By usatlas
Generic Python tooling skills used across HEP workflows: Typer CLIs with pixi/uv/Hatch, and PEP-723 standalone scripts.
Use when building a Python command-line interface with Typer: adding arguments and options to a script, creating subcommands, wiring an entry point into pyproject.toml, validating CLI inputs with callbacks, or adding a CLI layer to an existing analysis script or HEP workflow.
Use when setting up code quality tooling for a HEP Python project: configuring pre-commit hooks, adding ruff for linting and auto-formatting, setting up mypy for static type checking, or debugging linter failures in CI or a pre-commit run.
Use when creating a new Python package, adding pyproject.toml to an existing project, choosing a build backend, setting up src layout, configuring VCS-based versioning, or managing a development environment with pixi or uv for a HEP Python project.
Use when writing or configuring tests for a HEP Python project with pytest: setting up pyproject.toml test configuration, writing fixtures and parametrized tests, handling numerical tolerances for physics quantities, setting up code coverage, or choosing between unit and integration tests.
Use when generating a self-contained Python script with PEP 723 inline dependency metadata: writing the script block header, making a script runnable with uv run --script, combining with a Typer CLI for argument handling, or creating a one-off analysis tool that should not live inside a package and must declare its own dependencies inline.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugin marketplace for ATLAS physics analysis. Three plugins cover USATLAS Analysis Facilities, the full ATLAS software and analysis stack, and generic HEP Python tooling.
# From GitHub
/plugins marketplace add usatlas/marketplace
# From a local clone
/plugins marketplace add /path/to/marketplace
Then install whichever plugins you need from the marketplace browser.
analysis-facilitiesSkills for USATLAS Analysis Facilities (UChicago AF, BNL AF, SLAC AF).
| Skill | Description |
|---|---|
uchicago-af | HTCondor batch, JupyterLab, XCache, Rucio, ServiceX, Coffea-Casa, Triton at af.uchicago.edu |
More facility skills (BNL, SLAC) coming soon.
atlasATLAS analysis plugin covering the full workflow from raw data to publication.
Subagents (invoked automatically or via Agent(subagent_type=...)):
| Subagent | Purpose |
|---|---|
atlas-analysis-architect | Designs end-to-end analysis pipelines; produces a structured specification |
atlas-analysis-coder | Writes Python analysis code (uproot, ServiceX, coffea, hist) |
atlas-docs-expert | Answers ATLAS software questions; cites hosted docs at atlas-software.docs.cern.ch |
atlas-stats-expert | Statistical model design: pyhf/cabinetry workspaces, TRExFitter configs, limits |
atlas-data-explorer | Dataset and file discovery via Rucio, AMI, and ATLAS Open Data MCPs |
Skills:
| Category | Skills |
|---|---|
| Orientation | atlas-software |
| Statistics | pyhf, cabinetry, pyhs3, histfitter, trexfitter, roounfold |
| Frameworks | topcptoolkit, fastframes |
| Data access | servicex, analysis-spec-builder, fsspec-xrootd |
| Core tools | uproot, awkward, coffea, hist, vector |
| Scikit-HEP | iminuit, fastjet, particle, hepunits, decaylanguage, pyhepmc, pylhe |
| Interop | cpp-bindings |
MCP servers (configured in plugins/atlas/.mcp.json):
| Server | Launch command | Purpose |
|---|---|---|
rucio | pixi exec rucio-mcp serve --read-only | Dataset and replica discovery |
ami | pixi exec ami-mcp serve | AMI metadata (cross-sections, tags) |
atlasopenmagic | uvx atlasopenmagic-mcp serve | ATLAS Open Data catalog |
Required environment variables for Rucio MCP:
export RUCIO_ACCOUNT=yourusername # required — no default
export RUCIO_AUTH_TYPE=x509_proxy # default; or "oidc" / "userpass"
voms-proxy-init --voms atlas # obtain a valid proxy first
hep-python-toolsGeneric Python tooling skills for HEP workflows.
| Skill | Description |
|---|---|
cli-creator | Typer CLI scripts with modern Annotated syntax |
standalone-script | PEP 723 inline-metadata scripts runnable with uv run --script |
python-packaging | pyproject.toml, src layout, VCS versioning, pixi/uv environment setup |
code-quality-tools | pre-commit hooks, ruff linting/formatting, mypy static type checking |
python-testing | pytest fixtures, parametrization, numerical tolerances, coverage for HEP |
plugins/
analysis-facilities/
.claude-plugin/plugin.json
skills/uchicago-af/SKILL.md
atlas/
.claude-plugin/plugin.json
.mcp.json
agents/ # 5 subagents
skills/ # 25 skills
VENDORED-LICENSES.md # BSD 3-Clause attribution for upstream content
hep-python-tools/
.claude-plugin/plugin.json
skills/ # 5 skills
.claude-plugin/marketplace.json
npx claudepluginhub usatlas/marketplace --plugin hep-python-toolsSkills for working with USATLAS Analysis Facilities including UChicago, BNL, and SLAC sites.
ATLAS analysis plugin: grid/catalog MCPs (Rucio, AMI, ATLAS Open Data), statistics (pyhf, cabinetry, HistFitter, TRExFitter, RooUnfold, pyhs3), analysis frameworks (TopCPToolkit, FastFrames, ServiceX), Scikit-HEP tools, and ATLAS software orientation.
AI-powered development tools for code review, research, design, and workflow automation.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.