commit a62363aca3cf3484331a15e29ce805419f38a53e
Author: Zhongwei Li <lizhongwei.nkcs@gmail.com>
Date:   Sun Nov 30 08:35:31 2025 +0800

    Initial commit

diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
new file mode 100644
index 0000000..67411e1
--- /dev/null
+++ b/.claude-plugin/plugin.json
@@ -0,0 +1,12 @@
+{
+  "name": "Hydrology",
+  "description": "水文学研究SKILLs",
+  "version": "0.0.0-2025.11.28",
+  "author": {
+    "name": "Dongdong Kong",
+    "email": "kongdd.sysu@gmail.com"
+  },
+  "skills": [
+    "./skills/hydro-forecast"
+  ]
+}
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..00a0a60
--- /dev/null
+++ b/README.md
@@ -0,0 +1,3 @@
+# Hydrology
+
+水文学研究SKILLs
diff --git a/plugin.lock.json b/plugin.lock.json
new file mode 100644
index 0000000..5c304fc
--- /dev/null
+++ b/plugin.lock.json
@@ -0,0 +1,48 @@
+{
+  "$schema": "internal://schemas/plugin.lock.v1.json",
+  "pluginId": "gh:kongdd/Skills_for_Your_AI_Student:hydrology",
+  "normalized": {
+    "repo": null,
+    "ref": "refs/tags/v20251128.0",
+    "commit": "a9f0b3f9657e68543b463ba8b22395ac0a791141",
+    "treeHash": "0eeb6497b4536ed66cd3fd541632163de017b2ae4b73bcf738bcef3791ddb332",
+    "generatedAt": "2025-11-28T10:19:55.420120Z",
+    "toolVersion": "publish_plugins.py@0.2.0"
+  },
+  "origin": {
+    "remote": "git@github.com:zhongweili/42plugin-data.git",
+    "branch": "master",
+    "commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390",
+    "repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data"
+  },
+  "manifest": {
+    "name": "Hydrology",
+    "description": "水文学研究SKILLs"
+  },
+  "content": {
+    "files": [
+      {
+        "path": "README.md",
+        "sha256": "4b3f6fb3334be58ff87e354f79cd3d24c89ce33c2b3d970cba15eadb743423fa"
+      },
+      {
+        "path": ".claude-plugin/plugin.json",
+        "sha256": "350d3093230a5710bf22a6e34be823758a740d18e765e86ab50a2148a6b23284"
+      },
+      {
+        "path": "skills/hydro-forecast/examples.jl",
+        "sha256": "2962c429ca92208da63123ab7234245e19b7710d58fca256f364a741b19fac05"
+      },
+      {
+        "path": "skills/hydro-forecast/SKILL.md",
+        "sha256": "8d38eb768b6bb886729500af7c9e92a951f7edd26186bd91dc62b7c9e3396506"
+      }
+    ],
+    "dirSha256": "0eeb6497b4536ed66cd3fd541632163de017b2ae4b73bcf738bcef3791ddb332"
+  },
+  "security": {
+    "scannedAt": null,
+    "scannerVersion": null,
+    "flags": []
+  }
+}
\ No newline at end of file
diff --git a/skills/hydro-forecast/SKILL.md b/skills/hydro-forecast/SKILL.md
new file mode 100644
index 0000000..9ae68e1
--- /dev/null
+++ b/skills/hydro-forecast/SKILL.md
@@ -0,0 +1,125 @@
+---
+name: hydro-forecast
+description: 
+---
+
+# 1 运行环境说明
+
+- 在Julia中运行
+
+- 在julia中首先加载包，`using HydroTools`
+
+- 若没有包加载出错，则安装之，`using Pkg; Pkg.add("HydroTools")`
+
+
+## 说明
+
+先不要立即执行该skills，提醒用户输入的数据的格式。用户需要整理好的数据路径即可。
+
+```
+
+```
+
+`model`模型选择
+
++ MarrMot
++ XAJ
++ TCN
++ LSTM
++ KAN
+
+如果复杂、参数比较多的模型：要求用户输入模型参数`json`文件。
+按照如下示例
+
+```json
+{
+    "clumping_index": 0.62,
+    "LAI_max_o": 4.5,
+    "LAI_max_u": 2.4,
+    "z00": 1.33,
+    "mass_overstory": 35,
+    "mass_understory": 10,
+    "root_depth": 0.6,
+    "α_canopy_vis": 0.035,
+    "α_canopy_nir": 0.23,
+    "r_root_decay": 0.95,
+    "minimum_stomatal_resistance": 150,
+    "z_canopy_o": 20,
+    "z_canopy_u": 3,
+    "g1_w": 8,
+    "VCmax25": 62.5,
+    "leaf_resp_co": 0.0015,
+    "stem_resp_co": 0.0020,
+    "root_resp_co": 0.0020,
+    "fine_root_resp_co": 0.003,
+    "N_leaf": 4.45,
+    "slope_Vc": 0.33152
+}
+```
+
+## 1.1 任务说明
+
+### 1.1.1 `framework`：
+
+```julia
+
+function hydro_forecast(f; model, outdir)
+  res = ...
+
+  fwrite(res.output, ...)
+  fwrite(res.gof, ...)
+  fwrite(res.info_flood, ...)
+  fwrite(res.dat_flood, ...)
+  fwrite(res.evaluation, ...)
+end
+
+function hydro_forecast(X::AbstractArray, Y::AbstractArray; model::Function, outdir = "OUTPUT")
+  mkpath(outdir)
+  res; # return a NamedTuple
+end
+```
+
+**输入**：X, Y, model
+
+**输出**：Qsim, GOF, Pass_rate
+
+  + `output`: 三类数据集的输出，A DataFrame with columns of `date`, `Qsim`, 
+  + `gof`: 三类数据的拟合优度
+  + `info_flood`: 洪水场次信息，`id`, `time_beg`, `time_end`, `duration`, `Q_peak`, `Q_min`
+  + `dat_flood`：洪水场次的驱动数据，
+  + `evaluation`: 每个洪水场次上的模拟优度, csv
+
+**绘图**：
+
+  + 交给他绘图的函数，数据
+
+**总结**：
+
+  + `evaluation`总结模型预报精度 （`AI执行`）
+
+
+**内部模块设计**：
+
+  + `flood_division`: 采用R语言，划分洪水场次
+
+  + `划分数据集`：train, test, valid
+
+  + `loss`: 根据拟合优度指标去设计loss，例如KGE, NSE, RMSE，注意loss越小越优。根据loss去优选模型参数。
+ 
+  + `evaluation`: 在三种数据集，train, test, valid。每个洪水场次的洪峰、峰现时间合格率。
+
+
+### 1.1.2 `model`：水文模型、LSTM、TCN、KAN
+
+  ```julia
+  Ysim = Model(X, Y; params, state) # Lux的设计哲学
+  ```
+
+### 1.1.3 文件保存
+
+文件保存采用Julia包`DataFrames`，`RTableTools`
+
+```julia
+using RTableTools
+fwrite(df, "out.csv") # df is a DataFrame
+```
diff --git a/skills/hydro-forecast/examples.jl b/skills/hydro-forecast/examples.jl
new file mode 100644
index 0000000..38f4c1e
--- /dev/null
+++ b/skills/hydro-forecast/examples.jl
@@ -0,0 +1,22 @@
+using HydroTools
+using Dates
+
+lat = 20.0
+doy = 120
+
+ws = HourAngleSunSet(lat, doy)
+# doy
+cal_Rsi_toa(lat, doy)
+
+# date
+date = Date(2010, 6, 12)
+doy = dayofyear(date)
+cal_Rsi_toa(lat, doy)
+
+# datetime
+time = DateTime(2010, 6, 12)
+doy = dayofyear(date)
+Rsi = cal_Rsi_toa(lat, doy) # [MJ d-1 m-2]
+
+
+MJ2W(Rsi) # [MJ d-1 m-2] to [W m-2]