VectorSpaceLab/AREX-Skill - Page 5

alibi

Routes Alibi users to the right explanation, confidence, prototype, or optional-backend workflow and points them to the bundled helpers needed to run it.

anchors-local-explanations

Routes Alibi requests for AnchorTabular, AnchorText, and AnchorImage workflows, including sampling, segmentation, and precision/coverage troubleshooting.

attribution-and-shap

Routes Alibi requests for KernelShap, TreeShap, and IntegratedGradients, including optional-backend selection and attribution troubleshooting.

confidence-prototypes-utilities

Routes Alibi requests for TrustScore, LinearityMeasure, ProtoSelect, save/load round-trips, and the small shared utilities they rely on.

counterfactuals-and-similarity

Routes Alibi requests for Counterfactual, CEM, CounterfactualProto, CounterfactualRL, and GradientSimilarity workflows and their backend gating.

global-tabular-explanations

Routes requests for ALE, partial dependence, PD variance, permutation importance, and other global tabular explanation workflows.

align-anything

Operate the Align-Anything multimodal alignment package, including training, serving, remote reward models, and satellite projects.

multimodal-serving

Serve and smoke-check align-anything text, multimodal, and omni-modal inference without reading the source checkout.

project-workflows

Route Align-Anything satellite project workflows and decide runnable versus extension versus reference-only use.

remote-reward-models

Operate Align-Anything remote reward servers, payload checks, and PPO remote-RM wiring.

training-and-alignment

Route Align-Anything training modules, alignment algorithms, configs, datasets, launchers, and trainer troubleshooting.

alpamayo-r1

Router for Alpamayo R1 multimodal driving inference and trajectory sampling.

inference

End-to-end Alpamayo R1 multimodal driving inference, sample generation, and troubleshooting.

alpasim

Use AlpaSim repository guidance for autonomous-driving simulation setup, Hydra wizard runs, runtime services, ego drivers and plugins, ASL evaluation, controller/physics/traffic components, gRPC contracts, and operational troubleshooting.

control-physics-traffic

Use when an AlpaSim task concerns vehicle state, controller or MPC selection, ground-mesh physics, CATK traffic sessions, handover behavior, or backend/data requirements for these services.

drivers-and-plugins

Select, configure, inspect, and extend AlpaSim ego drivers and model plugins while preserving camera, trajectory, asset, and optional-backend contracts.

evaluation-and-logs

Inspect AlpaSim ASL rollouts, extract camera streams, evaluate and aggregate metrics, re-evaluate completed runs, render diagnostic videos, and analyze trajectories, maps, and geometry without producing new simulations.

grpc-and-developer-tools

Maintain AlpaSim protobuf and gRPC contracts, use generated stubs, inspect installed packages and entry points, and perform safe contributor/tooling checks without starting simulation or external infrastructure.

runtime-services

Use when diagnosing or adapting AlpaSim's runtime event loop, service lifecycle, gRPC address routing, one-shot or daemon execution, replay, timing validation, renderer caches, or video-model chunk scheduling.

simulation-wizard

Install and operate AlpaSim's Hydra simulation wizard: select scenes and drivers, validate configs, generate or run Docker/Slurm deployments, tune timing/topology, and inspect run telemetry and outputs.

alpha-gpt

Route AlphaGPT data ingestion, factor mining, live strategy, and dashboard workflows.

dashboard-ops

Operate and troubleshoot AlphaGPT's Streamlit dashboard, local state inputs, read-only DB/RPC views, Plotly visualizers, and emergency STOP control.

data-pipeline

Configure, validate, and operate AlphaGPT's safe OHLCV ingestion pipeline.

factor-mining

Operate AlphaGPT factor-token mining, formula execution, feature engineering, backtest scoring, and training artifacts safely.

live-strategy

Operate AlphaGPT live strategy, risk, portfolio state, STOP control, and guarded Solana/Jupiter execution.

alphafold

Route AlphaFold protein structure prediction setup, data preparation, local prediction, model configuration, output interpretation, and relaxation workflows.

docker-and-data-setup

Plan AlphaFold Docker execution, database/model-parameter acquisition, update flows, and safe dry-run command construction without starting containers or downloads.

input-data-and-formats

Validate AlphaFold FASTA, MSA, template, notebook, and data-pipeline inputs without running external searches.

model-config-and-api

Inspect and modify AlphaFold model presets, RunModel configuration, feature processing, parameter loading, and backend dependency issues.

outputs-and-confidence

Inspect AlphaFold output folders, confidence JSON, ranked structures, AFDB files, and AlphaFold Server JSON schemas.

prediction-cli

Guide local AlphaFold prediction CLI workflows, flags, presets, MSA reuse, relaxation choices, random seeds, and output expectations.

relaxation

Guide AlphaFold Amber/OpenMM relaxation, AmberRelaxation APIs, CPU/GPU relax choices, structural violation metrics, and PDB cleanup constraints.

alphafold2

Guide alphafold2-pytorch protein sequence, MSA, distogram, angle-logit, coordinate-refinement, recycling, embedding, and structure-utility workflows with version-aware troubleshooting.

core-model

Guide construction and execution of the verified Alphafold2 sequence/MSA trunk and direct Evoformer API, including distogram and angle-logit prediction, masks, templates, extra MSA inputs, embeddings, and supported trunk configuration.

embeddings

Guides ESM, MSA Transformer, ProtTrans/ProtBERT, and precomputed sequence/MSA representations for Alphafold2, including projection, masks, caches, downloads, Apex, and OOM diagnosis.

structure-and-recycling

Guide coordinate prediction, IPA structure refinement, confidence and recyclable outputs, and optional template or extra-MSA inputs that feed structure refinement in alphafold2-pytorch 0.4.32.

utilities

Use alphafold2_pytorch utilities to validate and transform protein coordinates, distograms, masks, MDS reconstructions, sidechain layouts, alignments, and structure-quality metrics.

alphafold3-pytorch

Use AlphaFold 3 PyTorch for protein and biomolecular structure-prediction workflows, heterogeneous molecule inputs, PDB/mmCIF/MSA/template preparation, bounded model inference, training configuration, and local CLI or Gradio operation.

cli-serving

Operate the alphafold3_pytorch CLI and alphafold3_pytorch_app Gradio entry points, construct safe multimolecule commands, and diagnose checkpoint, device, output, entity, cache, and precision behavior.

data-pipeline

Prepare and validate AlphaFold 3 mmCIF/PDB, MSA, template, crop, sampling, and large-dataset curation inputs without performing unsafe acquisition or mutation.