VectorSpaceLab/AREX-Skill

dynamic-resources

Example skill loaded from resources_discover

لغة النص الأصلي: الإنجليزية

create-paper-skills

Creates reusable Agent Skills from an AI research paper using the Paper2Skills Distiller workflow. Use in Creator mode when the user provides a paper PDF, paper URL, arXiv id, paper title, or paper/repo pair, or asks to convert a scientific paper into skills…

لغة النص الأصلي: الإنجليزية

create-repo-skill

Creates a repo-specific operating Agent Skill for DisCo Researcher from a local repository by inspecting source files and an installed or auto-prepared, backend-aware Python package environment. Use when the user asks to create a skill for a repo, generate…

لغة النص الأصلي: الإنجليزية

extend-repo-skill

Extends an existing repository-specific Agent Skill with new capabilities, deeper coverage, troubleshooting, scripts, and usability tests. Use when the user asks to expand, improve, deepen, or add coverage to an already implemented skill instead of creating a…

لغة النص الأصلي: الإنجليزية

import-repo-skills-to-agent

Use this skill when the user asks to export DisCo's managed repository skills and repo-skills-router into another agent tool such as Codex under ~/.agents/skills, Claude Code under ~/.claude/skills, or a project-local agent directory. Handles canonical source…

لغة النص الأصلي: الإنجليزية

refresh-repo-skill

Refreshes an existing repository-specific Agent Skill after the source repository changed. Use when the user says repo code, APIs, docs, examples, configs, dependencies, or behavior changed and an old skill may now be stale, outdated, inconsistent with…

لغة النص الأصلي: الإنجليزية

repo-skills-router

Routes substantive ML, AI, data, scientific-computing, and software-engineering requests to the smallest useful set of managed repository skills. Invoke proactively when a request names or implies a package, framework, model family, dataset, modality,…

لغة النص الأصلي: الإنجليزية

verify-repo-skill

Verifies a generated or refreshed repo-specific Agent Skill by creating assertion-backed usability test cases, running content-level self-refine, checking backend-classified native repo examples/tests against the prepared CPU/GPU environment plan, enforcing…

لغة النص الأصلي: الإنجليزية

3d-resnets-pytorch

Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.

لغة النص الأصلي: الإنجليزية

data-preparation

Prepare raw videos and annotations for the 3D-ResNets-PyTorch dataset loaders.

لغة النص الأصلي: الإنجليزية

training-and-inference

Routes training, fine-tuning, validation, checkpoint, and inference workflows for 3D ResNets PyTorch.

لغة النص الأصلي: الإنجليزية

3ddfa

Guide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.

لغة النص الأصلي: الإنجليزية

cpp-onnx-port

Operate the optional 3DDFA C++ OpenCV DNN port, checkpoint-to-ONNX export, weight placement, build/run expectations, and C++ troubleshooting.

لغة النص الأصلي: الإنجليزية

geometry-rendering

Reconstruct 3DMM vertices, serialize mesh outputs, and manage 3DDFA rendering helpers.

لغة النص الأصلي: الإنجليزية

python-inference

Operate 3DDFA Python image and video inference for landmarks, dense vertices, meshes, pose boxes, depth, PNCC, and PAF outputs.

لغة النص الأصلي: الإنجليزية

training-evaluation

Routes 3DDFA training recipes, loss selection, checkpoint resume, dataset layout, and benchmark evaluation.

لغة النص الأصلي: الإنجليزية

3ddfa-v2

Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.

لغة النص الأصلي: الإنجليزية

onnx-and-benchmarking

Use 3DDFA_V2 ONNX Runtime acceleration and CPU latency or speed benchmark workflows.

لغة النص الأصلي: الإنجليزية

setup-and-assets

Prepare 3DDFA_V2 runtime assets and native extension builds before demos or benchmarks.

لغة النص الأصلي: الإنجليزية

still-image-demo

Run 3DDFA_V2 still-image alignment, rendering, pose, texture, and mesh export workflows.

لغة النص الأصلي: الإنجليزية

video-and-tracking

Run 3DDFA_V2 video, smoothing, and manual webcam tracking workflows.

لغة النص الأصلي: الإنجليزية

ab3dmot

Operate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.

لغة النص الأصلي: الإنجليزية

data-conversion

Routes KITTI and nuScenes data-layout, detection-conversion, and schema-validation work for AB3DMOT inputs.

لغة النص الأصلي: الإنجليزية

evaluation-visualization

Evaluate, threshold, combine, and visualize AB3DMOT KITTI and nuScenes tracking results.

لغة النص الأصلي: الإنجليزية

tracking-pipeline

Run AB3DMOT tracking safely and use the core AB3DMOT tracker APIs for KITTI and nuScenes 3D MOT workflows.

لغة النص الأصلي: الإنجليزية

accelerate

Use Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model inference/offload, checkpointing, tracking, and troubleshooting.

لغة النص الأصلي: الإنجليزية

big-model-inference

Use Accelerate big-model inference utilities for meta initialization, device-map planning, checkpoint dispatch, CPU/disk offload, hooks, pipeline inference, and memory sizing without triggering downloads or heavyweight runs.

لغة النص الأصلي: الإنجليزية

checkpointing-and-tracking

Save and resume Accelerate training state, register checkpoint hooks and custom state, log safely across processes, use experiment trackers, profile runs, and clean up memory.

لغة النص الأصلي: الإنجليزية

configuration-and-cli

Use this sub-skill when working with Hugging Face Accelerate configuration files and CLI commands, including accelerate config/default/update/env/launch/test/estimate-memory/merge-weights/to-fsdp2, launch command construction, multi-node and SLURM planning,…

لغة النص الأصلي: الإنجليزية

distributed-training-backends

Select, configure, and diagnose Accelerate distributed training backends including DeepSpeed, FSDP/FSDP2, Megatron-LM, torch native parallelism, TPU/XLA, FP8, quantization, compilation, Local SGD, and DDP communication hooks.

لغة النص الأصلي: الإنجليزية

training-loop-integration

Migrate raw PyTorch training and evaluation loops to Hugging Face Accelerate using Accelerator, prepare(), backward(), gradient accumulation, dataloader behavior, gather/reduce, mixed precision, DDP kwargs, local SGD, communication hooks, and basic…

لغة النص الأصلي: الإنجليزية

acme

Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.

لغة النص الأصلي: الإنجليزية

core-workflows

Build and debug Acme core dm_env loops, specs, wrappers, logging, counting, observers, and simple custom Actor/Learner components.

لغة النص الأصلي: الإنجليزية

jax-agents

Select, configure, and adapt Acme JAX agents and JAX experiment workflows.

لغة النص الأصلي: الإنجليزية

replay-and-data

Use Acme adders, Reverb replay tables and datasets, offline data iterators, image augmentation, and replay shape troubleshooting.

لغة النص الأصلي: الإنجليزية

tf-agents

Select, configure, debug, and adapt Acme TensorFlow/Sonnet agents, networks, savers, Launchpad examples, and TF losses.

لغة النص الأصلي: الإنجليزية

act-plus-plus

Routes ACT++, ACT, Diffusion Policy, VINN, and MuJoCo simulation workflows for bimanual ALOHA episode data and imitation-learning tasks.

لغة النص الأصلي: الإنجليزية

policy-training

Routes ACT, CNNMLP, Diffusion Policy, and latent-model training or evaluation workflows for ACT++ checkpoints and datasets.

لغة النص الأصلي: الإنجليزية

simulation-data

Routes simulated ALOHA episode generation, replay, visualization, mirroring, compression, and truncation workflows for ACT++ HDF5 data.

لغة النص الأصلي: الإنجليزية

vinn-offline

Routes VINN feature caching and non-interactive k-selection workflows for ACT++ BYOL/ResNet episode features.

لغة النص الأصلي: الإنجليزية