菜单
OpenStudio Analysis Framework (OSAF) workflows, algorithm selection, validation, submission, and result download. Use when the user asks about OSAF, OpenStudio Server analyses, sampling, sweeps, optimization, calibration, or OSA JSON configs.
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。
基于 SOC 职业分类
Add custom EMS control or reporting logic (EnergyPlus Python Plugins) — setpoint resets, schedule overrides, supervisory control, custom metrics. Use when no packaged HVAC/schedule tool covers the control logic the user wants.
Create, test, and apply custom OpenStudio measures. Use when user asks to "write a measure", "create a custom measure", "modify the model with Ruby/Python code", or needs logic beyond what existing tools provide.
Generate comprehensive energy analysis report from simulation results. Use when user asks for "energy report", "full results", or "detailed analysis".
OpenStudio model object relationships, tool dependencies, and common error patterns. Use when building or modifying models to ensure correct tool ordering.
Run model quality checks before simulation. Use when user asks to "check the model", "validate", "QA/QC", or before running a simulation.
Create a complete building model from scratch — geometry, envelope, loads, HVAC, weather, and simulation. Use when user wants to "create a building", "build a model", or "start a new model".
| name | osaf-analysis |
| description | OpenStudio Analysis Framework (OSAF) workflows, algorithm selection, validation, submission, and result download. Use when the user asks about OSAF, OpenStudio Server analyses, sampling, sweeps, optimization, calibration, or OSA JSON configs. |
| disable-model-invocation | true |
Use this skill when working with OpenStudio Server / OSAF analysis JSON, support ZIPs, sampling sweeps, optimization, calibration, or server smoke tests.
For “list OSAF algorithms” or “what is this algorithm best for”, call:
openstudio_analysis_algorithms
Filter by category or analysis type when useful:
openstudio_analysis_algorithms category="sampling"
openstudio_analysis_algorithms category="lhs"
The tool returns analysis types, categories, best-fit use cases, caveats, typical algorithm keys, and the correct start sequence.
Common choices:
| Need | Prefer |
|---|---|
| Check server/config/package with one run | single_run |
| One-variable or general parameter sweep | lhs |
| Full-factorial style experiment with 2+ variables | doe |
| Screening many variables cheaply | morris |
| Formal variance-based sensitivity | sobol |
| Multi-objective Pareto calibration/design | nsga_nrel or spea_nrel |
| Continuous calibration/search | pso or rgenoud |
| Debugging repeatability or bounds | repeat_run or preflight |
Do not use DOE for only one real variable. Use LHS for one-variable sweeps.
For existing OpenStudio-server/spec OSA JSON configs, call:
openstudio_analysis_validate_osa_json
Raw validation is schema-focused by default and accepts legacy server config
patterns. Use require_foundational_measures=true when validating an
MCP-generated analysis that is about to be packaged/submitted.
Create OSA JSON from measures:
openstudio_analysis_create_osa_json_from_measures
Before uploading a support ZIP:
openstudio_analysis_prepare_package
openstudio_analysis_validate_package
Submit and upload:
openstudio_analysis_submit
Generated analysis JSON files and support ZIP packages always include the foundational measures:
Default output variables are exported and visualized so OSAF plots can show OpenStudio Results whole-building metrics and electricity/natural gas end uses.
OSAF sampled analyses need two start actions:
Prefer:
openstudio_analysis_start_sampled_run
For a single-run smoke test, start single_run first, then batch_run.