“Model inference”

Mathematical alignment through LaTeX-only questions.

WHAT — C4 model methodology (Context, Container, Component, Code) guidance — what to draw at each level, when, and how to render C4-inspired diagrams via…

Cite file:line, command output, or a captured artifact for every claim; treat should/presumably/likely as unfinished work.

Run IV, DiD, and RDD analyses in R with proper diagnostics.

Route AI evaluation, ML training and inference engineering, and model operational readiness; use security review for authority-boundary threats.

Reviewing new-model / pipeline / checkpoint / deploy-config PRs and stage-topology issues — plumbing vs parity evidence, checkpoint layout gate, stage…

Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment.

When asked to estimate something unstated, produce a legible correctable evidence chain rather than refusing or fabricating a number.

Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging…

Change how the simulated car and engine behave in speeduino-serial-sim — driver, gearbox, engine torque, manifold, thermal model, Speeduino fuel/ignition/idle…

Builds Phase 2 golden C reference model with bitexact conformance and bandwidth estimation.

Use when tasks need optional PyCaret model training, ML factor generation, inference wrappers, feature importance, or sparse LASSO weight generation.

Use python-doctr (docTR) for OCR/KIE inference, document IO/export, model customization, datasets/training/evaluation, CLI helpers, deployment, and…

Set the model or effort a Stratum agent uses in this project, saved in .stratum/models.json.

Route DoWhy causal inference, graphical causal model, and graph/data workflows to the right sub-skill and bundled references.

Fetch weather/climate data via Earth2Studio data sources for specific variables and times.

Add causal reasoning to agent actions.

Use when working directly with the `esm` Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.

**[REQUIRED]** For **ALL** data science and machine learning tasks.

Detect and resolve incoherence across documentation, code and specs.

Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs.

Use AlphaFold 3 PyTorch for protein and biomolecular structure-prediction workflows, heterogeneous molecule inputs, PDB/mmCIF/MSA/template preparation…

Show or set the models max-speed workers run on.

Model and inspect a software product spanning multiple repositories using explicit members and contract relationships, without inferring architecture from…