math-skill 2.1.0 → 3.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.en-US.md +159 -200
- package/README.md +159 -200
- package/agents/math-critic.en.md +2 -2
- package/agents/math-critic.md +8 -8
- package/commands/ask.md +3 -10
- package/design-patterns/attention/equivariant-attention.en.md +72 -0
- package/design-patterns/attention/equivariant-attention.md +72 -0
- package/design-patterns/attention/geometry-aware-attention.en.md +73 -0
- package/design-patterns/attention/geometry-aware-attention.md +72 -0
- package/design-patterns/attention/information-bottleneck-attention.en.md +72 -0
- package/design-patterns/attention/information-bottleneck-attention.md +72 -0
- package/design-patterns/attention/projection-attention.en.md +68 -0
- package/design-patterns/attention/projection-attention.md +68 -0
- package/design-patterns/attention/spectral-attention.en.md +71 -0
- package/design-patterns/attention/spectral-attention.md +71 -0
- package/design-patterns/compression/leverage-score-selection.en.md +71 -0
- package/design-patterns/compression/leverage-score-selection.md +71 -0
- package/design-patterns/compression/low-rank-kv-cache.en.md +60 -0
- package/design-patterns/compression/low-rank-kv-cache.md +60 -0
- package/design-patterns/compression/spectral-token-pruning.en.md +61 -0
- package/design-patterns/compression/spectral-token-pruning.md +61 -0
- package/design-patterns/compression/topology-preserving-compression.en.md +64 -0
- package/design-patterns/compression/topology-preserving-compression.md +64 -0
- package/design-patterns/loss/constraint-penalty.en.md +67 -0
- package/design-patterns/loss/constraint-penalty.md +78 -0
- package/design-patterns/loss/contrastive-loss.en.md +59 -0
- package/design-patterns/loss/contrastive-loss.md +68 -0
- package/design-patterns/loss/information-bottleneck-loss.en.md +69 -0
- package/design-patterns/loss/information-bottleneck-loss.md +74 -0
- package/design-patterns/loss/orthogonality-loss.en.md +56 -0
- package/design-patterns/loss/orthogonality-loss.md +60 -0
- package/design-patterns/loss/variational-loss.en.md +61 -0
- package/design-patterns/loss/variational-loss.md +71 -0
- package/design-patterns/representation/equivariant-split.en.md +87 -0
- package/design-patterns/representation/equivariant-split.md +89 -0
- package/design-patterns/representation/manifold-representation.en.md +85 -0
- package/design-patterns/representation/manifold-representation.md +87 -0
- package/design-patterns/representation/shared-private-decomposition.en.md +84 -0
- package/design-patterns/representation/shared-private-decomposition.md +86 -0
- package/design-patterns/representation/subspace-alignment.en.md +90 -0
- package/design-patterns/representation/subspace-alignment.md +92 -0
- package/design-patterns/routing/graph-routing.en.md +79 -0
- package/design-patterns/routing/graph-routing.md +81 -0
- package/design-patterns/routing/moe-routing.en.md +85 -0
- package/design-patterns/routing/moe-routing.md +87 -0
- package/design-patterns/routing/optimal-transport-routing.en.md +68 -0
- package/design-patterns/routing/optimal-transport-routing.md +72 -0
- package/design-patterns/routing/spectral-clustering-routing.en.md +88 -0
- package/design-patterns/routing/spectral-clustering-routing.md +90 -0
- package/knowledge-base/differential-geometry/connection.en.md +51 -0
- package/knowledge-base/differential-geometry/connection.md +51 -0
- package/knowledge-base/differential-geometry/curvature.en.md +49 -0
- package/knowledge-base/differential-geometry/curvature.md +49 -0
- package/knowledge-base/differential-geometry/geodesic.en.md +51 -0
- package/knowledge-base/differential-geometry/geodesic.md +51 -0
- package/knowledge-base/differential-geometry/manifold.en.md +47 -0
- package/knowledge-base/differential-geometry/manifold.md +47 -0
- package/knowledge-base/differential-geometry/metric-tensor.en.md +50 -0
- package/knowledge-base/differential-geometry/metric-tensor.md +50 -0
- package/knowledge-base/differential-geometry/tangent-space.en.md +48 -0
- package/knowledge-base/differential-geometry/tangent-space.md +48 -0
- package/knowledge-base/information-geometry/fisher-metric.en.md +56 -0
- package/knowledge-base/information-geometry/fisher-metric.md +56 -0
- package/knowledge-base/information-geometry/natural-gradient.en.md +54 -0
- package/knowledge-base/information-geometry/natural-gradient.md +54 -0
- package/knowledge-base/lie-theory/equivariance.en.md +54 -0
- package/knowledge-base/lie-theory/equivariance.md +54 -0
- package/knowledge-base/lie-theory/group-action.en.md +51 -0
- package/knowledge-base/lie-theory/group-action.md +51 -0
- package/knowledge-base/lie-theory/lie-algebra.en.md +51 -0
- package/knowledge-base/lie-theory/lie-algebra.md +51 -0
- package/knowledge-base/lie-theory/lie-group.en.md +51 -0
- package/knowledge-base/lie-theory/lie-group.md +51 -0
- package/knowledge-base/lie-theory/representation.en.md +52 -0
- package/knowledge-base/lie-theory/representation.md +52 -0
- package/knowledge-base/matrix-analysis/low-rank-approximation.en.md +49 -0
- package/knowledge-base/matrix-analysis/low-rank-approximation.md +49 -0
- package/knowledge-base/matrix-analysis/matrix-perturbation.en.md +49 -0
- package/knowledge-base/matrix-analysis/matrix-perturbation.md +49 -0
- package/knowledge-base/matrix-analysis/positive-semidefinite.en.md +50 -0
- package/knowledge-base/matrix-analysis/positive-semidefinite.md +50 -0
- package/knowledge-base/matrix-analysis/projection.en.md +47 -0
- package/knowledge-base/matrix-analysis/projection.md +47 -0
- package/knowledge-base/matrix-analysis/spectral-decomposition.en.md +48 -0
- package/knowledge-base/matrix-analysis/spectral-decomposition.md +48 -0
- package/knowledge-base/optimization/constrained-optimization.en.md +53 -0
- package/knowledge-base/optimization/constrained-optimization.md +53 -0
- package/knowledge-base/optimization/convex-optimization.en.md +50 -0
- package/knowledge-base/optimization/convex-optimization.md +50 -0
- package/knowledge-base/optimization/lagrangian-duality.en.md +50 -0
- package/knowledge-base/optimization/lagrangian-duality.md +50 -0
- package/knowledge-base/optimization/proximal-method.en.md +52 -0
- package/knowledge-base/optimization/proximal-method.md +52 -0
- package/knowledge-base/optimization/riemannian-optimization.en.md +51 -0
- package/knowledge-base/optimization/riemannian-optimization.md +51 -0
- package/knowledge-base/overview.en.md +29 -218
- package/knowledge-base/overview.md +29 -220
- package/knowledge-base/probability/concentration-inequality.en.md +45 -0
- package/knowledge-base/probability/concentration-inequality.md +45 -0
- package/knowledge-base/probability/entropy.en.md +47 -0
- package/knowledge-base/probability/entropy.md +47 -0
- package/knowledge-base/probability/fisher-information.en.md +48 -0
- package/knowledge-base/probability/fisher-information.md +48 -0
- package/knowledge-base/probability/information-bottleneck.en.md +49 -0
- package/knowledge-base/probability/information-bottleneck.md +49 -0
- package/knowledge-base/probability/kl-divergence.en.md +51 -0
- package/knowledge-base/probability/kl-divergence.md +51 -0
- package/knowledge-base/topology/euler-characteristic.en.md +54 -0
- package/knowledge-base/topology/euler-characteristic.md +54 -0
- package/knowledge-base/topology/fundamental-group.en.md +52 -0
- package/knowledge-base/topology/fundamental-group.md +52 -0
- package/knowledge-base/topology/persistent-homology.en.md +54 -0
- package/knowledge-base/topology/persistent-homology.md +54 -0
- package/lenses/algorithmic.en.md +49 -0
- package/lenses/algorithmic.md +49 -0
- package/lenses/axiomatization.en.md +48 -0
- package/lenses/axiomatization.md +48 -0
- package/lenses/categorical.en.md +48 -0
- package/lenses/categorical.md +48 -0
- package/lenses/causal.en.md +49 -0
- package/lenses/causal.md +49 -0
- package/lenses/duality.en.md +47 -0
- package/lenses/duality.md +47 -0
- package/lenses/game.en.md +50 -0
- package/lenses/game.md +50 -0
- package/lenses/geometric.en.md +53 -0
- package/lenses/geometric.md +53 -0
- package/lenses/local-to-global.en.md +52 -0
- package/lenses/local-to-global.md +52 -0
- package/lenses/perturbation.en.md +51 -0
- package/lenses/perturbation.md +51 -0
- package/lenses/probabilistic.en.md +48 -0
- package/lenses/probabilistic.md +48 -0
- package/lenses/projection.en.md +50 -0
- package/lenses/projection.md +50 -0
- package/lenses/spectral.en.md +52 -0
- package/lenses/spectral.md +52 -0
- package/lenses/symmetry.en.md +49 -0
- package/lenses/symmetry.md +49 -0
- package/lenses/topological.en.md +48 -0
- package/lenses/topological.md +48 -0
- package/lenses/variational.en.md +48 -0
- package/lenses/variational.md +48 -0
- package/package.json +9 -3
- package/references/books/abstract-algebra.md +5 -5
- package/references/books/algebraic-geometry-rising-sea.md +5 -5
- package/references/books/differential-geometry.md +3 -3
- package/references/books/matrix-analysis.md +4 -4
- package/references/books/micro-lie-theory.md +3 -3
- package/references/books/optimization-ml.md +1 -1
- package/references/books/smooth-manifolds.md +3 -3
- package/references/gpu-friendly-math.en.md +8 -8
- package/references/gpu-friendly-math.md +2 -2
- package/references/inspiration.en.md +1 -1
- package/references/inspiration.md +2 -2
- package/skills/math-research-activator/SKILL.en.md +161 -106
- package/skills/math-research-activator/SKILL.md +162 -110
- package/skills/math-research-activator/original-texts.en.md +9 -9
- package/skills/math-research-activator/original-texts.md +11 -11
- package/commands/abstraction.md +0 -11
- package/commands/algorithmic-thinking.md +0 -11
- package/commands/axiomatization.md +0 -11
- package/commands/causal-inference.md +0 -11
- package/commands/discrete-combinatorial.md +0 -11
- package/commands/game-theory.md +0 -11
- package/commands/induction-analogy.md +0 -11
- package/commands/information-theory.md +0 -11
- package/commands/logic-deduction.md +0 -11
- package/commands/modeling.md +0 -11
- package/commands/optimization.md +0 -11
- package/commands/probability-statistics.md +0 -11
- package/commands/symmetry-invariance.md +0 -11
- package/commands/topological-thinking.md +0 -11
- package/commands/transformation.md +0 -11
- package/skills/abstraction/SKILL.en.md +0 -117
- package/skills/abstraction/SKILL.md +0 -121
- package/skills/abstraction/original-texts.en.md +0 -163
- package/skills/abstraction/original-texts.md +0 -175
- package/skills/algorithmic-thinking/SKILL.en.md +0 -132
- package/skills/algorithmic-thinking/SKILL.md +0 -138
- package/skills/algorithmic-thinking/original-texts.en.md +0 -253
- package/skills/algorithmic-thinking/original-texts.md +0 -256
- package/skills/axiomatization/SKILL.en.md +0 -144
- package/skills/axiomatization/SKILL.md +0 -151
- package/skills/axiomatization/original-texts.en.md +0 -154
- package/skills/axiomatization/original-texts.md +0 -160
- package/skills/causal-inference/SKILL.en.md +0 -147
- package/skills/causal-inference/SKILL.md +0 -151
- package/skills/causal-inference/original-texts.en.md +0 -136
- package/skills/causal-inference/original-texts.md +0 -167
- package/skills/discrete-combinatorial/SKILL.en.md +0 -124
- package/skills/discrete-combinatorial/SKILL.md +0 -131
- package/skills/discrete-combinatorial/original-texts.en.md +0 -184
- package/skills/discrete-combinatorial/original-texts.md +0 -185
- package/skills/game-theory/SKILL.en.md +0 -117
- package/skills/game-theory/SKILL.md +0 -123
- package/skills/game-theory/original-texts.en.md +0 -131
- package/skills/game-theory/original-texts.md +0 -131
- package/skills/induction-analogy/SKILL.en.md +0 -145
- package/skills/induction-analogy/SKILL.md +0 -152
- package/skills/induction-analogy/original-texts.en.md +0 -140
- package/skills/induction-analogy/original-texts.md +0 -154
- package/skills/information-theory/SKILL.en.md +0 -134
- package/skills/information-theory/SKILL.md +0 -140
- package/skills/information-theory/original-texts.en.md +0 -127
- package/skills/information-theory/original-texts.md +0 -127
- package/skills/logic-deduction/SKILL.en.md +0 -130
- package/skills/logic-deduction/SKILL.md +0 -135
- package/skills/logic-deduction/original-texts.en.md +0 -160
- package/skills/logic-deduction/original-texts.md +0 -173
- package/skills/modeling/SKILL.en.md +0 -135
- package/skills/modeling/SKILL.md +0 -139
- package/skills/modeling/original-texts.en.md +0 -162
- package/skills/modeling/original-texts.md +0 -165
- package/skills/optimization/SKILL.en.md +0 -129
- package/skills/optimization/SKILL.md +0 -135
- package/skills/optimization/original-texts.en.md +0 -167
- package/skills/optimization/original-texts.md +0 -168
- package/skills/probability-statistics/SKILL.en.md +0 -146
- package/skills/probability-statistics/SKILL.md +0 -151
- package/skills/probability-statistics/original-texts.en.md +0 -191
- package/skills/probability-statistics/original-texts.md +0 -193
- package/skills/symmetry-invariance/SKILL.en.md +0 -135
- package/skills/symmetry-invariance/SKILL.md +0 -139
- package/skills/symmetry-invariance/original-texts.en.md +0 -206
- package/skills/symmetry-invariance/original-texts.md +0 -221
- package/skills/topological-thinking/SKILL.en.md +0 -124
- package/skills/topological-thinking/SKILL.md +0 -128
- package/skills/topological-thinking/original-texts.en.md +0 -134
- package/skills/topological-thinking/original-texts.md +0 -164
- package/skills/transformation/SKILL.en.md +0 -120
- package/skills/transformation/SKILL.md +0 -124
- package/skills/transformation/original-texts.en.md +0 -204
- package/skills/transformation/original-texts.md +0 -216
package/README.md
CHANGED
|
@@ -2,9 +2,9 @@
|
|
|
2
2
|
<a href="README.md">中文</a> | <a href="README.en-US.md">English</a>
|
|
3
3
|
</p>
|
|
4
4
|
|
|
5
|
-
# ⚔️ Math Skill —
|
|
5
|
+
# ⚔️ Math Skill — 面向 AI 架构创新的数学研究操作系统
|
|
6
6
|
|
|
7
|
-
>
|
|
7
|
+
> **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。**
|
|
8
8
|
|
|
9
9
|
[](LICENSE)
|
|
10
10
|
[](https://www.npmjs.com/package/math-skill)
|
|
@@ -12,7 +12,7 @@
|
|
|
12
12
|
|
|
13
13
|
---
|
|
14
14
|
|
|
15
|
-
> **如果这个项目对你有所启发,请不吝点亮一颗 Star
|
|
15
|
+
> **如果这个项目对你有所启发,请不吝点亮一颗 Star⭐。** 每一个 Star 都是对数学之美的共鸣,也是支撑这个项目继续前行的力量。欢迎每一位热爱数学、在数学海洋中遨游的同行者。
|
|
16
16
|
|
|
17
17
|
---
|
|
18
18
|
|
|
@@ -20,53 +20,87 @@
|
|
|
20
20
|
|
|
21
21
|
Sophus Lie 打造"屠龙刀"的故事告诉我们:为解微分方程发明的李群-李代数,最终成为描述对称性、机器人状态估计的通用语言——数学工具的价值远超初衷,这正是「跨领域激活」的原型。详见 [`references/inspiration.md`](references/inspiration.md)。
|
|
22
22
|
|
|
23
|
-
>
|
|
23
|
+
> 数学最迷人的地方:为特定问题发明的工具,在完全不同的领域展现出远超初衷的价值。
|
|
24
24
|
|
|
25
25
|
---
|
|
26
26
|
|
|
27
27
|
## 核心理念
|
|
28
28
|
|
|
29
|
-
|
|
29
|
+
当你面对一个 AI 研究问题时,这个系统帮你回答四个问题:
|
|
30
30
|
|
|
31
|
-
|
|
31
|
+
1. **该用什么数学思想看?** → 思想透镜
|
|
32
|
+
2. **需要查什么具体数学知识?** → 知识库
|
|
33
|
+
3. **怎么把数学变成模型设计?** → 设计翻译层
|
|
34
|
+
4. **这个设计是否数学上靠谱、工程上可行?** → 批判器
|
|
32
35
|
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
- **GPU 八维横切**:15 个思想武器都显式落到 `references/gpu-friendly-math.md` 的正式八维: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。
|
|
45
|
-
- **单一研究路径**:面向科研、算法、算子和训练/推理 Infra;不再保留生活建议模式。
|
|
46
|
-
- **渐进式披露**:常驻层(activator + description)→ 方法论层(按需)→ 书籍层(按需),避免无关上下文常驻。
|
|
36
|
+
```
|
|
37
|
+
问题
|
|
38
|
+
↓
|
|
39
|
+
思想透镜:这个问题该用什么视角看?
|
|
40
|
+
↓
|
|
41
|
+
数学知识:这个视角需要哪些具体数学工具?
|
|
42
|
+
↓
|
|
43
|
+
设计翻译:这些工具怎么变成模型结构 / loss / 算子?
|
|
44
|
+
↓
|
|
45
|
+
批判器:数学上站得住、工程上跑得动吗?
|
|
46
|
+
```
|
|
47
47
|
|
|
48
48
|
---
|
|
49
49
|
|
|
50
|
-
##
|
|
51
|
-
|
|
52
|
-
|
|
|
53
|
-
|
|
54
|
-
|
|
|
55
|
-
|
|
|
56
|
-
|
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
|
66
|
-
|
|
67
|
-
|
|
|
68
|
-
|
|
|
69
|
-
|
|
|
50
|
+
## 三层正交架构
|
|
51
|
+
|
|
52
|
+
| 层 | 职责 | 目录 | 文件数 |
|
|
53
|
+
|----|------|------|--------|
|
|
54
|
+
| **思想透镜** | 诊断问题结构,推荐数学视角 | `lenses/*.md` | 15 |
|
|
55
|
+
| **数学知识** | 提供具体数学工具(定义/定理/公式) | `knowledge-base/*/*.md` | 31 |
|
|
56
|
+
| **设计翻译** | 把数学变成 AI 模块/loss/算子 | `design-patterns/*/*.md` | 22 |
|
|
57
|
+
|
|
58
|
+
辅助层:
|
|
59
|
+
- `references/books/*.md`:7 本书蒸馏稿,需要深入时的完整上下文
|
|
60
|
+
- `references/gpu-friendly-math.md`:GPU 八维验收门
|
|
61
|
+
- `agents/math-critic.md`:数学-工程双重批判器
|
|
62
|
+
|
|
63
|
+
### 15 个思想透镜
|
|
64
|
+
|
|
65
|
+
| 透镜 | 文件 | 核心视角 |
|
|
66
|
+
|------|------|---------|
|
|
67
|
+
| 公理化 | `lenses/axiomatization.md` | 审查假设的相容性/独立性/完备性 |
|
|
68
|
+
| 对偶 | `lenses/duality.md` | 转换到对偶空间暴露约束与不变量 |
|
|
69
|
+
| 对称性 | `lenses/symmetry.md` | 变换下的不变量与守恒律 |
|
|
70
|
+
| 谱分解 | `lenses/spectral.md` | 特征值/奇异值揭示主导结构 |
|
|
71
|
+
| 几何 | `lenses/geometric.md` | 度量/曲率/流形上的空间结构 |
|
|
72
|
+
| 投影与分解 | `lenses/projection.md` | 正交分解、子空间分离、冲突消除 |
|
|
73
|
+
| 变分 | `lenses/variational.md` | 约束下极值、能量最小化 |
|
|
74
|
+
| 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 |
|
|
75
|
+
| 拓扑 | `lenses/topological.md` | 连续变形不变量、连通性、空洞 |
|
|
76
|
+
| 范畴化 | `lenses/categorical.md` | 泛性质、函子、自然变换 |
|
|
77
|
+
| 扰动 | `lenses/perturbation.md` | 小扰动的传播、稳定性、鲁棒性 |
|
|
78
|
+
| 因果 | `lenses/causal.md` | 相关≠因果、干预、反事实 |
|
|
79
|
+
| 博弈 | `lenses/game.md` | 多方策略互动、均衡、机制设计 |
|
|
80
|
+
| 概率统计 | `lenses/probabilistic.md` | 量化不确定性、贝叶斯更新 |
|
|
81
|
+
| 算法 | `lenses/algorithmic.md` | 复杂度、可行性、并行性 |
|
|
82
|
+
|
|
83
|
+
### 知识库(按数学领域)
|
|
84
|
+
|
|
85
|
+
| 领域 | 知识卡片 |
|
|
86
|
+
|------|---------|
|
|
87
|
+
| 矩阵分析 | projection, spectral-decomposition, low-rank-approximation, positive-semidefinite, matrix-perturbation |
|
|
88
|
+
| 最优化 | lagrangian-duality, convex-optimization, constrained-optimization, riemannian-optimization, proximal-method |
|
|
89
|
+
| 微分几何 | manifold, tangent-space, metric-tensor, geodesic, curvature, connection |
|
|
90
|
+
| 李理论 | group-action, lie-group, lie-algebra, representation, equivariance |
|
|
91
|
+
| 拓扑 | persistent-homology, euler-characteristic, fundamental-group |
|
|
92
|
+
| 概率与信息 | concentration-inequality, entropy, kl-divergence, information-bottleneck, fisher-information |
|
|
93
|
+
| 信息几何 | natural-gradient, fisher-metric |
|
|
94
|
+
|
|
95
|
+
### 设计模式库(按 AI 组件)
|
|
96
|
+
|
|
97
|
+
| 组件 | 设计模式 |
|
|
98
|
+
|------|---------|
|
|
99
|
+
| 注意力 | projection-attention, spectral-attention, equivariant-attention, geometry-aware-attention, information-bottleneck-attention |
|
|
100
|
+
| 损失函数 | orthogonality-loss, contrastive-loss, variational-loss, information-bottleneck-loss, constraint-penalty |
|
|
101
|
+
| 路由 | optimal-transport-routing, graph-routing, moe-routing, spectral-clustering-routing |
|
|
102
|
+
| 表示 | shared-private-decomposition, manifold-representation, equivariant-split, subspace-alignment |
|
|
103
|
+
| 压缩 | low-rank-kv-cache, spectral-token-pruning, topology-preserving-compression, leverage-score-selection |
|
|
70
104
|
|
|
71
105
|
---
|
|
72
106
|
|
|
@@ -74,219 +108,144 @@ Sophus Lie 打造"屠龙刀"的故事告诉我们:为解微分方程发明的
|
|
|
74
108
|
|
|
75
109
|
### 安装
|
|
76
110
|
|
|
77
|
-
直接粘贴下面这段给 Claude Code 或其他终端型 AI 助手即可:
|
|
78
|
-
|
|
79
111
|
```
|
|
80
112
|
请帮我安装 math-skill:https://github.com/the-thinker0/math-skill,并教我如何使用
|
|
81
113
|
```
|
|
82
114
|
|
|
83
|
-
|
|
115
|
+
手动安装:
|
|
84
116
|
|
|
85
117
|
```bash
|
|
86
118
|
git clone https://github.com/the-thinker0/math-skill.git
|
|
87
119
|
```
|
|
88
120
|
|
|
89
|
-
Claude Code / Codex 类平台:按平台的 skills / commands 目录规则复制或软链 `skills/`、`commands/`,并把 `references/` 保持在同一仓库层级。不要只复制单个 `SKILL.md`,否则 `../../references/*` 无法解析。
|
|
90
|
-
|
|
91
|
-
Cursor / 其他 Markdown 规则平台:把 `commands/*.md` 作为手动入口,把 `skills/*/SKILL.md` 作为规则/技能正文,并保留 `references/`。如果平台没有自动 skill 触发机制,就用 `/ask` 或对应命令手动触发。
|
|
92
|
-
|
|
93
|
-
也可先检查 npm 包内容:
|
|
94
|
-
|
|
95
|
-
```bash
|
|
96
|
-
npm pack math-skill --dry-run
|
|
97
|
-
```
|
|
98
|
-
|
|
99
121
|
### 使用
|
|
100
122
|
|
|
101
|
-
|
|
123
|
+
**自动触发**:系统自动诊断用户意图,路由到合适的层:
|
|
102
124
|
|
|
103
|
-
|
|
125
|
+
| 场景 | 诊断信号 | 调用路径 |
|
|
126
|
+
|------|---------|---------|
|
|
127
|
+
| 问题分析 | "这个设计合理吗?" | 透镜 → critic |
|
|
128
|
+
| 机制设计 | "设计新 attention" | 透镜 → 知识 → 设计 → critic |
|
|
129
|
+
| 知识查询 | "切空间和梯度优化有什么关系?" | 知识 |
|
|
130
|
+
| 验证审查 | "这个公式成立吗?" | 知识 → critic |
|
|
131
|
+
| 纯工程 | debug、重构、调参 | **不调用** |
|
|
104
132
|
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
例如你可以直接这样问:
|
|
108
|
-
|
|
109
|
-
```
|
|
110
|
-
我想设计一个更省 KV-Cache 的长上下文 attention,有没有现代数学视角?
|
|
111
|
-
```
|
|
112
|
-
|
|
113
|
-
或:
|
|
114
|
-
|
|
115
|
-
```
|
|
116
|
-
这个 Triton kernel 的访存和融合方式能不能从算法结构上优化?
|
|
117
|
-
```
|
|
118
|
-
|
|
119
|
-
这类问题会触发 `math-research-activator`,并按需加载 `references/gpu-friendly-math.md` 与 `references/books/*.md`。`/ask` 和下面的 slash commands 是**显式入口 / 兜底入口**:当平台没有自动 skill 触发机制,或你想强制指定某个思想武器时再使用。
|
|
120
|
-
|
|
121
|
-
**手动触发**(不确定该用哪个武器时先 `/ask`):
|
|
133
|
+
**手动触发**:
|
|
122
134
|
|
|
123
135
|
```
|
|
124
|
-
/ask <你的问题>
|
|
125
|
-
/axiomatization <你的问题> # 公理化思想
|
|
126
|
-
/abstraction <你的问题> # 抽象化思想
|
|
127
|
-
/logic-deduction <你的问题> # 逻辑演绎
|
|
128
|
-
/modeling <你的问题> # 建模思想
|
|
129
|
-
/optimization <你的问题> # 优化思想
|
|
130
|
-
/probability-statistics <你的问题> # 概率与统计
|
|
131
|
-
/transformation <你的问题> # 变换思想
|
|
132
|
-
/symmetry-invariance <你的问题> # 对称与不变性
|
|
133
|
-
/induction-analogy <你的问题> # 归纳与类比
|
|
134
|
-
/algorithmic-thinking <你的问题> # 算法与计算思想
|
|
135
|
-
/information-theory <你的问题> # 信息论思想
|
|
136
|
-
/game-theory <你的问题> # 博弈论思想
|
|
137
|
-
/causal-inference <你的问题> # 因果推断思想
|
|
138
|
-
/topological-thinking <你的问题> # 拓扑思想
|
|
139
|
-
/discrete-combinatorial <你的问题> # 离散与组合思想
|
|
136
|
+
/ask <你的问题> # 智能诊断:自动判断场景并路由
|
|
140
137
|
```
|
|
141
138
|
|
|
142
139
|
### 语言切换
|
|
143
140
|
|
|
144
|
-
|
|
141
|
+
自动检测用户语言:中文消息返回中文输出,英文消息返回英文输出。
|
|
145
142
|
|
|
146
143
|
---
|
|
147
144
|
|
|
148
|
-
##
|
|
149
|
-
|
|
150
|
-
### 自动触发(研究 / 算法 / GPU)
|
|
145
|
+
## 工作流范例
|
|
151
146
|
|
|
152
|
-
|
|
147
|
+
**用户**:"设计新的 KV Cache 压缩方法,保留长期依赖,不想只做 top-k"
|
|
153
148
|
|
|
154
|
-
### 手动触发(研究场景)
|
|
155
|
-
|
|
156
|
-
**审查算法的理论假设**:
|
|
157
149
|
```
|
|
158
|
-
|
|
159
|
-
|
|
160
|
-
|
|
161
|
-
|
|
162
|
-
|
|
163
|
-
|
|
164
|
-
|
|
165
|
-
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
|
|
169
|
-
|
|
170
|
-
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
|
|
174
|
-
|
|
175
|
-
|
|
176
|
-
|
|
177
|
-
|
|
178
|
-
|
|
150
|
+
第一步 诊断:场景 B(机制设计)
|
|
151
|
+
问题类型:序列记忆压缩 + 信息保留 + 长程结构
|
|
152
|
+
核心张力:压缩 token 数量 vs 不破坏长期依赖
|
|
153
|
+
|
|
154
|
+
第二步 透镜选择:
|
|
155
|
+
1. 谱分解(保留主导子空间)
|
|
156
|
+
2. 信息论(保留最大互信息状态)
|
|
157
|
+
3. 拓扑(保留序列结构关键连接点)
|
|
158
|
+
|
|
159
|
+
第三步 知识查询:
|
|
160
|
+
→ low-rank-approximation(矩阵分析)
|
|
161
|
+
→ leverage-score-selection(矩阵分析)
|
|
162
|
+
→ information-bottleneck(概率与信息)
|
|
163
|
+
|
|
164
|
+
第四步 设计翻译:
|
|
165
|
+
候选 A:Spectral KV Compression(低秩 + leverage score)
|
|
166
|
+
候选 B:Information-Preserving Cache(query sensitivity)
|
|
167
|
+
候选 C:Topology-Preserving Cache(图桥接节点保留)
|
|
168
|
+
|
|
169
|
+
第五步 Critic 审查:
|
|
170
|
+
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
|
|
171
|
+
建议:优先 A,B 作轻量 gate
|
|
179
172
|
```
|
|
180
173
|
|
|
181
174
|
---
|
|
182
175
|
|
|
183
|
-
## 三层渐进式披露
|
|
184
|
-
|
|
185
|
-
| 层 | 内容 | 加载时机 |
|
|
186
|
-
|----|------|---------|
|
|
187
|
-
| 常驻触发层 | `skills/math-research-activator/SKILL.md` + 各武器简短 `description` | 自动 / 手动触发即载 |
|
|
188
|
-
| 方法论层 | `references/agentic-workflow.md`(Human-in-the-Agent-Loop)、`references/gpu-friendly-math.md`(八维门) | 激活器按需引用 |
|
|
189
|
-
| 书籍激活层 | `references/books/*.md` × 7(现代数学结构蒸馏稿) | 按问题类型按需加载 |
|
|
190
|
-
|
|
191
|
-
**深挖回查**:蒸馏稿自足可用;需原文全保真且本机有 `math_book/<PDF>` 时,让 Agent 自动 `pdftotext` + grep + Read 命中页(不依赖预埋锚点)。PDF 绝不打包进 npm / git(版权 + 110MB)。
|
|
192
|
-
|
|
193
|
-
---
|
|
194
|
-
|
|
195
176
|
## 目录结构
|
|
196
177
|
|
|
197
178
|
```
|
|
198
179
|
math-skill/
|
|
199
|
-
├──
|
|
200
|
-
|
|
201
|
-
├──
|
|
202
|
-
├──
|
|
203
|
-
│ ├──
|
|
204
|
-
│
|
|
205
|
-
├──
|
|
206
|
-
│ ├──
|
|
207
|
-
│ ├──
|
|
208
|
-
│ ├──
|
|
209
|
-
│ └──
|
|
210
|
-
├──
|
|
211
|
-
├──
|
|
212
|
-
├──
|
|
213
|
-
├──
|
|
180
|
+
├── skills/
|
|
181
|
+
│ └── math-research-activator/ # 总控:意图诊断 + 路由
|
|
182
|
+
├── lenses/ # 15 个思想透镜(推理方法论)
|
|
183
|
+
├── knowledge-base/ # 数学知识库(按领域组织)
|
|
184
|
+
│ ├── matrix-analysis/ # 矩阵分析(5 卡片)
|
|
185
|
+
│ ├── optimization/ # 最优化(5 卡片)
|
|
186
|
+
│ ├── differential-geometry/ # 微分几何(6 卡片)
|
|
187
|
+
│ ├── lie-theory/ # 李理论(5 卡片)
|
|
188
|
+
│ ├── topology/ # 拓扑(3 卡片)
|
|
189
|
+
│ ├── probability/ # 概率与信息(5 卡片)
|
|
190
|
+
│ └── information-geometry/ # 信息几何(2 卡片)
|
|
191
|
+
├── design-patterns/ # 设计翻译层(按 AI 组件组织)
|
|
192
|
+
│ ├── attention/ # 注意力机制(5 模式)
|
|
193
|
+
│ ├── loss/ # 损失函数(5 模式)
|
|
194
|
+
│ ├── routing/ # 路由(4 模式)
|
|
195
|
+
│ ├── representation/ # 表示(4 模式)
|
|
196
|
+
│ └── compression/ # 压缩(4 模式)
|
|
197
|
+
├── references/ # 参考层
|
|
198
|
+
│ ├── books/ # 7 本书蒸馏稿
|
|
199
|
+
│ ├── gpu-friendly-math.md # GPU 八维验收门
|
|
200
|
+
│ ├── agentic-workflow.md # 协作方式
|
|
201
|
+
│ └── inspiration.md # 灵感来源
|
|
202
|
+
├── agents/math-critic.md # 数学-工程双重批判器
|
|
203
|
+
├── commands/ask.md # /ask 手动入口
|
|
204
|
+
├── math_book/ # 本地 PDF(不发布)
|
|
214
205
|
└── README.md / LICENSE
|
|
215
206
|
```
|
|
216
207
|
|
|
217
208
|
---
|
|
218
209
|
|
|
219
|
-
##
|
|
220
|
-
|
|
221
|
-
每个 `skills/*/SKILL.md`(v2 单一研究 / 算法路径):
|
|
222
|
-
|
|
223
|
-
1. **核心原则** + blockquote 子节 **数学形式化**(定义 / 定理 / 公式)
|
|
224
|
-
2. **GPU 友好性(横切检查)**——本武器结构如何映射 GPU,过八维门
|
|
225
|
-
3. **不适用场景** / **何时使用**(研究触发,含算法 / 算子设计用法)
|
|
226
|
-
4. **方法流程**——单一科研路径(保留全部数学)
|
|
227
|
-
5. **常见错误**——含一行 GPU 可算性
|
|
228
|
-
6. **操作规程**——单一输出格式,末尾 `[GPU 可行性]` 项
|
|
229
|
-
7. **与其他 skill 的关系**——含「现代数学激活」行,指向 `references/books/*`
|
|
230
|
-
|
|
231
|
-
每个武器还配 `original-texts.md`(数学出处与经典文献)。审视产出可交 `agents/math-critic.md`(18 维,含 GPU 可行性 + 现代数学激活)二次把关。
|
|
232
|
-
|
|
233
|
-
---
|
|
210
|
+
## 推荐书目
|
|
234
211
|
|
|
235
|
-
|
|
212
|
+
| # | 书名 | 作者 | 出版社 / 版次 | 年份 | ISBN | 蒸馏文件 |
|
|
213
|
+
|---|------|------|-------------|------|------|---------|
|
|
214
|
+
| 1 | *Contemporary Abstract Algebra* | Joseph A. Gallian | Brooks/Cole, Cengage, 8th ed. | 2013 | 978-1-133-59971-5 | `abstract-algebra.md` |
|
|
215
|
+
| 2 | *The Rising Sea: Foundations of Algebraic Geometry* | Ravi Vakil | Princeton University Press | 2025 | 978-0-691-26866-8 | `algebraic-geometry-rising-sea.md` |
|
|
216
|
+
| 3 | *Manifolds and Differential Geometry* | Jeffrey M. Lee | AMS, Graduate Studies in Math Vol. 107 | 2009 | 978-0-8218-4815-9 | `differential-geometry.md` |
|
|
217
|
+
| 4 | *Matrix Analysis* | Roger A. Horn, Charles R. Johnson | Cambridge University Press, 2nd ed. | 2013 | 978-0-521-83940-2 | `matrix-analysis.md` |
|
|
218
|
+
| 5 | *A micro Lie theory for state estimation in robotics* | Joan Solà et al. | arXiv:1812.01537v9 | 2021 | — | `micro-lie-theory.md` |
|
|
219
|
+
| 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` |
|
|
220
|
+
| 7 | *Introduction to Smooth Manifolds* | John M. Lee | Springer, GTM 218, 2nd ed. | 2013 | 978-1-4419-9981-8 | `smooth-manifolds.md` |
|
|
236
221
|
|
|
237
|
-
|
|
222
|
+
蒸馏文件已随 npm 包发布。如需全保真原文,将 PDF 放入 `math_book/` 文件夹即可。
|
|
238
223
|
|
|
239
224
|
---
|
|
240
225
|
|
|
241
|
-
##
|
|
242
|
-
|
|
243
|
-
以下 7 本现代数学教材是本 skill 的「深层弹药库」。每本书配有蒸馏文件(`references/books/*.md`),已随 npm 包发布,自足可用。如需全保真原文查阅,可将对应 PDF 放入项目根目录的 `math_book/` 文件夹——Agent 会自动用 `pdftotext` + grep 定位原文页面。
|
|
244
|
-
|
|
245
|
-
| # | 书名 | 作者 | 出版社 / 版次 | 年份 | ISBN | 蒸馏文件 | 本地 PDF |
|
|
246
|
-
|---|------|------|-------------|------|------|---------|---------|
|
|
247
|
-
| 1 | *Contemporary Abstract Algebra* | Joseph A. Gallian | Brooks/Cole, Cengage, 8th ed. | 2013 | 978-1-133-59971-5 | `abstract-algebra.md` | `Contemporary Abstract Algebra.pdf` |
|
|
248
|
-
| 2 | *The Rising Sea: Foundations of Algebraic Geometry* | Ravi Vakil | Princeton University Press | 2025 | 978-0-691-26866-8 | `algebraic-geometry-rising-sea.md` | `The Rising Sea Foundations of Algebraic Geometry.pdf` |
|
|
249
|
-
| 3 | *Manifolds and Differential Geometry* | Jeffrey M. Lee | AMS, Graduate Studies in Math Vol. 107 | 2009 | 978-0-8218-4815-9 | `differential-geometry.md` | `Manifolds and Differential Geometry.pdf` |
|
|
250
|
-
| 4 | *Matrix Analysis* | Roger A. Horn, Charles R. Johnson | Cambridge University Press, 2nd ed. | 2013 | 978-0-521-83940-2 | `matrix-analysis.md` | `Matrix Analysis.pdf` |
|
|
251
|
-
| 5 | *A micro Lie theory for state estimation in robotics* | Joan Solà, Jérémie Deray, Dinesh Atchuthan | arXiv:1812.01537v9 | 2021 | — | `micro-lie-theory.md` | `A micro Lie theory.pdf` |
|
|
252
|
-
| 6 | *An Introduction to Optimization, With Applications to Machine Learning* | Edwin K. P. Chong, Wu-Sheng Lu, Stanisław H. Żak | John Wiley & Sons, 5th ed. | 2024 | 978-1-119-87763-9 | `optimization-ml.md` | `An Introduction to Optimization With Applications to Machine Learning.pdf` |
|
|
253
|
-
| 7 | *Introduction to Smooth Manifolds* | John M. Lee | Springer, GTM 218, 2nd ed. | 2013 | 978-1-4419-9981-8 | `smooth-manifolds.md` | `Introduction to Smooth Manifolds.pdf` |
|
|
226
|
+
## 变更日志
|
|
254
227
|
|
|
255
|
-
|
|
256
|
-
- 蒸馏文件(`references/books/*.md`)已随 npm 包发布,无需额外操作。
|
|
257
|
-
- 如需全保真原文:将上表中对应 PDF 文件放入 `math_book/` 文件夹,Agent 会自动搜索定位。
|
|
258
|
-
- PDF 绝不通过 npm / git 分发(版权原因),需自行获取。
|
|
228
|
+
### v3.0.0 — 数学研究操作系统
|
|
259
229
|
|
|
260
|
-
|
|
230
|
+
**架构重构**:从"思想武器库"升级为"数学参谋部"——三层正交架构:
|
|
261
231
|
|
|
262
|
-
|
|
232
|
+
- **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
|
|
233
|
+
- **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
|
|
234
|
+
- **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
|
|
235
|
+
- **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)
|
|
236
|
+
- **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)
|
|
263
237
|
|
|
264
238
|
### v2.1.0 — 完整双语支持
|
|
265
|
-
-
|
|
266
|
-
- **自动语言路由**:基于用户消息语言自动检测,路由到对应语言版本。**中文用户只加载中文件,英文用户只加载英文件**——不会消耗双倍 token。
|
|
267
|
-
- **命令一致**:中英文用户使用完全相同的命令(`/ask`、`/optimization` 等),无需记忆不同入口。
|
|
268
|
-
- **路由优化**:command 文件采用语言优先判断,直接路由到目标语言版本,避免多余文件加载。
|
|
269
|
-
- **书目推荐**:README 新增「推荐书目」章节,列出 7 本现代数学教材的完整出版信息(作者、出版社、版次、ISBN)及 PDF 放置说明。
|
|
270
|
-
- **蒸馏文件增强**:7 个 `references/books/*.md` 的「深挖入口」补充完整书目信息与 PDF 启用方式。
|
|
271
|
-
- **语言切换升级**:从手动 `in English` 后缀改为自动检测用户消息语言,零配置。
|
|
239
|
+
- 全面双语(37 个 .en.md 文件)、自动语言路由、命令一致、token 保障
|
|
272
240
|
|
|
273
241
|
### v2.0.1
|
|
274
|
-
-
|
|
275
|
-
- **新增排除门(Gate 0)**:代码审查、debug、参数传递链核查、重构、调参、loss 实现修改等纯工程任务明确列入排除列表,优先级最高。
|
|
276
|
-
- **环境信号收窄**:仅有 `model.py`、`trainer.py`、`config.json` 等常规 ML 工程文件不再构成环境信号;需要架构核心代码(attention/transformer/MoE、CUDA/Triton kernel)或研究笔记。
|
|
277
|
-
- **description 字段更新**:显式标注"不触发于"场景列表,减少 AI 平台的 skill metadata 误匹配。
|
|
242
|
+
- 收紧自动触发条件、新增排除门、环境信号收窄
|
|
278
243
|
|
|
279
244
|
### v2.0.0
|
|
280
|
-
-
|
|
245
|
+
- 16 思想武器、现代数学激活层、GPU 八维横切
|
|
281
246
|
|
|
282
247
|
### v1.0.0
|
|
283
|
-
-
|
|
284
|
-
- 十五个 `skills/*/SKILL.md`(含核心原则、不适用场景、方法流程、常见错误、操作规程)+ 对应 `original-texts.md`(数学出处与经典文献)。
|
|
285
|
-
- 十五个手动触发的 slash 命令入口(`commands/*.md`)。
|
|
286
|
-
- `knowledge-base/overview.md`(三大支柱 / 主要分支 / 知识层次 / 武器映射)。
|
|
287
|
-
- `agents/math-critic.md` 审视 Agent。
|
|
288
|
-
- 校验脚本 `tests/{validate.sh, validate.ps1}`。
|
|
289
|
-
- 发布至 npm(`math-skill`),MIT 协议。
|
|
248
|
+
- 初始发布:十五思想武器 + 科研与生活双路径
|
|
290
249
|
|
|
291
250
|
---
|
|
292
251
|
|
|
@@ -298,7 +257,7 @@ MIT License. 详见 `LICENSE`。
|
|
|
298
257
|
|
|
299
258
|
## 贡献
|
|
300
259
|
|
|
301
|
-
欢迎提交 Issue 和 Pull Request
|
|
260
|
+
欢迎提交 Issue 和 Pull Request!
|
|
302
261
|
|
|
303
262
|
---
|
|
304
263
|
|
package/agents/math-critic.en.md
CHANGED
|
@@ -130,11 +130,11 @@ The following dimensions correspond to the fifteen mathematical thinking toolkit
|
|
|
130
130
|
- Were multiple candidate structures enumerated (rather than only one)?
|
|
131
131
|
- If uncertain about which dimensions to review, first invoke `/ask` to have the activator recommend the 3-5 most suitable review dimensions.
|
|
132
132
|
|
|
133
|
-
### 17. GPU-Feasibility Review ↔ `references/gpu-friendly-math.md`
|
|
133
|
+
### 17. GPU-Feasibility Review ↔ `references/gpu-friendly-math.en.md`
|
|
134
134
|
|
|
135
135
|
> **Mandatory** when the deliverable involves algorithm/operator/training/GPU design. Corresponds to the second gate of the "dual-acceptance gate."
|
|
136
136
|
|
|
137
|
-
- Does the deliverable pass the **eight dimensions** of `references/gpu-friendly-math.md`? Tensorization / GEMM-mappability / Complexity (sub-quadratic) / Memory
|
|
137
|
+
- Does the deliverable pass the **eight dimensions** of `references/gpu-friendly-math.en.md`? Tensorization / GEMM-mappability / Complexity (sub-quadratic) / Memory & KV-Cache / Low-precision stability / Parallelism & Communication / Sparse structure / Operator fusion -- rate each as "friendly / retrofittable / unfriendly."
|
|
138
138
|
- Are there structures that are "mathematically beautiful but not computable"? (Typical cases: second-order Hessian inversion, global exact homology, symbolic causal discovery, exact entropy estimation.) Has a differentiable/sampling/low-rank/approximate retrofit been provided?
|
|
139
139
|
- Are the inverse transforms and numerical components stable (condition number, ill-conditioning)?
|
|
140
140
|
- Have memory and communication been assessed (KV-Cache, distributed all-reduce, optimizer state precision)?
|
package/agents/math-critic.md
CHANGED
|
@@ -26,7 +26,7 @@
|
|
|
26
26
|
|
|
27
27
|
## 审视维度
|
|
28
28
|
|
|
29
|
-
|
|
29
|
+
以下维度与十五种数学思想透镜及激活器对应,并新增 GPU 可行性与现代数学激活两维。**不需要机械地逐一检查所有维度**——应根据问题性质和用户关注点,选择最相关的维度深入审视,其余可简略提及或跳过。若产出涉及算法/算子/GPU 设计,**第 17(GPU)与第 18(现代数学激活)维为强制检查项**。
|
|
30
30
|
|
|
31
31
|
### 1. 假设审查 / Assumption Review ↔ 📐 公理化思想
|
|
32
32
|
|
|
@@ -127,8 +127,8 @@
|
|
|
127
127
|
### 16. 工具选择与流程审视 / Tool-Selection & Flow Review ↔ 🧭 math-research-activator
|
|
128
128
|
|
|
129
129
|
- 审视维度的选择本身是否最优?是否遗漏了关键维度?
|
|
130
|
-
-
|
|
131
|
-
- (v2)是否遵循激活器主流程:**诊断 → 现代数学结构映射 →
|
|
130
|
+
- 是否选择了最适合问题性质的思想透镜,而非仅仅选择最熟悉的?
|
|
131
|
+
- (v2)是否遵循激活器主流程:**诊断 → 现代数学结构映射 → 思想透镜路由 → GPU 筛选**?是否跳过了诊断就堆数学科普?
|
|
132
132
|
- 是否枚举了多个候选结构(而非只给一个)?
|
|
133
133
|
- 若不确定该审视哪些维度,先调用 `/ask` 让激活器推荐最合适的 3–5 个审视维度。
|
|
134
134
|
|
|
@@ -136,7 +136,7 @@
|
|
|
136
136
|
|
|
137
137
|
> 产出涉及算法/算子/训练/GPU 设计时为**强制项**。对应「双验收门」的第二道门。
|
|
138
138
|
|
|
139
|
-
- 产出是否过 `references/gpu-friendly-math.md` 的**八维**?张量化 / GEMM
|
|
139
|
+
- 产出是否过 `references/gpu-friendly-math.md` 的**八维**?张量化 / GEMM 可映射 / 复杂度(亚二次)/ 显存与 KV-Cache / 低精度稳定 / 并行与通信 / 稀疏结构 / 算子融合——逐项给「友好/可改造/不友好」。
|
|
140
140
|
- 是否存在「数学美但不可算」的结构?(典型:二阶法 Hessian 求逆、全局精确同调、符号因果发现、精确熵估计)——是否给出了可微/采样/低秩/近似改造?
|
|
141
141
|
- 逆变换/数值部分是否稳定(条件数、病态)?
|
|
142
142
|
- 显存与通信是否被评估(KV-Cache、分布式 all-reduce、optimizer state 精度)?
|
|
@@ -165,7 +165,7 @@
|
|
|
165
165
|
### 实现阶段
|
|
166
166
|
|
|
167
167
|
7. **定位修正点**:从审视发现的问题中,确定哪些需要具体实现方案。
|
|
168
|
-
8.
|
|
168
|
+
8. **选择思维工具**:针对每个修正点,选择最合适的数学思想透镜作为实现工具。
|
|
169
169
|
9. **给出实现方案**:为每个修正点提供具体的推导步骤、证明框架、算法设计或模型改进方案;若原方案不可算,给出可微/采样/低秩/近似改造方向。
|
|
170
170
|
|
|
171
171
|
## 输出格式
|
|
@@ -208,7 +208,7 @@
|
|
|
208
208
|
### 实现部分
|
|
209
209
|
|
|
210
210
|
#### 问题一:[必须/应当改正的问题标题]
|
|
211
|
-
- 思维工具: [
|
|
211
|
+
- 思维工具: [使用的数学思想透镜]
|
|
212
212
|
- 实现方案: [具体推导步骤 / 证明框架 / 算法设计 / 模型改进方案]
|
|
213
213
|
- 验证方式: [如何确认修正有效]
|
|
214
214
|
|
|
@@ -216,7 +216,7 @@
|
|
|
216
216
|
- [同上结构,根据问题数量灵活增减]
|
|
217
217
|
|
|
218
218
|
### 思维工具索引
|
|
219
|
-
- [
|
|
219
|
+
- [本次审视与实现中实际使用的思想透镜及其在哪个环节发挥作用]
|
|
220
220
|
|
|
221
221
|
### 总体评估
|
|
222
222
|
- [是否达标 + 主要修正路径 + 双验收门是否通过]
|
|
@@ -225,7 +225,7 @@
|
|
|
225
225
|
说明:
|
|
226
226
|
- 审视部分的"实现方向"是简要指引,实现部分的"实现方案"才是完整展开。两者呼应但不重复。
|
|
227
227
|
- 若某个问题无需深入实现(如纯粹的逻辑跳跃只需指出即可),实现部分可省略该条目。
|
|
228
|
-
- "思维工具索引"
|
|
228
|
+
- "思维工具索引"汇总本次实际动用的思想透镜,而非机械列出全部。
|
|
229
229
|
- 审视维度的选择因问题而异——审查论文假设时公理化思想是核心,评估算法时算法与计算思想+GPU 可行性是核心,不必每次都从假设开始。
|
|
230
230
|
|
|
231
231
|
## 原则
|
package/commands/ask.md
CHANGED
|
@@ -1,18 +1,11 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: ask
|
|
3
3
|
description: |
|
|
4
|
-
|
|
5
|
-
English:
|
|
4
|
+
数学研究操作系统入口:自动诊断用户意图,路由到思想透镜、数学知识库或设计翻译层。
|
|
5
|
+
English: Math Research OS entry: auto-diagnose user intent, route to thinking lenses, math knowledge base, or design translation layer.
|
|
6
6
|
---
|
|
7
7
|
|
|
8
|
-
若用户消息为英文,读取并遵循 `../skills/math-research-activator/SKILL.en.md`;否则读取并遵循 `../skills/math-research-activator/SKILL.md
|
|
8
|
+
若用户消息为英文,读取并遵循 `../skills/math-research-activator/SKILL.en.md`;否则读取并遵循 `../skills/math-research-activator/SKILL.md`。
|
|
9
9
|
|
|
10
10
|
当前问题:
|
|
11
11
|
$ARGUMENTS
|
|
12
|
-
|
|
13
|
-
输出要求(遵循激活器操作规程):
|
|
14
|
-
1. **[诊断]** 一句话点明问题核心特征/瓶颈(互动性/不确定性/约束/结构/动态/复杂度/显存/数值/并行)。
|
|
15
|
-
2. **[映射]** 枚举可迁移的现代数学结构候选(≥2 个,标注来自哪本书 `../references/books/*`);若与算法/算子设计无关可略。
|
|
16
|
-
3. **[武器路由]** 推荐 1–3 个思想武器,标主/辅 + 触发命令(如 `/optimization`);多个时说明组合顺序。
|
|
17
|
-
4. **[GPU 筛选]** 候选过 `../references/gpu-friendly-math.md` 八维,给「友好/可改造/不友好」+ 改造建议;若与硬件无关可略。
|
|
18
|
-
5. **[结论]** 保留通过双验收门的候选;标注哪些武器不适用;若不适合任何武器,明确说明。
|