math-skill 3.0.1 → 3.1.0

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

@@ -1,9 +1,7 @@
 # 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
 
@@ -18,6 +16,21 @@
 | 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
 
 **Mathematical beauty ≠ computability.** For a structure to truly enter training and inference on modern GPU clusters, it must simultaneously satisfy two requirements:
@@ -66,13 +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 [v] Tensorization / dim 2 [x] Not a Tensor Core GEMM (runs on CUDA cores) / dim 3 [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 (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

@@ -20,6 +20,21 @@
 | 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：
@@ -72,9 +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 [v] 张量化 / dim 2 [x] 非 Tensor Core GEMM（落 CUDA core）/ dim 3 [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（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
+```

package/skills/math-research-activator/SKILL.en.md

@@ -5,32 +5,7 @@ description: |
 ---
 
 
-> **File routing**: When this document references any file (lenses, knowledge-base, design-patterns, references, agents), always load the `.en.md` variant if it exists. For example, `../../lenses/symmetry.md` → load `lenses/symmetry.en.md`.
->
-> ## Language Routing & Mixed-Input Rules
->
-> 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" → Chinese.
->
-> 2. **English technical terms do not count as English primary language**
->    - attention, loss, routing, embedding, manifold, operator, kernel, KV-cache, transformer, MoE, etc. 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 `SKILL.md`, respond in Chinese, retaining necessary English terms.
->    - English primary → read `SKILL.en.md`, respond in English.
->    - If the user explicitly requests "in English" / "in Chinese," follow the explicit request.
+> **Language Routing & Mixed-Input Rules**: Judge primary language by sentence structure/verbs/mood particles. AI/math/engineering terms don't count. Code/paths/formulas excluded. When CN/EN ratio is close, follow last turn; default to Chinese if no context. Explicit request overrides. Chinese → `SKILL.md`, English → this file. Full rules: `../../references/skill-index.en.md`.
 
 # Math Research OS
 
@@ -38,18 +13,26 @@ description: |
 
 This system is a mathematical staff office for AI architecture innovation — not an arsenal, but one that tells you: **what kind of battle this is, which arms to deploy, how to deploy them, and where things could go wrong.**
 
+## Core Principle
+
+> Math Skill does not store mathematics. It activates, routes, and translates mathematics for AI research.
+
+- **knowledge-base/** is not a closed encyclopedia but a set of mathematical activation anchors
+- When existing cards cannot cover a problem, the agent must NOT stop or force-fit; instead, generate a "temporary knowledge card" based on lenses, reference layers, and the agent's own mathematical knowledge, then continue with design translation
+- **design-patterns/** is a collection of math→AI translation prototypes, not a complete model repository; when no matching pattern exists, generate a temporary design candidate from the mathematical structure and label it as a temporary design pattern
+
 ## Three-Layer Orthogonal Architecture
 
 | Layer | Responsibility | Directory | Core Question |
 |-------|---------------|-----------|--------------|
-| **Thinking Lenses** | Diagnose problem structure, recommend mathematical perspectives | `../../lenses/*.md` | Which perspective should we view this problem through? |
-| **Math Knowledge** | Provide concrete mathematical tools (definitions/theorems/formulas) | `../../knowledge-base/*/*.md` | What specific mathematics does this perspective require? |
-| **Design Translation** | Translate mathematics into AI modules/losses/operators | `../../design-patterns/*/*.md` | How does this mathematics become model architecture? |
+| **Thinking Lenses** | Diagnose problem structure, recommend mathematical perspectives | `../../lenses/*.en.md` | Which perspective should we view this problem through? |
+| **Math Knowledge** | Provide concrete mathematical tools (definitions/theorems/formulas) | `../../knowledge-base/*/*.en.md` | What specific mathematics does this perspective require? |
+| **Design Translation** | Translate mathematics into AI modules/losses/operators | `../../design-patterns/*/*.en.md` | How does this mathematics become model architecture? |
 
 Auxiliary layers:
-- `../../references/books/*.md`: Distilled notes from 7 textbooks; full context when deeper understanding is needed
-- `../../references/gpu-friendly-math.md`: GPU Eight-Dimension Acceptance Gate (single source of truth)
-- `../../agents/math-critic.md`: Math-engineering dual critic
+- `../../references/books/*.en.md`: Distilled notes from 7 textbooks; full context when deeper understanding is needed
+- `../../references/gpu-friendly-math.en.md`: GPU Eight-Dimension Acceptance Gate (single source of truth)
+- `../../agents/math-critic.en.md`: Math-engineering dual critic
 
 ## Intent Diagnosis (5 Scenarios)
 
@@ -58,56 +41,20 @@ Auxiliary layers:
 | **A. Problem Analysis** | "Is this design sound?" "Are there gaps in the reasoning chain?" | Lenses → critic |
 | **B. Mechanism Design** | "Design a new attention mechanism" "Transfer X to Y" | Lenses → Knowledge → Design → critic |
 | **C. Knowledge Query** | "What is a tangent space on a manifold?" "How is the projection theorem applied?" | Knowledge |
-| **D. Verification & Review** | "Does this formula hold?" "What guarantees does this loss provide?" | Knowledge → critic |
+| **D. Verification & Review** | "Does this formula hold?" "What guarantees does this loss provide?" | Knowledge → relevant design patterns (if a concrete AI construct is cited) → critic |
 | **E. Pure Engineering** | Debugging, refactoring, hyperparameter tuning, code review | **Do not invoke the math system** |
 
 ## 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.md` | Examine consistency/independence/completeness of assumptions |
-| Duality | `../../lenses/duality.md` | Transform to the dual space to expose constraints and invariants |
-| Symmetry | `../../lenses/symmetry.md` | Invariants and conservation laws under transformations |
-| Spectral Decomposition | `../../lenses/spectral.md` | Eigenvalues/singular values reveal dominant structure |
-| Geometric | `../../lenses/geometric.md` | Metric/curvature/spatial structure on manifolds |
-| Projection & Decomposition | `../../lenses/projection.md` | Orthogonal decomposition, subspace separation, conflict elimination |
-| Variational | `../../lenses/variational.md` | Constrained extrema, energy minimization |
-| Local-to-Global | `../../lenses/local-to-global.md` | Patching local properties into global ones, cohomological obstructions |
-| Topological | `../../lenses/topological.md` | Invariants under continuous deformation, connectedness, holes |
-| Categorical | `../../lenses/categorical.md` | Universal properties, functors, natural transformations |
-| Perturbation | `../../lenses/perturbation.md` | Propagation of small perturbations, stability, robustness |
-| Causal | `../../lenses/causal.md` | Correlation ≠ causation, interventions, counterfactuals |
-| Game-Theoretic | `../../lenses/game.md` | Multi-agent strategic interaction, equilibria, mechanism design |
-| Probabilistic & Statistical | `../../lenses/probabilistic.md` | Quantifying uncertainty, Bayesian updating |
-| Algorithmic | `../../lenses/algorithmic.md` | Complexity, feasibility, parallelizability |
+15 lenses covering: Axiomatization, Duality, Symmetry, Spectral Decomposition, Geometric, Projection & Decomposition, Variational, Local-to-Global, Topological, Categorical, Perturbation, Causal, Game-Theoretic, Probabilistic & Statistical, Algorithmic. Directory: `../../lenses/*.en.md`. Full catalog table: `../../references/skill-index.en.md`.
 
 ## 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 |
+7 domains: Matrix Analysis, Optimization, Differential Geometry, Lie Theory, Topology, Probability & Information, Information Geometry. Directory: `../../knowledge-base/*/*.en.md`. Full catalog table: `../../references/skill-index.en.md`.
 
 ## 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 |
+5 component types: Attention, Loss Functions, Routing, Representation, Compression. Directory: `../../design-patterns/*/*.en.md`. Full catalog table: `../../references/skill-index.en.md`.
 
 ## Automatic Trigger Conditions
 
@@ -138,76 +85,87 @@ The user's intent matches one of scenarios A/B/C/D. Pure engineering tasks match
 
 ```
 Scenario A (Analysis): Select 1–3 lenses → output perspective diagnosis → critic review
-Scenario B (Design): Select 1–3 lenses → query knowledge cards → generate design patterns → critic review
-Scenario C (Query): Load knowledge cards directly → output per knowledge activation protocol
-Scenario D (Verification): Load knowledge cards → critic reviews conditions and boundaries
+Scenario B (Design): Select 1–3 lenses → invoke relevant activation anchors; if no coverage, enter Knowledge Gap Protocol → generate formal/temporary design patterns → critic review
+Scenario C (Query): Prefer loading relevant activation anchors; if no coverage, generate temporary knowledge card → output per knowledge activation protocol
+Scenario D (Verification): Load relevant anchors or temporary knowledge cards → critic reviews conditions and boundaries
 Scenario E (Engineering): No intervention
 ```
 
 ### Step 3: Output Format
 
+**Token-economy rule**: The following is the maximum structure, not the default full template. Trim to the user's question; for simple knowledge queries, provide only the needed definition / formula / risk. Expand design and GPU sections only when relevant, and do not restate loaded cards verbatim.
+
 **Scenario A/B Output**:
 1. **[Diagnosis]** Problem type + core tension
 2. **[Lens]** Recommend 1–3 mathematical perspectives (annotate why each is/is not suitable)
-3. **[Knowledge]** (Scenario B only) Required concrete mathematical tools (reference knowledge cards)
-4. **[Design]** (Scenario B only) Candidate AI module drafts (reference design patterns)
+3. **[Knowledge]** (Scenario B only) Activated mathematical structures (reference activation anchors or temporary knowledge cards)
+4. **[Design]** (Scenario B only) Candidate AI module drafts (reference design patterns or temporary design drafts)
 5. **[GPU]** Run candidates through the Eight-Dimension Gate (friendly/retrofittable/unfriendly)
 6. **[Conclusion]** Retain candidates that pass both acceptance gates + next-step recommendations
 
-**Scenario C Output** (Knowledge Activation Protocol):
+**Scenario C Output** (Knowledge Activation Protocol, trimmed as needed):
 1. Minimal definition
 2. Core formulas
 3. Applicable problems
-4. AI design translation
-5. Engineering feasibility
+4. AI design translation (only when the question involves AI / operators)
+5. Engineering feasibility (only when implementation / GPU matters)
 6. Risks and failure conditions
-7. Further references (distilled book notes / original book paths)
+7. Further references (only when traceability is requested or the conclusion depends on book references)
 
-**Scenario D Output**:
+**Scenario D Output** (short conclusion first + conditions/boundaries):
 1. Conditions under which it holds
 2. Conditions under which it fails
 3. What it can guarantee at most
 4. What it cannot guarantee
-5. Engineering feasibility
+5. Engineering feasibility (only when implementation / GPU matters)
 
 **A conclusion must always be provided — never output analysis alone without convergence.**
 
 ## GPU Eight-Dimension Acceptance Gate
 
-Formal terminology (single authoritative source: `../../references/gpu-friendly-math.md`):
+Formal terminology (single authoritative source: `../../references/gpu-friendly-math.en.md`):
 **Tensorization / GEMM-mappability / Complexity / Memory & KV-Cache / Low-Precision Stability / Parallelism & Communication / Sparse Structure / Operator Fusion**
 
+**Quantitative assessment requirements**: For each candidate design, the GPU assessment should not only provide [v]/[~]/[x] labels but also answer:
+1. FLOPs of core operations and ratio vs. baseline
+2. Peak memory (bytes), whether large matrices are materialized
+3. Numerical stability strategy under bf16/fp8
+4. Number of fusible kernels and expected speedup
+
+See the quantitative checklist in `../../references/gpu-friendly-math.en.md`.
+
 ## Depth-of-Consultation Protocol
 
-- **Light**: Read knowledge cards (`../../knowledge-base/*/*.md`); self-contained and immediately usable
-- **Medium**: Read distilled book notes (`../../references/books/*.md`) for more complete context
+- **Light**: Read knowledge cards (`../../knowledge-base/*/*.en.md`); self-contained and immediately usable
+- **Medium**: Read distilled book notes (`../../references/books/*.en.md`) for more complete context
 - **Deep**: When `math_book/<PDF>` is available locally, the agent automatically runs `pdftotext` + grep to locate the original page
 
-## Workflow Example
+## Knowledge Gap Protocol
 
-**User**: "Design a new KV Cache compression method that preserves long-range dependencies — I don't want to just do top-k."
+When the mathematical tools required by the user's problem are not in the existing `knowledge-base/`, do NOT force-fit existing cards. Execute the following procedure:
 
-```
-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
-```
+1. **Gap Identification**: Explicitly state that no fully corresponding knowledge card exists. Classify the gap as: new domain, new theorem family, new structure, new application scenario, or combinatorial extension of existing cards.
+
+2. **Lens Fallback**: Select 1–3 most relevant thinking lenses to determine the problem's mathematical structure. E.g., local-to-global, categorical, spectral, projection, causal, perturbation.
+
+3. **Candidate Knowledge Localization**: Provide mathematical keywords, theorem families, concept clusters, and reference book directions to look up. Existing card coverage is not required, but explain why these concepts are relevant.
+
+4. **Temporary Knowledge Card**: Generate a temporary knowledge summary in the same format as formal cards:
+   - Minimal definition
+   - Core structure
+   - Applicable problems
+   - AI design translation
+   - GPU feasibility
+   - Risks and failure conditions
+   - **Source & Confidence** (required):
+     - Knowledge source: label as "Agent inference / Lens derivation / Reference book extrapolation / Requires external verification"
+     - Confidence: High (theorem-backed) / Medium (reasonable inference, not rigorously proven) / Low (exploratory hypothesis)
+     - Unverified claims: list key conclusions requiring subsequent verification
+
+5. **Design Translation**: If the user's goal is mechanism design, translate the temporary knowledge into candidate AI modules, losses, routing, attention, representation, or compression schemes.
+
+6. **Upgrade Recommendation**: If this gap recurs frequently, recommend adding a formal knowledge card or design pattern.
+
+## Workflow Example
+
+Full workflow example: `../../references/skill-index.en.md`.