math-skill 3.0.0 → 3.1.0

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

@@ -5,25 +5,34 @@ 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`.
-# 🧭 Math Research OS
+> **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
 
 > "The thinking system does not hand out theorems, the knowledge system does not indulge in loose inspiration, and the design layer does not fake profundity."
 
 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)
 
@@ -32,56 +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
 
@@ -112,76 +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`.

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

@@ -5,14 +5,22 @@ description: |
   English: Mathematical research OS — auto-diagnoses user intent, routes to thinking lenses, math knowledge base, or design translation layer. Triggers on architecture/operator design, theoretical analysis, math-to-AI transfer. Does NOT trigger for pure engineering tasks.
 ---
 
-> **语言路由**：若用户消息为英文，请读取并遵循同目录下的 `SKILL.en.md`；中文消息则继续使用本文件。
+> **语言路由与混合输入规则**：看句式/动词/语气词主框架判定主语言。AI/数学/工程术语不计入。代码/路径/公式不计入。中英接近时沿用上一轮，无上下文默认中文。显式要求优先。中文→本文件，英文→`SKILL.en.md`。完整规则见 `../../references/skill-index.md`。
 
-# 🧭 数学研究操作系统 / Math Research OS
+# 数学研究操作系统 / Math Research OS
 
 > "思想系统不负责给定理，知识系统不负责乱启发，设计层不负责装深刻。"
 
 本系统是面向 AI 架构创新的数学参谋部——不是武器库，而是告诉你：**这场仗是什么仗、该用什么兵种、怎么部署、哪里会翻车。**
 
+## 核心原则
+
+> Math Skill 不存储数学，它激活数学、路由数学，并把数学翻译成 AI 研究设计。
+
+- **knowledge-base/** 不是封闭百科，而是数学激活锚点集合（activation anchors）
+- 当现有卡片不能覆盖问题时，Agent 不得停止或强行套用，而应基于透镜、参考层和自身数学知识生成"临时知识卡"，继续完成设计翻译
+- **design-patterns/** 是 math→AI 翻译原型集合，不是完整模型仓库；无对应模式时根据数学结构临时生成候选设计，并标记为 temporary design pattern
+
 ## 三层正交架构
 
 | 层 | 职责 | 目录 | 核心问题 |
@@ -38,51 +46,15 @@ description: |
 
 ## 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 |
+15 个透镜覆盖：公理化、对偶、对称性、谱分解、几何、投影与分解、变分、局部到整体、拓扑、范畴化、扰动、因果、博弈、概率统计、算法。目录：`../../lenses/*.md`。完整目录表见 `../../references/skill-index.md`。
 
 ## 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 |
+7 个领域：矩阵分析、最优化、微分几何、李理论、拓扑、概率与信息、信息几何。目录：`../../knowledge-base/*/*.md`。完整目录表见 `../../references/skill-index.md`。
 
 ## 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 |
+5 个组件类型：注意力、损失函数、路由、表示、压缩。目录：`../../design-patterns/*/*.md`。完整目录表见 `../../references/skill-index.md`。
 
 ## 自动触发条件
 
@@ -113,37 +85,39 @@ description: |
 
 ```
 场景 A（分析）：选 1-3 个透镜 → 输出视角诊断 → critic 审查
-场景 B（设计）：选 1-3 个透镜 → 查知识卡片 → 生成设计模式 → critic 审查
-场景 C（查询）：直接加载知识卡片 → 按知识激活协议输出
-场景 D（验证）：加载知识卡片 → critic 审查条件与边界
+场景 B（设计）：选 1-3 个透镜 → 调用相关激活锚点；若无覆盖则进入 Knowledge Gap Protocol → 生成正式/临时设计模式 → critic 审查
+场景 C（查询）：优先加载相关激活锚点；若无覆盖则生成临时知识卡 → 按知识激活协议输出
+场景 D（验证）：加载相关锚点或临时知识卡 → critic 审查条件与边界
 场景 E（工程）：不介入
 ```
 
 ### 第三步：输出格式
 
+**Token 经济原则**：以下是最长结构，不是默认全文模板。按用户问题裁剪；简单知识查询只给必要定义/公式/风险，设计与 GPU 内容只在与问题有关时展开；避免复述已加载卡片全文。
+
 **场景 A/B 输出**：
 1. **[诊断]** 问题类型 + 核心张力
 2. **[透镜]** 推荐 1-3 个数学视角（标注为什么适合/不适合）
-3. **[知识]**（仅场景 B）需要的具体数学工具（引用知识卡片）
-4. **[设计]**（仅场景 B）候选 AI 模块草案（引用设计模式）
+3. **[知识]**（仅场景 B）激活的数学结构（引用激活锚点或临时知识卡）
+4. **[设计]**（仅场景 B）候选 AI 模块草案（引用设计模式或临时设计草案）
 5. **[GPU]** 候选过八维门（友好/可改造/不友好）
 6. **[结论]** 保留通过双验收门的候选 + 下一步建议
 
-**场景 C 输出**（知识激活协议）：
+**场景 C 输出**（知识激活协议，按需裁剪）：
 1. 最小定义
 2. 核心公式
 3. 适用问题
-4. AI 设计翻译
-5. 工程可行性
+4. AI 设计翻译（仅当问题与 AI/算子相关）
+5. 工程可行性（仅当涉及实现/GPU）
 6. 风险与失效条件
-7. 深入参考（书蒸馏稿 / 原书路径）
+7. 深入参考（仅当用户要追溯或结论依赖外部书稿）
 
-**场景 D 输出**：
+**场景 D 输出**（优先短结论 + 条件边界）：
 1. 成立条件
 2. 不成立条件
 3. 最多能保证什么
 4. 不能保证什么
-5. 工程可行性
+5. 工程可行性（仅当涉及实现/GPU）
 
 **必须给出结论，不得只输出分析而不收敛。**
 
@@ -152,37 +126,46 @@ description: |
 正式术语（唯一权威来源：`../../references/gpu-friendly-math.md`）：
 **张量化 / GEMM 可映射 / 复杂度 / 显存与 KV-Cache / 低精度稳定 / 并行与通信 / 稀疏结构 / 算子融合**
 
+**量化评估要求**：对每个候选设计，GPU 评估不应只给 [v]/[~]/[x] 标签，还需回答：
+1. 核心操作的 FLOPs 和与 baseline 的比值
+2. 峰值显存 (bytes)，是否物化大矩阵
+3. bf16/fp8 下的数值稳定性策略
+4. 可融合的 kernel 数和预期加速
+
+详见 `../../references/gpu-friendly-math.md` 的量化检查清单。
+
 ## 深度查阅协议
 
 - **轻度**：读知识卡片（`../../knowledge-base/*/*.md`），自足可用
 - **中度**：读书蒸馏稿（`../../references/books/*.md`），获取更完整上下文
 - **深度**：本机有 `math_book/<PDF>` 时，Agent 自动 `pdftotext` + grep 定位原文页
 
-## 工作流范例
+## 知识缺口协议 / Knowledge Gap Protocol
 
-**用户**："设计新的 KV Cache 压缩方法，保留长期依赖，不想只做 top-k"
+当用户问题需要的数学工具不在现有 `knowledge-base/` 中时，不得强行套用已有卡片。执行以下流程：
 
-```
-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（矩阵分析）
-  → 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
-```
+1. **缺口识别**：明确指出现有知识库中没有完全对应的知识卡片。判断缺口属于：新领域、新定理族、新结构、新应用场景，还是已有卡片的组合扩展。
+
+2. **透镜回退**：选择 1-3 个最相关思想透镜，用它们确定问题的数学结构。例如：局部到整体、范畴化、谱分解、投影、因果、扰动等。
+
+3. **候选知识定位**：给出应查找的数学关键词、定理族、概念簇、参考书方向。不要求已有知识卡覆盖，但必须说明为什么这些知识相关。
+
+4. **临时知识卡**：生成一个"临时知识摘要"，格式同正式知识卡：
+   - 最小定义
+   - 核心结构
+   - 适用问题
+   - AI 设计翻译
+   - GPU 可行性
+   - 风险与失效条件
+   - **来源与置信度**（必填）：
+     - 知识来源：标注为"Agent 推断 / 透镜推导 / 参考书外推 / 需外部验证"
+     - 置信度：高（有定理支撑）/ 中（合理推断但未严格证明）/ 低（探索性假说）
+     - 未核验声明：列出需要后续验证的关键结论
+
+5. **设计翻译**：若用户目标是机制设计，则将临时知识转译为候选 AI 模块、loss、routing、attention、representation 或 compression 方案。
+
+6. **升级建议**：如果该缺口高频出现，建议新增正式 knowledge card 或 design pattern。
+
+## 工作流范例
+
+完整工作流范例见 `../../references/skill-index.md`。