anchapin

Building energy modeling (BEM) expert that bridges physics-based simulation and production-grade code in Python, Rust, and Ruby. Triggers on tasks involving EnergyPlus (IDF editing, SQL output parsing, convergence debugging), OpenStudio (.OSM manipulation, measure writing in Ruby), ASHRAE standards applied to buildings (90.1 envelope and equipment, 62.1 ventilation, 55 comfort, 14 measurement and verification), psychrometric calculations for HVAC airstreams and building conditioning, building envelope analysis (thermal bridging, U-values, SHGC), parametric and surrogate energy modeling, and simulation math implemented in Rust. Use this skill when the user is working on building energy models, HVAC design for buildings, or any code that interfaces with EnergyPlus or OpenStudio — even for a quick lookup like a ventilation rate or setpoint, the answer should include the ASHRAE citation, the formula, and a code path. Do NOT trigger for general thermodynamics (power cycles, flat-plate convection, Rankine cycle), a

Evaluate proposals — feasibility, ROI, risk.

System design — module boundaries, API contracts, ADRs.

Python server code, APIs, async, strict typing.

CI failures — read error, minimal fix, verify.

DevOps — Docker, CI/CD, cloud infra, monitoring.

React / Next.js UI, state, accessibility.

Planning — decompose goals, create tasks via task server.

Run interactive brainstorming across verifiers environments, evaluations, GEPA, and RL training. Use when the user wants ideation, literature scanning, concept teaching, roadmap planning, or research program design grounded in local CLI sources, verifiers, and RL trainer code.

Discover and inspect verifiers environments through the Prime ecosystem. Use when asked to find environments on the Hub, compare options, inspect metadata, check action status, pull local copies for inspection, or choose environment starting points before evaluation, training, or migration work.

Create or migrate verifiers environments for the Prime Lab ecosystem. Use when asked to build a new environment from scratch, port an eval or benchmark from papers or other libraries, start from an environment on the Hub, or convert existing tasks into a package that exposes load_environment and installs cleanly with prime env install.

Run and analyze evaluations for verifiers environments using prime eval. Use when asked to smoke-test environments, run benchmark sweeps, resume interrupted evaluations, compare models, inspect sample-level outputs, or produce evaluation summaries suitable for deciding next steps.

Audit and optimize verifiers environments for async performance. Use when asked to profile, speed up, or review an environment for concurrency bottlenecks, event loop blocking, or scaling issues under high rollout counts.

Optimize environment system prompts with GEPA through prime gepa run. Use when asked to improve prompt performance without gradient training, compare baseline versus optimized prompts, run GEPA from CLI or TOML configs, or interpret GEPA outputs before deployment.

Review verifiers environments for correctness, robustness, and ecosystem compatibility. Use when asked for environment code review, quality audit, migration validation, or release readiness checks for local environments or environments pulled from the Hub.

Train models with verifiers environments using hosted RL or prime-rl. Use when asked to configure RL runs, tune key hyperparameters, diagnose instability, set up difficulty filtering and oversampling, or create practical train and eval loops for new environments.

Run accessibility tests to ensure the ResumeAI application is accessible to all users.

Analyze test coverage reports to identify areas needing more tests.

Run linters, formatters, and type checkers for both frontend and backend code.

Inspect and query the SQLite database used by the ResumeAI application.

Build and run Docker containers for the ResumeAI application.

Detect unused npm dependencies in the ResumeAI frontend project.

Manage git branches, commits, and pull requests for ResumeAI development workflow.

Run frontend and backend tests with coverage reporting for the ResumeAI project.

Automated PR review, fixing, CI monitoring, and merging with hybrid batch/individual strategy

Test and validate Genkit AI flows with sample inputs

Generate Shadcn/ui components following project conventions

Implements top 3-5 priority GitHub issues in parallel using git worktrees and separate subagents, then creates PRs for each. Use when you want to tackle multiple issues simultaneously.

Analyzes open GitHub issues, prioritizes them by roadmap impact, determines parallel workability with git worktrees, and creates a plan to work on multiple issues simultaneously using sub-agents. Use when planning parallel development work.

Processes multiple GitHub issues in parallel using git worktrees and subagents. Creates either a single consolidated PR or individual PRs per issue. Use when working on batches of related GitHub issues simultaneously.

Iteratively fixes CI failures in open PRs and merges them when tests pass. Handles merge conflicts and coordinates multi-PR merges. Use when PRs have failing CI checks or when ready to merge PRs.

Automatically fix all test failures and ensure coverage targets are met. Runs tests, fixes issues iteratively until 100% pass with 0 skips, runs coverage, and adds tests until targets (85% lines, 80% branches) are achieved. Use when user says "fix tests", "ensure coverage", "make tests pass", or similar.