菜单
Define reproducible demand-side-management comparisons with frozen baselines, controls, comfort constraints, weather, and tariff semantics.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/bbartling/py-bacnet-stacks-playground --skill dsm-experiment-design命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Calibrate an existing-building EnergyPlus model against measured energy and operational evidence using auditable Guideline-14-style scorecards.
Build or modify a defensible EnergyPlus seed model from building evidence, including geometry, schedules, HVAC mapping, and controlled IDF changes.
Route shared EnergyPlus work to the right intake, authoring, calibration, tariff, results, or DSM procedure.
正在显示 SKILL.md
| name | dsm-experiment-design |
| description | Define reproducible demand-side-management comparisons with frozen baselines, controls, comfort constraints, weather, and tariff semantics. |
Compare DSM strategies against a reproducible baseline without changing weather, initial state, occupancy, tariff semantics or unrelated model parameters between arms.
If using a shaped RL reward, version it separately from physical/economic evaluation. A reward may include readiness, comfort, energy, demand, and action-smoothness terms, but it must not replace the published readiness constraint or tariff accounting. Preserve incumbent and candidate baseline definitions; do not relabel a modeled baseline as verified BAS behavior without source evidence.
Report kWh, peak kW, time of peak, comfort/unmet hours and cost separately. A lower peak with unacceptable comfort or a large energy penalty is not automatically a better strategy.