Use when migrating a directory of local ROOT files to BNL-OSG2_LOCALGROUPDISK via Rucio on BNL SDCC nodes, or for any sub-step of that workflow: pre-flight checks (Rucio account, grid proxy, quotas, RSE names, pnfs mount), monitoring a Rucio replication rule until it reaches OK/STUCK, or building a symlink farm from an already-replicated dataset for transparent proxy-free access.
Use when working with the UChicago ATLAS Analysis Facility, submitting HTCondor batch jobs at UChicago, accessing JupyterLab at af.uchicago.edu, using XCache or Rucio for ATLAS data at UChicago, deploying ML models on Triton at UChicago AF, setting up ServiceX or Coffea Casa, or troubleshooting SSH access to login.af.uchicago.edu
Use when running or writing ART (ATLAS Release Tester) validation tests for ATLAS nightly builds, using art.py to run, list, or compare tests, debugging ART test failures in nightly CI, or understanding ATLAS release validation infrastructure.
Use when creating ATLAS publication-quality plots with the official ATLAS ROOT style macros (atlasrootstyle), applying SetAtlasStyle, placing ATLAS labels (Internal, Preliminary, Simulation), using ATLASLabel or myText helper functions, or following ATLAS publication plotting conventions in ROOT or PyROOT.
Use when visualizing ATLAS detector events with the Atlantis event display: launching the Atlantis GUI, opening JiveXML event files, producing JiveXML output from Athena reconstruction, or troubleshooting Java runtime issues in containerized environments.
Use when a question involves ATLAS software concepts: Athena framework, event data model, CP algorithms, derivation formats (DAOD), CMake build system, CVMFS software releases, analysis releases, ASG tools, or any ATLAS-internal software infrastructure. This skill routes to the right resource or subagent; for deep lookup delegate to atlas-docs-expert.
Use when searching for ATLAS Monte Carlo or data samples: querying the PMG central sample database for MC datasets by process, generator, or campaign, looking up cross-sections and filter efficiencies, or identifying which centrally produced samples are available for a given physics process.
Use when writing a columnar ATLAS analysis with coffea: defining a NanoEvents or custom processor, running over ROOT files, accumulating histograms with hist, applying scale factors and systematic weights, or migrating a for-loop event analysis to a coffea processor pattern.