pnnl

Run ASOPB evaluation with credential routing, build context sync, and baseline comparison

Walk the full ADEPT Code Hygiene Quick Reference Card checklist and report PASS/FAIL/N-A for each item. Use as a final check before pushing.

Full task closure workflow -- runs test validation, session report, tracking doc updates, commit preparation, and hygiene audit in sequence. Use at the end of a development session. Pass an optional title hint as argument.

Configure Claude Code to connect to an ADEPT instance (local Docker stack or remote server). Generates .mcp.json, runs doctor check, verifies connectivity. Use when setting up or switching between ADEPT instances.

Guided workflow to deploy ADEPT on cloud infrastructure (AWS, Azure, or GCP) as a single VM or A2A mesh pair. Covers provisioning, OS prep, stack deployment, and optional A2A federation between two independently-deployed stacks.

Add a new tool to an existing MCP server following the canonical register(mcp) + Pydantic pattern. Use during Phase 4 (Implement) of the feature development lifecycle.

Analyze a Python library and produce an MCP server implementation plan. Audits the API surface, maps functions to tools, classifies dependencies, and identifies session boundaries. Use during Phase 1-2 (Plan + Discover) of the feature development lifecycle.

Register (or re-register) an MCP server's tools with the ADEPT gateway. Includes pre-flight validation, schema checking, registration, and verification. Use during Phase 9 (Close) of the feature development lifecycle.

Train a UQ model for a pretrained MLIP using uq-mlip, run an MD simulation decorated with per-atom uncertainty, and output predicted quantiles. Use when: training uncertainty quantification model on MLIP validation set, wrapping MACE or UMA calculator with UQ, running ASE molecular dynamics with per-atom UQ, extracting quantile predictions from MD trajectory, monitoring UQ profile during simulation.

Run GALAS (Graph Analytics for Large Atomistic Simulations) defect analysis on LAMMPS dump files. Use when: analyzing defects in atomistic simulation data, identifying vacancies or grain boundaries, tracking defect evolution over MD trajectories, generating defect summary reports with counts and types, producing plots of defect metrics over time.

Use this skill when the user is writing Python code that uses the comcheck_api package to build COMcheck project JSON, run compliance simulations against the PNNL COMcheck Web API, or work with envelope or building-area operations. Triggers on imports of `comcheck_api`, mentions of COMcheck/ASHRAE 90.1/IECC compliance, or requests to validate building energy code compliance.

Run Compositional Community Detection (CCD) on Atom Probe Tomography data. Use when: analyzing APT point clouds, identifying compositional communities in APT neighborhoods, detecting phases or precipitates in APT data, running CCD on .pos/.apt/.csv files with .rrng range files, interpreting KS statistics heatmaps from APT analysis.

Exploratory data analysis