Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".
Port an open-source bioinformatics data pipeline into the BioIR pipeline architecture. Use when the user asks to create, port, convert, or write a new data pipeline from OSS code, or add a new model's data processing to the BioIR system. Level 2 is one full build_processor run of the sample manifest, serial and Ray.
Implement an upstream pretrained model natively in BioIR using its optimized components, with checkpoint conversion and numerical validation. Use when adding a new model or architecture to BioIR; includes data pipeline integration when requested.
Audits existing interfaces for WCAG 2.2 AA conformance and remediates the violations found. Use when auditing a page or component for accessibility, running axe-core or pa11y, triaging a11y violations, or checking screen reader and contrast issues before shipping.
Prepare an ECC skill contribution for review by organizing repository, install-surface, cross-harness, validation, security, and commit observations into a local proposal. Use when preparing a skill contribution for review.
Prepare an ECC skill contribution for review by organizing repository, install-surface, cross-harness, validation, security, and commit observations into a local proposal. Use when preparing a skill contribution for review.
Measure or improve the runtime, startup time, memory use, or throughput of a Newton simulation that already behaves correctly, or review a Newton step loop for performance problems such as CUDA graph capture mistakes and host synchronization. Not for setting up simulations, general solver or API questions, debugging unstable or incorrect physics without a performance goal, or optimizing Warp code that does not use Newton.
Set up, build, or debug physics simulations with the Newton Python package. Use when installing Newton, choosing simulation components, finding examples, or diagnosing simulation and runtime problems.
Use before building a feature: challenge the scope, then review architecture, code quality, tests and performance, and end with a plan to build. (gstack)
Use when building or debugging cuEquivariance PyTorch tensor products or equivariant GNNs, especially CPU references, layouts, indexing, and gradients.