docs(status): 记入分工硬规矩（决策 47）+「明天从这里开始」；test_solve 改逐条 skip

- STATUS.md：新增决策 47 —— 算法一律由用户本人写（即便用户改口也不代写），
  工程事务（入口/校验、tests/、lint、docstring、卡片、STATUS/CHANGELOG）由 Codex 写；
  L0 计数 9/12 -> 10/12；skip 说明 37 -> 34 条。
- STATUS.md：新增「⭐ 明天从这里开始」区块 —— 第一个要写的文件是
  src/mcm_toolkit/solve/simulate.py 的 monte_carlo（L0 11/12，S 档），
  含参考契约、向量化要求、get_rng 口径、三条测试建议、卡片路径与一个待拍板口径。
- tests/test_solve.py：模块级 pytestmark 拆成 9 条逐条 skip（决策 26、易错点 9）。
- CHANGELOG.md：同步记录。

校验：pytest 177 收集 / 143 passed / 34 skipped / 0 xfail；ruff 0；pyright 0。

tests/test_solve.py

@@ -5,9 +5,10 @@ from __future__ import annotations
 import numpy as np
 import pytest
 
-pytestmark = pytest.mark.skip(reason="未实现：见 docs/03-roadmap.md L0/L1")
+_NOT_IMPLEMENTED = "未实现：见 docs/03-roadmap.md L0/L1"
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_monte_carlo_integral_converges_to_analytic_value():
     """∫₀¹ x² dx = 1/3。n=2e5 时误差应 < 0.01。"""
     from mcm_toolkit.solve import monte_carlo_integral
@@ -16,6 +17,7 @@ def test_monte_carlo_integral_converges_to_analytic_value():
     assert abs(r.data - 1 / 3) < 0.01
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_monte_carlo_probability_of_standard_normal():
     """P(Z > 0) = 0.5，n=5000 时误差应 < 0.05。"""
     from mcm_toolkit.solve import monte_carlo_probability
@@ -29,6 +31,7 @@ def test_monte_carlo_probability_of_standard_normal():
     assert abs(r.metrics["probability"] - 0.5) < 0.05
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_monte_carlo_is_reproducible():
     from mcm_toolkit.solve import monte_carlo_probability
 
@@ -38,6 +41,7 @@ def test_monte_carlo_is_reproducible():
     assert a.metrics["probability"] == b.metrics["probability"]
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_markov_steady_state_two_state_chain():
     """P=[[0.9,0.1],[0.2,0.8]] 的平稳分布是 [2/3, 1/3]。"""
     from mcm_toolkit.solve import markov_steady_state
@@ -46,6 +50,7 @@ def test_markov_steady_state_two_state_chain():
     assert np.allclose(r.data, [2 / 3, 1 / 3], atol=1e-6)
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_knapsack_dp_known_optimum():
     from mcm_toolkit.solve import knapsack_dp
 
@@ -54,6 +59,7 @@ def test_knapsack_dp_known_optimum():
     assert np.isclose(r.metrics["total_weight"], 7.0)
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_linear_program_basic():
     from mcm_toolkit.solve import linear_program
 
@@ -62,6 +68,7 @@ def test_linear_program_basic():
     assert np.isclose(r.metrics["objective"], 4.0)
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_mm1_metrics_closed_form():
     from mcm_toolkit.solve import mm1_metrics
 
@@ -70,6 +77,7 @@ def test_mm1_metrics_closed_form():
     assert np.isclose(r.metrics["L"], 2.0, rtol=1e-6)
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_mm1_rejects_unstable_system():
     """λ >= μ 时系统不稳定，应 success=False 而不是返回 inf。"""
     from mcm_toolkit.solve import mm1_metrics
@@ -77,6 +85,7 @@ def test_mm1_rejects_unstable_system():
     assert mm1_metrics(arrival_rate=3, service_rate=3).success is False
 
 
+@pytest.mark.skip(reason=_NOT_IMPLEMENTED)
 def test_simulated_annealing_finds_quadratic_minimum():
     from mcm_toolkit.solve import simulated_annealing