math-skill 3.3.0 → 3.3.1

package/README.en-US.md

@@ -16,9 +16,7 @@
 
 ## 📢 Community Announcements
 
-> **This skill is under rapid iteration — your feedback and suggestions are warmly welcome!** Your input is the core driver of our continuous evolution. Feel free to reach out via GitHub Issues or Discussions.
-
-> **v3.3.0**: canonical entry structure, minimum-context routing, AI/cryptography isolation, mathematical and cryptographic corrections, relevance-driven GPU review, and complete bilingual pairing. Root `SKILL.md` is authoritative, and all three cryptography distillations now have dedicated English versions. See the changelog.
+> **v3.3.1 released**: documentation-discipline patch — completed the README directory tree, corrected the workflow example, slimmed the changelog, and unified entry phrasing and counting caliber. v3.3.0 delivered routing convergence and technical corrections; this release fixes the documentation-consistency issues it left behind. See the changelog. Feedback and edge-case reports are welcome via GitHub Issues or Discussions.
 
 ---
 
@@ -53,8 +51,6 @@ Design Translation: How do these tools become model structures / losses / operat
 Critic: Mathematically sound? Engineering-feasible?
 ```
 
-> **v3.2.1 Design Philosophy Refinement**: This skill is a mathematical-thinking activator and anchor, not a knowledge encyclopedia. `knowledge-base/` anchors describe mathematical structures (manifolds, spectra, sheaf cohomology, pseudorandom function families, etc.), not specific AI architectures (diffusion, SSM, etc.); `design-patterns/` is a paradigmatic demonstration of "math→AI module" translation, not a copy-paste template library. This ensures the skill retains guiding capacity for any research direction (diffusion, SSM, MoE, alignment, etc.) and does not become outdated as concrete architectures evolve.
-
 ---
 
 ## Three-Layer Orthogonal Architecture
@@ -70,7 +66,7 @@ Supporting layers:
 - `references/gpu-friendly-math.en.md`: on-demand GPU checks with N/A for irrelevant dimensions
 - `agents/math-critic.en.md`: 19-dimension deep critic loaded only for comprehensive or paper-grade review
 
-### Domain Router (new in v3.2.0)
+### Domain Router
 
 AI research and cryptography **share** mathematical foundations (probability/information/algebra/matrix/spectrum/optimization) but each has **exclusive** specialty layers. After intent diagnosis and before lens invocation, Domain Router determines the problem's domain and decides which anchors/books/design patterns to load, avoiding cross-domain pollution and token waste.
 
@@ -178,25 +174,24 @@ Step 1  Diagnosis: Scenario B (Mechanism Design)
   Problem type: sequence memory compression + information preservation + long-range structure
   Core tension: compress token count vs. preserve long-range dependencies
 
-Step 2  Lens Selection:
+Step 2  Lens Selection (default ≤2):
   1. Spectral (preserve dominant subspace)
-  2. Information-theoretic (preserve max mutual information states)
-  3. Topological (preserve key connection points in sequence structure)
+  2. Probabilistic/Information (preserve mutual-information-sensitive states)
+  (Add Topological only when the user stresses connectivity/bridge structure; not in default budget)
 
 Step 3  Activation Anchors:
   → low-rank-approximation (Matrix Analysis anchor)
-  → leverage-score-selection (Design Pattern: compression)
   → information-bottleneck (Probability & Information anchor)
+  → leverage-score-selection or low-rank-kv-cache (0–2 compression design patterns)
   If existing anchors are insufficient, enter Knowledge Gap Protocol to generate a temporary knowledge card.
 
 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)
+  Primary: Spectral KV Compression (low-rank + leverage score)
+  Alternative (key difference only): Information-Preserving Cache (relies on future query estimation)
 
-Step 5  Critic Review:
-  A is most GPU-friendly, B needs future query estimation (uncertainty), C graph construction too expensive
-  Recommendation: prioritize A, use B as a lightweight gate
+Step 5  Compact Review (ordinary tasks do not load the full critic):
+  Primary is most GPU-friendly; alternative needs future query estimation, higher uncertainty
+  Conclusion: prioritize primary; add a lightweight gate only if query-sensitive retention is needed
 ```
 
 ---
@@ -208,14 +203,16 @@ math-skill/
 ├── skills/
 │   └── math-research-activator/    # Orchestrator: intent diagnosis + routing
 ├── lenses/                         # 15 thinking lenses (reasoning methodology)
-├── knowledge-base/                 # Activation anchors by math domain, not a closed encyclopedia
+├── knowledge-base/                 # Activation anchors by math domain, not a closed encyclopedia (37 cards total)
 │   ├── matrix-analysis/            # Matrix analysis (5 cards)
 │   ├── optimization/               # Optimization (5 cards)
 │   ├── differential-geometry/      # Differential geometry (6 cards)
 │   ├── lie-theory/                 # Lie theory (5 cards)
 │   ├── topology/                   # Topology (3 cards)
 │   ├── probability/                # Probability & information (5 cards)
-│   └── information-geometry/       # Information geometry (2 cards)
+│   ├── information-geometry/       # Information geometry (2 cards)
+│   ├── algebraic-geometry/         # Algebraic geometry (2 cards)
+│   └── cryptography/               # Cryptography (4 cards, domain-exclusive)
 ├── design-patterns/                # Design translation (by AI component)
 │   ├── attention/                  # Attention mechanisms (5 patterns)
 │   ├── loss/                       # Loss functions (5 patterns)
@@ -226,7 +223,9 @@ math-skill/
 │   ├── books/                      # 10 book distillations (7 AI + 3 crypto)
 │   ├── gpu-friendly-math.en.md     # GPU checklist (applicable dimensions only)
 │   ├── agentic-workflow.en.md      # Collaboration style
-│   └── inspiration.en.md           # Inspiration
+│   ├── inspiration.en.md           # Inspiration
+│   ├── musings.en.md               # Musings (philosophical reflections, not auto-loaded)
+│   └── skill-index.en.md           # Index (on-demand directory, not loaded by default)
 ├── agents/math-critic.en.md           # Math-engineering dual critic (19 dims, with crypto security review)
 ├── commands/ask.en.md                 # /ask manual entry
 ├── math_book/                      # Local PDFs (not published)
@@ -249,7 +248,7 @@ math-skill/
 | 6 | *An Introduction to Optimization, With Applications to ML* | Chong, Lu, Żak | John Wiley & Sons, 5th ed. | 2024 | 978-1-119-87763-9 | `optimization-ml.en.md` |
 | 7 | *Introduction to Smooth Manifolds* | John M. Lee | Springer, GTM 218, 2nd ed. | 2013 | 978-1-4419-9981-8 | `smooth-manifolds.en.md` |
 
-### Cryptography Direction (3 books, new in v3.2.0)
+### Cryptography Direction (3 books)
 
 | # | Title | Author(s) | Publisher / Edition | Year | ISBN | Distillation |
 |---|-------|-----------|-------------------|------|------|-------------|
@@ -265,6 +264,14 @@ Distillation files ship with the npm package. For full-fidelity lookups, place P
 
 ## Changelog
 
+### v3.3.1 — Documentation-Discipline Patch
+
+- **README directory tree completed**: added `algebraic-geometry/`, `cryptography/`, `musings.md`, `skill-index.md`; card total aligned to 37
+- **README workflow example corrected**: lenses default ≤2, design patterns separated from anchors, Step 5 changed to compact review — consistent with `SKILL.md` budgets
+- **Changelog slimmed**: v1/v2 compressed to one-line summaries; removed stale "37 .en.md" / "16 thinking weapons" numbers
+- **Entry phrasing & counting caliber unified**: three entries use consistent "when to load .en" wording; repo-wide count standardized as 33 shared + 4 crypto = 37
+- **Metadata & hygiene**: `package.json` description/keywords trimmed; `CLAUDE.md` dir tree and Node.js note fixed; `validate.sh` gained 20 documentation-discipline checks; `original-texts` gained purpose note and v2 terminology fix
+
 ### v3.3.0 — Routing Convergence, Bilingual Completion & Technical Corrections
 
 - **Canonical entry and compatibility structure**: root `SKILL.md` / `SKILL.en.md` are now complete, self-contained normative entries. `skills/math-research-activator/SKILL*.md` are thin forwarders that preserve Claude/plugin layouts without allowing two full instruction copies to drift. `commands/ask*`, the critic, indexes, and overview now reference the root entries.
@@ -341,22 +348,19 @@ Distillation files ship with the npm package. For full-fidelity lookups, place P
 **Architecture overhaul**: from "thinking weapon arsenal" to "math general staff" — three-layer orthogonal architecture:
 
 - **Thinking Lenses** (15): slimmed down from v2's "thinking weapons" — reasoning methodology only, no concrete math knowledge mixed in
-- **Knowledge Base** (31 cards): concrete math tools organized by domain, with definitions/formulas/AI design translation/GPU feasibility
+- **Knowledge Base** (31 cards, expanded to 37 in v3.2): concrete math tools organized by domain, with definitions/formulas/AI design translation/GPU feasibility
 - **Design Translation Layer** (new): the bridge from math to AI modules, organized by AI component (attention/loss/routing/representation/compression)
 - **Activator rewrite**: from environment-signal matching to intent diagnosis (5 scenarios: analysis/design/query/verification/engineering)
 - **Knowledge activation protocol**: fixed output format for knowledge cards (minimal definition → formula → applicable problems → AI translation → engineering feasibility → risks)
 
 ### v2.1.0 — Full Bilingual Support
-- 37 .en.md files, auto language routing, same commands for both languages, no double token cost
-
-### v2.0.1
-- Tightened auto-trigger conditions, added exclusion gate, narrowed environment signals
+- Full bilingual support, auto language routing, same commands for both languages, no double token cost
 
-### v2.0.0
-- 16 thinking weapons, modern math activation layer, GPU 8-D cross-cut
+### v2.0.0–v2.0.1
+- 16 thinking weapons (v2 naming, replaced by 15 lenses in v3), modern math activation layer, GPU 8-D cross-cut; tightened auto-trigger conditions and exclusion gate
 
 ### v1.0.0
-- Initial release: fifteen thinking weapons + dual research/life paths
+- Initial release: early "thinking-weapon arsenal + dual research/life paths" form (restructured into three-layer architecture in v3.0.0)
 
 ---
 

package/README.md

@@ -16,9 +16,7 @@
 
 ## 📢 社区公告
 
-> **本 Skill 正在快速迭代中，欢迎各位使用者提出宝贵的使用感受和改进建议！** 你的反馈是我们持续进化的核心动力。欢迎通过 GitHub Issues 或 Discussions 与我们交流。
-
-> **v3.3.0**：完成入口结构、最小上下文路由、AI/密码学领域隔离、数学与密码学准确性、GPU 审查和全量中英配对升级。根 `SKILL.md` 是权威入口，三份密码学书稿已提供独立英文版。详见变更日志。
+> **v3.3.1 已发布**：文档纪律修复版——补全 README 目录树遗漏域、纠正工作流范例、瘦身 changelog、统一入口话术与计数口径。v3.3.0 完成路由收敛与专业性校正；本版修复其遗留的文档一致性问题。详见变更日志。欢迎通过 GitHub Issues 或 Discussions 反馈使用体验与边界场景。
 
 ---
 
@@ -53,8 +51,6 @@ Sophus Lie 打造"屠龙刀"的故事告诉我们：为解微分方程发明的
 批判器：数学上站得住、工程上跑得动吗？
 ```
 
-> **v3.2.1 设计哲学修正**：本 skill 是数学思考的 activator 与锚点，不是知识百科。`knowledge-base/` 的锚点描述数学结构（流形、谱、层上同调、伪随机函数族等），而非具体 AI 架构（diffusion、SSM 等）；`design-patterns/` 是"数学→AI 模块"的翻译范式示范，不是可复制的模板库。这保证了 skill 对任意研究方向（扩散、SSM、MoE、对齐等）都有引导能力，而不会随具体架构过时。
-
 ---
 
 ## 三层正交架构
@@ -70,7 +66,7 @@ Sophus Lie 打造"屠龙刀"的故事告诉我们：为解微分方程发明的
 - `references/gpu-friendly-math.md`：按需 GPU 检查；不适用维度标 N/A
 - `agents/math-critic.md`：仅全面/论文级审查按需加载的 19 维深度批判器
 
-### Domain Router（v3.2.0 新增）
+### Domain Router
 
 AI 研究与密码学**共享**数学根基（概率/信息/代数/矩阵/谱/优化），但**独有**各自专业层。Domain Router 在意图诊断后、调用透镜前，先判定问题归属，决定加载哪些锚点/书稿/设计模式，避免跨域污染与 token 浪费。
 
@@ -178,25 +174,24 @@ git clone https://github.com/the-thinker0/math-skill.git ~/.codex/skills/math-re
   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：
+第二步 透镜选择（默认 ≤2）：
   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）
+  2. 概率/信息（保留互信息敏感状态）
+  （拓扑仅在用户强调连通/桥接结构时再加，不计入默认预算）
 
 第三步 激活锚点：
   → low-rank-approximation（矩阵分析锚点）
-  → leverage-score-selection（压缩设计模式）
   → information-bottleneck（概率与信息锚点）
+  → leverage-score-selection 或 low-rank-kv-cache（0–2 个压缩设计模式）
   若现有锚点不足，进入 Knowledge Gap Protocol 生成临时知识卡。
 
 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）
+  主方案：Spectral KV Compression（低秩 + leverage score）
+  备选仅写关键差异：Information-Preserving Cache（依赖未来 query 估计）
 
-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
+第五步 紧凑审查（普通任务不加载完整 critic）：
+  主方案最 GPU 友好；备选需估计未来 query，不确定性更高
+  结论：优先主方案；需要 query 敏感保留时再加轻量 gate
 ```
 
 ---
@@ -208,14 +203,16 @@ math-skill/
 ├── skills/
 │   └── math-research-activator/    # 总控：意图诊断 + 路由
 ├── lenses/                         # 15 个思想透镜（推理方法论）
-├── knowledge-base/                 # 激活锚点（按数学领域组织，非封闭百科）
+├── knowledge-base/                 # 激活锚点（按数学领域组织，非封闭百科；共 37 卡）
 │   ├── matrix-analysis/            # 矩阵分析（5 卡片）
 │   ├── optimization/               # 最优化（5 卡片）
 │   ├── differential-geometry/      # 微分几何（6 卡片）
 │   ├── lie-theory/                 # 李理论（5 卡片）
 │   ├── topology/                   # 拓扑（3 卡片）
 │   ├── probability/                # 概率与信息（5 卡片）
-│   └── information-geometry/       # 信息几何（2 卡片）
+│   ├── information-geometry/       # 信息几何（2 卡片）
+│   ├── algebraic-geometry/         # 代数几何（2 卡片）
+│   └── cryptography/               # 密码学（4 卡片，域独有）
 ├── design-patterns/                # 设计翻译层（按 AI 组件组织）
 │   ├── attention/                  # 注意力机制（5 模式）
 │   ├── loss/                       # 损失函数（5 模式）
@@ -226,7 +223,9 @@ math-skill/
 │   ├── books/                      # 10 本书蒸馏稿（7 AI + 3 密码学）
 │   ├── gpu-friendly-math.md        # GPU 维度清单（仅评相关项）
 │   ├── agentic-workflow.md         # 协作方式
-│   └── inspiration.md              # 灵感来源
+│   ├── inspiration.md              # 灵感来源
+│   ├── musings.md                  # 杂谈（哲学感悟，不自动加载）
+│   └── skill-index.md              # 索引（按需目录，不默认加载）
 ├── agents/math-critic.md           # 数学-工程双重批判器（19 维，含密码学安全审视）
 ├── commands/ask.md                 # /ask 手动入口
 ├── math_book/                      # 本地 PDF（不发布）
@@ -241,15 +240,15 @@ math-skill/
 
 | # | 书名 | 作者 | 出版社 / 版次 | 年份 | ISBN | 蒸馏文件 |
 |---|------|------|-------------|------|------|---------|
-| 1 | *Contemporary Abstract Algebra* | Joseph A. Gallian | Brooks/Cole, Cengage, 8th ed. | 2013 | 978-1-133-59971-5 | `abstract-algebra.md` |
-| 2 | *The Rising Sea: Foundations of Algebraic Geometry* | Ravi Vakil | Princeton University Press | 2025 | 978-0-691-26866-8 | `algebraic-geometry-rising-sea.md` |
-| 3 | *Manifolds and Differential Geometry* | Jeffrey M. Lee | AMS, Graduate Studies in Math Vol. 107 | 2009 | 978-0-8218-4815-9 | `differential-geometry.md` |
-| 4 | *Matrix Analysis* | Roger A. Horn, Charles R. Johnson | Cambridge University Press, 2nd ed. | 2013 | 978-0-521-83940-2 | `matrix-analysis.md` |
-| 5 | *A micro Lie theory for state estimation in robotics* | Joan Solà et al. | arXiv:1812.01537v9 | 2021 | — | `micro-lie-theory.md` |
-| 6 | *An Introduction to Optimization, With Applications to ML* | Chong, Lu, Żak | John Wiley & Sons, 5th ed. | 2024 | 978-1-119-87763-9 | `optimization-ml.md` |
-| 7 | *Introduction to Smooth Manifolds* | John M. Lee | Springer, GTM 218, 2nd ed. | 2013 | 978-1-4419-9981-8 | `smooth-manifolds.md` |
+| 1 | *Contemporary Abstract Algebra* | Joseph A. Gallian | Brooks/Cole, Cengage, 8th ed. | 2013 | 978-1-133-59971-5 | `abstract-algebra.md` / `.en.md` |
+| 2 | *The Rising Sea: Foundations of Algebraic Geometry* | Ravi Vakil | Princeton University Press | 2025 | 978-0-691-26866-8 | `algebraic-geometry-rising-sea.md` / `.en.md` |
+| 3 | *Manifolds and Differential Geometry* | Jeffrey M. Lee | AMS, Graduate Studies in Math Vol. 107 | 2009 | 978-0-8218-4815-9 | `differential-geometry.md` / `.en.md` |
+| 4 | *Matrix Analysis* | Roger A. Horn, Charles R. Johnson | Cambridge University Press, 2nd ed. | 2013 | 978-0-521-83940-2 | `matrix-analysis.md` / `.en.md` |
+| 5 | *A micro Lie theory for state estimation in robotics* | Joan Solà et al. | arXiv:1812.01537v9 | 2021 | — | `micro-lie-theory.md` / `.en.md` |
+| 6 | *An Introduction to Optimization, With Applications to ML* | Chong, Lu, Żak | John Wiley & Sons, 5th ed. | 2024 | 978-1-119-87763-9 | `optimization-ml.md` / `.en.md` |
+| 7 | *Introduction to Smooth Manifolds* | John M. Lee | Springer, GTM 218, 2nd ed. | 2013 | 978-1-4419-9981-8 | `smooth-manifolds.md` / `.en.md` |
 
-### 密码学方向（3 本，v3.2.0 新增）
+### 密码学方向（3 本）
 
 | # | 书名 | 作者 | 出版社 / 版次 | 年份 | ISBN | 蒸馏文件 |
 |---|------|------|-------------|------|------|---------|
@@ -265,6 +264,14 @@ math-skill/
 
 ## 变更日志
 
+### v3.3.1 — 文档纪律修复版
+
+- **README 目录树补全**：补入 `algebraic-geometry/`、`cryptography/`、`musings.md`、`skill-index.md`，卡片总数标注对齐 37
+- **README 工作流范例纠正**：透镜默认 ≤2、设计模式与锚点分离、第五步改为紧凑审查，与 `SKILL.md` 预算一致
+- **changelog 瘦身**：v1/v2 压缩为一行摘要，移除"37 个 .en.md""16 思想武器"等失真数字
+- **入口话术与计数口径统一**：三处入口对"何时读 `.en` 版"措辞统一；全仓计数统一为 33 共用 + 4 密码 = 37
+- **元数据与工程卫生**：`package.json` description/keywords 瘦身；`CLAUDE.md` 目录树与 Node.js 依赖表述修正；`validate.sh` 新增 20 条文档纪律结构性检查；`original-texts` 加用途标注并修正 v2 旧术语
+
 ### v3.3.0 — 路由收敛、双语补全与专业性校正
 
 - **权威入口与兼容结构**：新增根 `SKILL.md` / `SKILL.en.md` 作为完整、自足的规范入口；`skills/math-research-activator/SKILL*.md` 缩为薄转发层，继续兼容 Claude/plugin 目录布局，同时避免两份完整正文长期漂移。`commands/ask*`、critic、索引和 overview 的引用均改到根入口。
@@ -341,22 +348,19 @@ math-skill/
 **架构重构**：从"思想武器库"升级为"数学参谋部"——三层正交架构：
 
 - **思想透镜**（15 个）：从 v2 的"思想武器"瘦身而来，只保留推理方法论，不再混入具体数学知识
-- **知识库**（31 张卡片）：按数学领域组织的具体工具卡片，含定义/公式/AI 设计翻译/GPU 可行性
+- **知识库**（31 张卡片，v3.2 起扩展至 37）：按数学领域组织的具体工具卡片，含定义/公式/AI 设计翻译/GPU 可行性
 - **设计翻译层**（新增）：数学→AI 模块的桥梁，按 AI 组件（attention/loss/routing/representation/compression）组织
 - **Activator 重写**：从环境信号匹配改为意图诊断（5 场景：分析/设计/查询/验证/工程）
 - **知识激活协议**：知识卡片固定输出格式（最小定义→公式→适用问题→AI 翻译→工程可行性→风险）
 
 ### v2.1.0 — 完整双语支持
-- 全面双语（37 个 .en.md 文件）、自动语言路由、命令一致、token 保障
-
-### v2.0.1
-- 收紧自动触发条件、新增排除门、环境信号收窄
+- 全面双语、自动语言路由、命令一致、token 保障
 
-### v2.0.0
-- 16 思想武器、现代数学激活层、GPU 八维横切
+### v2.0.0–v2.0.1
+- 16 思想武器（v2 旧名，v3 起改为 15 透镜）、现代数学激活层、GPU 八维横切；收紧自动触发条件与排除门
 
 ### v1.0.0
-- 初始发布：十五思想武器 + 科研与生活双路径
+- 初始发布：早期"思想武器库 + 科研与生活双路径"形态（已在 v3.0.0 重构为三层架构）
 
 ---
 

package/SKILL.en.md

@@ -7,7 +7,7 @@ description: |
 
 # Mathematical Research Router
 
-Answer in the user's primary language. Technical terms, code, paths, and formulas do not determine language. `SKILL.md` is the canonical Codex entry. This English file exists only for explicit English command-entry compatibility; do not load both files.
+This is the English compatibility entry, loaded only via explicit English command paths (e.g. `/ask` English routing). `SKILL.md` is the canonical Codex entry and can answer in either language. Answer in the user's primary language; technical terms, code, paths, and formulas do not determine language. Do not load both entries simultaneously.
 
 ## Objective and hard constraints
 

package/SKILL.md

@@ -7,7 +7,7 @@ description: |
 
 # 数学研究路由器
 
-本文件是 Codex 的权威入口。按用户主语言回答；技术词、代码、路径和公式不决定语言。不要为英文输入再次加载 `SKILL.en.md`；该文件只供显式英文命令入口兼容。
+本文件是 Codex 的权威入口。按用户主语言回答；技术词、代码、路径和公式不决定语言。`SKILL.en.md` 只供 `/ask` 英文入口等显式英文兼容路径加载，两者不同时加载——在本文档内即可中英作答。
 
 ## 目标与硬约束
 

package/commands/ask.en.md

@@ -8,8 +8,9 @@ description: |
 
 Determine primary language: judge by sentence frame, verbs, mood particles. AI/math/engineering terms (attention, loss, routing, etc.) do not count as language signals. Code, paths, formulas do not count. When CN/EN ratio is close, follow the previous turn's language; default to Chinese if no context. Explicit "in English/in Chinese" takes priority.
 
-- Chinese primary → load `../SKILL.md`
-- English primary → load `../SKILL.en.md`
+- Chinese primary → load `../SKILL.md` (canonical entry, can answer in either language)
+- English primary → load `../SKILL.en.md` (English compatibility entry)
+- Do not load both simultaneously
 
 Current question:
 $ARGUMENTS

package/commands/ask.md

@@ -9,8 +9,9 @@ description: |
 
 判定主语言：看句式、动词、语气词的主框架。AI/数学/工程术语（attention、loss、routing 等）不计入语言判定。代码、路径、公式不计入。中英比例接近时沿用上一轮语言，无上下文默认中文。显式"用英文/用中文"优先。
 
-- 中文主语言 → 读取 `../SKILL.md`
-- 英文主语言 → 读取 `../SKILL.en.md`
+- 中文主语言 → 读取 `../SKILL.md`（权威入口，可中英作答）
+- 英文主语言 → 读取 `../SKILL.en.md`（英文兼容入口）
+- 两者不同时加载
 
 当前问题：
 $ARGUMENTS

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "math-skill",
-  "version": "3.3.0",
-  "description": "面向 AI 架构创新与密码学研究的数学研究路由器：15 个思想透镜、33 个共用数学锚点、4 个密码学锚点、22 个 AI 设计原型，以及渐进加载、Domain Router 与 Knowledge Gap Protocol。Math research router for AI architecture and cryptography with progressive loading, domain isolation, and explicit token budgets.",
+  "version": "3.3.1",
+  "description": "面向 AI 架构创新与密码学研究的数学研究路由器：三层正交架构（15 透镜 / 37 锚点 / 22 设计原型）+ Domain Router + Knowledge Gap Protocol。Math research router for AI and cryptography: three-layer architecture with progressive loading and domain isolation.",
   "keywords": [
     "math",
     "mathematics",
@@ -10,49 +10,20 @@
     "claude",
     "cursor",
     "ai",
-    "axiomatization",
-    "abstraction",
-    "logic",
-    "modeling",
     "optimization",
     "probability",
-    "transformation",
     "symmetry",
-    "induction",
-    "algorithm",
+    "topology",
     "information-theory",
     "game-theory",
-    "causal-inference",
-    "topology",
-    "combinatorics",
-    "discrete-math",
-    "math-research-activator",
-    "ask",
-    "tool-selection",
-    "algebraic-geometry",
     "differential-geometry",
     "lie-theory",
-    "manifolds",
-    "category-theory",
     "matrix-analysis",
-    "gpu",
-    "tensor-core",
-    "gpu-friendly",
-    "agentic-workflow",
-    "auto-trigger",
-    "co-design",
-    "research",
-    "bilingual",
-    "lenses",
-    "knowledge-base",
-    "design-patterns",
-    "math-research-os",
     "cryptography",
     "crypto",
-    "security",
-    "reduction-proof",
-    "attack-game",
-    "domain-router"
+    "gpu-friendly",
+    "research",
+    "bilingual"
   ],
   "license": "MIT",
   "author": "the-thinker0",

package/references/inspiration.en.md

@@ -34,4 +34,4 @@ The inspiration for this project stems precisely from this insight:
 
 ---
 
-> **The "Life as an Optimization Problem" section below has been moved to `musings.en.md`.** This file no longer retains it. For philosophical reflections, see `musings.en.md`.
+> **The "Life as an Optimization Problem" section below has been moved to `musings.en.md`.** For philosophical reflections, see `musings.en.md`.

package/references/inspiration.md

@@ -36,4 +36,4 @@ Sophus Lie 是一个想打造一把**屠龙刀**（解通微分方程）的铁
 
 ---
 
-> **以下"人生就是一场最优化"部分已移至 `musings.md`**，本文件不再保留。如需查阅哲学感悟，请见 `musings.md`。
+> **以下"人生就是一场最优化"部分已移至 `musings.md`**。如需查阅哲学感悟，请见 `musings.md`。

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

@@ -7,4 +7,4 @@ description: |
 
 # Compatibility Entry
 
-This is the Claude/plugin-style compatibility entry. Read and follow `../../SKILL.en.md` completely; the root file is the single authoritative English body and all resource paths resolve from the repository root. Do not also load `SKILL.md`.
+This is the Claude/plugin-style compatibility entry. Read and follow `../../SKILL.en.md` completely; the root file is the single authoritative body and all resource paths resolve from the repository root. Do not load both the Chinese and English entries simultaneously.

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

@@ -7,4 +7,4 @@ description: |
 
 # 兼容入口
 
-这是 Claude/plugin 风格的兼容入口。完整读取并遵循 `../../SKILL.md`；该根文件是唯一权威正文，所有资源路径均相对仓库根解析。不要同时读取 `SKILL.en.md`。
+这是 Claude/plugin 风格的兼容入口。完整读取并遵循 `../../SKILL.md`；该根文件是唯一权威正文，所有资源路径均相对仓库根解析。英文经显式英文入口进入时读 `../../SKILL.en.md`，不要同时加载两个入口。

package/skills/math-research-activator/original-texts.en.md

@@ -1,5 +1,7 @@
 # Intellectual Sources for the Math Research OS
 
+> **Note**: This file is design-rationale background (Pólya/Newell-Simon/Schoenfeld intellectual sources), not a runtime resource — the Domain Router does not auto-load it. Consult it only to understand the skill's design motivation.
+
 ## The Tradition of Problem Classification and Tool Selection
 
 ### Pólya's Problem-Solving Heuristics
@@ -40,8 +42,8 @@ Core insight: **the nature of the problem space determines the choice of search
 
 Alan H. Schoenfeld, in *Mathematical Problem Solving* (1985), analyzed why students fail to solve problems even when they possess the necessary tools — the critical deficiency is not a lack of tools but a lack of **strategic decision-making ability**:
 
-- **Resources**: Knowledge, skills, tools — corresponding to our 15 intellectual weapons
-- **Heuristics**: How to use resources — corresponding to the methodological workflow for each intellectual weapon
+- **Resources**: Knowledge, skills, tools — corresponding to our 15 thinking lenses
+- **Heuristics**: How to use resources — corresponding to the methodological workflow for each thinking lens
 - **Control**: When to use which resource — corresponding to the function of the activator
 - **Belief Systems**: Beliefs about mathematics and about oneself — affecting whether the appropriate tool is selected
 
@@ -65,7 +67,7 @@ Characteristics of wicked problems:
 - Solutions are not right or wrong, only better or worse
 - Span multiple domains
 
-Core insight: **wicked problems require combinations of cross-domain intellectual weapons, whereas tame problems can be solved with a single tool**. The activator recommends multi-tool combinations when facing wicked problems and single-tool focus when facing tame problems.
+Core insight: **wicked problems require combinations of cross-domain thinking lenses, whereas tame problems can be solved with a single tool**. The activator recommends multi-tool combinations when facing wicked problems and single-tool focus when facing tame problems.
 
 > "Wicked problems have no right or wrong answers, only better or worse ways of dealing with them." — Rittel & Webber
 
@@ -76,7 +78,7 @@ Daniel Kahneman, in *Thinking, Fast and Slow* (2011), proposed the dual-system t
 - **System 1**: Fast, intuitive, automatic — responsible for the majority of everyday decisions
 - **System 2**: Slow, rational, deliberate — required for decisions demanding careful thought
 
-Core insight: **not all problems require System 2-level rational analysis**. Many everyday decisions require only intuition (System 1), and forcibly deploying intellectual weapons constitutes over-analysis. The activator's "inapplicable scenarios" list is grounded in this insight — simple problems do not need tools; wicked problems do.
+Core insight: **not all problems require System 2-level rational analysis**. Many everyday decisions require only intuition (System 1), and forcibly deploying thinking lenses constitutes over-analysis. The activator's "inapplicable scenarios" list is grounded in this insight — simple problems do not need tools; wicked problems do.
 
 > "Overthinking is the enemy of decision-making — some decisions are best left to intuition." — Kahneman
 

package/skills/math-research-activator/original-texts.md

@@ -1,5 +1,7 @@
 # 数学研究操作系统的思想来源 / Intellectual Sources for the Math Research OS
 
+> **注意**：本文件是项目设计理念的背景资料（Pólya/Newell-Simon/Schoenfeld 等思想来源），不是运行时资源——Domain Router 不自动加载本文件。仅供了解 skill 的设计动机时参阅。
+
 ## 问题分类与工具选择的传统 / The Tradition of Problem Classification and Tool Selection
 
 ### Pólya 的问题求解启发法 / Pólya's Problem-Solving Heuristics