觉的代数判据（D3/D8）|
+| 低秩基底 KV 压缩（Plücker/Grassmannian 视角） | 射影几何 | 存基底而非 Plücker 坐标（后者低秩时反扩张）；块摘要候选，压缩率/误差/吞吐需实测（D4）|
 
 使用时不要把上表当作已验证结论。正确做法是把每个组件写进 testplan：证明或估计复杂度，测峰值显存和吞吐，检查 bf16/fp8 稳定性，确认能否落到 GEMM / batched GEMM / fused kernel。只有实测和推导都通过后，才标为 "math beautiful × GPU friendly"。

package/references/skill-index.en.md

@@ -0,0 +1,105 @@
+# Skill Index: Lens Library, Knowledge Base, Design Pattern Library, Workflow Examples
+
+> This file is extracted from `../skills/math-research-activator/SKILL.en.md` for reference when the full catalogs are needed. SKILL.en.md retains condensed summaries with links to this file.
+
+## Language Routing & Mixed-Input Rules (Full Version)
+
+Language routing only determines "which language version to read" and "what language to respond in." It does NOT affect whether the math system triggers or the A/B/C/D/E scenario classification.
+
+### Decision Rules
+
+1. **Judge the natural-language frame first**
+   - If the user's sentence structure, verbs, and mood particles are primarily Chinese, treat as Chinese even if English technical terms are interspersed.
+   - E.g., "帮我 design 一个 attention" / "这个 loss 有没有理论问题" / "能不能用 manifold 做 routing" → Chinese.
+
+2. **English technical terms do not count as English primary language**
+   - attention, loss, routing, embedding, manifold, operator, kernel, KV-cache, transformer, MoE, and similar AI/math/engineering terms are domain terms and do not trigger a switch to English.
+
+3. **Code, paths, and formulas are excluded from language detection**
+   - File paths, function names, variable names, LaTeX formulas, and CLI arguments do not count toward language ratio.
+
+4. **When primary language is unclear, follow the user's last clear language**
+   - If the CN/EN ratio is close and indeterminate, use the user's most recent unambiguous natural language.
+   - If there is no prior context, default to Chinese.
+
+5. **Output language matches primary language**
+   - Chinese primary → read `../skills/math-research-activator/SKILL.md`, respond in Chinese, retaining necessary English terms.
+   - English primary → read `../skills/math-research-activator/SKILL.en.md`, respond in English.
+   - If the user explicitly requests "in English" / "in Chinese," follow the explicit request.
+
+## Lens Library (15 Mathematical Perspectives)
+
+Each lens answers: What is this perspective? What kinds of problems is it suited to diagnose? Which knowledge domains does it route to?
+
+| Lens | File | Core Perspective |
+|------|------|-----------------|
+| Axiomatization | `../lenses/axiomatization.en.md` | Examine consistency/independence/completeness of assumptions |
+| Duality | `../lenses/duality.en.md` | Transform to the dual space to expose constraints and invariants |
+| Symmetry | `../lenses/symmetry.en.md` | Invariants and conservation laws under transformations |
+| Spectral Decomposition | `../lenses/spectral.en.md` | Eigenvalues/singular values reveal dominant structure |
+| Geometric | `../lenses/geometric.en.md` | Metric/curvature/spatial structure on manifolds |
+| Projection & Decomposition | `../lenses/projection.en.md` | Orthogonal decomposition, subspace separation, conflict elimination |
+| Variational | `../lenses/variational.en.md` | Constrained extrema, energy minimization |
+| Local-to-Global | `../lenses/local-to-global.en.md` | Patching local properties into global ones, cohomological obstructions |
+| Topological | `../lenses/topological.en.md` | Invariants under continuous deformation, connectedness, holes |
+| Categorical | `../lenses/categorical.en.md` | Universal properties, functors, natural transformations |
+| Perturbation | `../lenses/perturbation.en.md` | Propagation of small perturbations, stability, robustness |
+| Causal | `../lenses/causal.en.md` | Correlation ≠ causation, interventions, counterfactuals |
+| Game-Theoretic | `../lenses/game.en.md` | Multi-agent strategic interaction, equilibria, mechanism design |
+| Probabilistic & Statistical | `../lenses/probabilistic.en.md` | Quantifying uncertainty, Bayesian updating |
+| Algorithmic | `../lenses/algorithmic.en.md` | Complexity, feasibility, parallelizability |
+
+## Knowledge Base (Organized by Mathematical Domain)
+
+Each knowledge card answers: Minimal definition, core formulas, applicable problems, AI design translation, engineering feasibility, risks.
+
+| Domain | Directory | Knowledge Cards |
+|--------|-----------|----------------|
+| Matrix Analysis | `../knowledge-base/matrix-analysis/` | projection, spectral-decomposition, low-rank-approximation, positive-semidefinite, matrix-perturbation |
+| Optimization | `../knowledge-base/optimization/` | lagrangian-duality, convex-optimization, constrained-optimization, riemannian-optimization, proximal-method |
+| Differential Geometry | `../knowledge-base/differential-geometry/` | manifold, tangent-space, metric-tensor, geodesic, curvature, connection |
+| Lie Theory | `../knowledge-base/lie-theory/` | group-action, lie-group, lie-algebra, representation, equivariance |
+| Topology | `../knowledge-base/topology/` | persistent-homology, euler-characteristic, fundamental-group |
+| Probability & Information | `../knowledge-base/probability/` | concentration-inequality, entropy, kl-divergence, information-bottleneck, fisher-information |
+| Information Geometry | `../knowledge-base/information-geometry/` | natural-gradient, fisher-metric |
+
+## Design Pattern Library (Organized by AI Component)
+
+Each design pattern answers: Mathematical origin, AI module form, implementable architecture, GPU feasibility, paper-level exposition, risks.
+
+| Component Type | Directory | Patterns |
+|---------------|-----------|----------|
+| Attention | `../design-patterns/attention/` | projection-attention, spectral-attention, equivariant-attention, geometry-aware-attention, information-bottleneck-attention |
+| Loss Functions | `../design-patterns/loss/` | orthogonality-loss, contrastive-loss, variational-loss, information-bottleneck-loss, constraint-penalty |
+| Routing | `../design-patterns/routing/` | optimal-transport-routing, graph-routing, moe-routing, spectral-clustering-routing |
+| Representation | `../design-patterns/representation/` | shared-private-decomposition, manifold-representation, equivariant-split, subspace-alignment |
+| Compression | `../design-patterns/compression/` | low-rank-kv-cache, spectral-token-pruning, topology-preserving-compression, leverage-score-selection |
+
+## Workflow Example
+
+**User**: "Design a new KV Cache compression method that preserves long-range dependencies — I don't want to just do top-k."
+
+```
+Step 1 — Diagnosis: Scenario B (Mechanism Design)
+  Problem type: Sequence memory compression + information preservation + long-range structure
+  Core tension: Compressing token count vs. preserving long-range dependencies
+
+Step 2 — Lens Selection:
+  1. Spectral Decomposition (preserve dominant subspace)
+  2. Information Theory (retain states with maximum mutual information)
+  3. Topological (preserve critical connectivity points of sequential structure)
+
+Step 3 — Knowledge Query:
+  → low-rank-approximation (Matrix Analysis)
+  → leverage-score-selection (Design Pattern: compression)
+  → information-bottleneck (Probability & Information)
+
+Step 4 — Design Translation:
+  Candidate A: Spectral KV Compression (low-rank + leverage score)
+  Candidate B: Information-Preserving Cache (query sensitivity)
+  Candidate C: Topology-Preserving Cache (graph bridge-node retention)
+
+Step 5 — Critic Review:
+  A is most GPU-friendly; B requires estimating future queries with inherent uncertainty; C has prohibitive graph construction cost
+  Recommendation: Prioritize A; use B as a lightweight gate
+```

package/references/skill-index.md

@@ -0,0 +1,105 @@
+# Skill 索引：透镜库、知识库、设计模式库、工作流范例
+
+> 本文件从 `../skills/math-research-activator/SKILL.md` 提取，供需要查阅完整目录时使用。SKILL.md 保留精简摘要和指向本文件的链接。
+
+## 语言路由与混合输入规则（完整版）
+
+语言路由只决定"读取哪个语言版本的说明"和"最终用什么语言回答"，不参与数学系统是否触发、也不参与 A/B/C/D/E 场景判断。
+
+### 判定规则
+
+1. **先判断自然语言主框架**
+   - 如果用户的请求句式、动词、语气词主要是中文，即使夹杂英文技术词，也按中文处理。
+   - 例如："帮我 design 一个 attention""这个 loss 有没有理论问题""能不能用 manifold 做 routing"均按中文处理。
+
+2. **英文技术词不计入英文主语言**
+   - attention、loss、routing、embedding、manifold、operator、kernel、KV-cache、transformer、MoE 等 AI/数学/工程术语视为领域术语，不作为切换到英文的依据。
+
+3. **代码、路径、公式不参与语言判定**
+   - 文件路径、函数名、变量名、LaTeX 公式、命令行参数不计入语言比例。
+
+4. **主语言不明显时，沿用用户上一轮主要语言**
+   - 若中英文比例接近且无法判断，以用户最近一次明确使用的自然语言为准。
+   - 若没有上下文，默认中文。
+
+5. **输出语言与主语言一致**
+   - 中文主语言 → 读取中文 `../skills/math-research-activator/SKILL.md`，用中文回答，保留必要英文术语。
+   - 英文主语言 → 读取 `../skills/math-research-activator/SKILL.en.md`，用英文回答。
+   - 用户明确要求"用英文/用中文"时，以用户显式要求为准。
+
+## 透镜库（15 个数学视角）
+
+每个透镜回答：这是什么视角？适合诊断什么问题？会路由到哪些知识域？
+
+| 透镜 | 文件 | 核心视角 |
+|------|------|---------|
+| 公理化 | `../lenses/axiomatization.md` | 审查假设的相容性/独立性/完备性 |
+| 对偶 | `../lenses/duality.md` | 转换到对偶空间暴露约束与不变量 |
+| 对称性 | `../lenses/symmetry.md` | 变换下的不变量与守恒律 |
+| 谱分解 | `../lenses/spectral.md` | 特征值/奇异值揭示主导结构 |
+| 几何 | `../lenses/geometric.md` | 度量/曲率/流形上的空间结构 |
+| 投影与分解 | `../lenses/projection.md` | 正交分解、子空间分离、冲突消除 |
+| 变分 | `../lenses/variational.md` | 约束下极值、能量最小化 |
+| 局部到整体 | `../lenses/local-to-global.md` | 局部性质拼接为全局、层上同调障碍 |
+| 拓扑 | `../lenses/topological.md` | 连续变形不变量、连通性、空洞 |
+| 范畴化 | `../lenses/categorical.md` | 泛性质、函子、自然变换 |
+| 扰动 | `../lenses/perturbation.md` | 小扰动的传播、稳定性、鲁棒性 |
+| 因果 | `../lenses/causal.md` | 相关≠因果、干预、反事实 |
+| 博弈 | `../lenses/game.md` | 多方策略互动、均衡、机制设计 |
+| 概率统计 | `../lenses/probabilistic.md` | 量化不确定性、贝叶斯更新 |
+| 算法 | `../lenses/algorithmic.md` | 复杂度、可行性、并行性 |
+
+## 知识库（按数学领域组织）
+
+每个知识卡片回答：最小定义、核心公式、适用问题、AI 设计翻译、工程可行性、风险。
+
+| 领域 | 目录 | 知识卡片 |
+|------|------|---------|
+| 矩阵分析 | `../knowledge-base/matrix-analysis/` | projection, spectral-decomposition, low-rank-approximation, positive-semidefinite, matrix-perturbation |
+| 最优化 | `../knowledge-base/optimization/` | lagrangian-duality, convex-optimization, constrained-optimization, riemannian-optimization, proximal-method |
+| 微分几何 | `../knowledge-base/differential-geometry/` | manifold, tangent-space, metric-tensor, geodesic, curvature, connection |
+| 李理论 | `../knowledge-base/lie-theory/` | group-action, lie-group, lie-algebra, representation, equivariance |
+| 拓扑 | `../knowledge-base/topology/` | persistent-homology, euler-characteristic, fundamental-group |
+| 概率与信息 | `../knowledge-base/probability/` | concentration-inequality, entropy, kl-divergence, information-bottleneck, fisher-information |
+| 信息几何 | `../knowledge-base/information-geometry/` | natural-gradient, fisher-metric |
+
+## 设计模式库（按 AI 组件组织）
+
+每个设计模式回答：数学来源、AI 模块形式、可实现结构、GPU 可行性、论文表述、风险。
+
+| 组件类型 | 目录 | 模式 |
+|---------|------|------|
+| 注意力 | `../design-patterns/attention/` | projection-attention, spectral-attention, equivariant-attention, geometry-aware-attention, information-bottleneck-attention |
+| 损失函数 | `../design-patterns/loss/` | orthogonality-loss, contrastive-loss, variational-loss, information-bottleneck-loss, constraint-penalty |
+| 路由 | `../design-patterns/routing/` | optimal-transport-routing, graph-routing, moe-routing, spectral-clustering-routing |
+| 表示 | `../design-patterns/representation/` | shared-private-decomposition, manifold-representation, equivariant-split, subspace-alignment |
+| 压缩 | `../design-patterns/compression/` | low-rank-kv-cache, spectral-token-pruning, topology-preserving-compression, leverage-score-selection |
+
+## 工作流范例
+
+**用户**："设计新的 KV Cache 压缩方法，保留长期依赖，不想只做 top-k"
+
+```
+第一步 诊断：场景 B（机制设计）
+  问题类型：序列记忆压缩 + 信息保留 + 长程结构
+  核心张力：压缩 token 数量 vs 不破坏长期依赖
+
+第二步 透镜选择：
+  1. 谱分解（保留主导子空间）
+  2. 信息论（保留最大互信息状态）
+  3. 拓扑（保留序列结构关键连接点）
+
+第三步 知识查询：
+  → low-rank-approximation（矩阵分析）
+  → leverage-score-selection（设计模式：压缩）
+  → information-bottleneck（概率与信息）
+
+第四步 设计翻译：
+  候选 A：Spectral KV Compression（低秩 + leverage score）
+  候选 B：Information-Preserving Cache（query sensitivity）
+  候选 C：Topology-Preserving Cache（图桥接节点保留）
+
+第五步 Critic 审查：
+  A 最 GPU 友好，B 需估计未来 query 有不确定性，C 图构建成本过高
+  建议：优先 A，B 作轻量 gate
+```