AI & LLM Engineering · For data scientists

Build and review OpenRLHF supervised/preference training plans for SFT, reward models, DPO, IPO, and cDPO.

VectorSpaceLab/AREX-Skill

Use this repo skill for Microsoft Swin-Transformer image-classification model, config, data, checkpoint, SimMIM, Swin-MoE, and optional CUDA acceleration workflows.

VectorSpaceLab/AREX-Skill

Build and debug Browser Use tools/actions: custom Tools/Controller actions, default browser/file actions, ActionResult returns, parameter injection, sensitive data, security guardrails, and…

VectorSpaceLab/AREX-Skill

Use this sub-skill when defining, validating, sharing, loading, or troubleshooting smolagents tools, built-in/default tools, Hub/Space/LangChain integrations, or MCP tool collections.

VectorSpaceLab/AREX-Skill

A skill your agent uses for AutoGen developer tooling maintenance: AutoGen Studio, AG Bench, Magentic-One CLI, pyautogen proxy compatibility, CLI help checks, safe benchmark/service planning, and…

VectorSpaceLab/AREX-Skill

Use Torch Points3D for point-cloud deep learning APIs, datasets/transforms, Hydra training/evaluation, checkpoints, sparse backend decisions, and registration workflows.

VectorSpaceLab/AREX-Skill

Use TorchMetrics to choose, inspect, and combine metric families for PyTorch evaluation, including core API, domain metrics, model-based metrics, and wrappers.

VectorSpaceLab/AREX-Skill

Use TorchRL for TensorDict-first reinforcement-learning environments, collectors, replay buffers, modules, objectives, LLM/RLHF/VLA workflows, services, rendering, and maintainer-safe repository…

VectorSpaceLab/AREX-Skill

A skill your agent uses for Ultralytics track mode, tracker YAML selection, persistent object IDs, and YOLO Solutions such as counting, heatmaps, speed, queue, region, similarity search, and…

VectorSpaceLab/AREX-Skill

Train or fine-tune ColBERT models, prepare and validate triples, use scored distillation examples, and plan GPU/resource settings.

VectorSpaceLab/AREX-Skill

A skill your agent uses for ModelScope trainer construction, TrainingArgs conversion, fine-tuning and evaluation preflight, checkpoint hooks, and safe train/eval command planning.

VectorSpaceLab/AREX-Skill

Use Towhee's optional PyTorch Trainer, TrainingConfig YAML, NNOperator training bridge, and towhee.models package boundaries safely.

VectorSpaceLab/AREX-Skill

A skill your agent uses when planning or auditing TorchVision reference training/evaluation workflows for classification, quantization, detection, segmentation, video classification, optical flow…

VectorSpaceLab/AREX-Skill

Compose timm API-level training loops with optimizer and scheduler factories, loss selection, task wrappers, EMA, AMP scaling, metrics, checkpoint state, and safe CPU smoke checks.

VectorSpaceLab/AREX-Skill

A skill your agent uses for Ultralytics YOLO package workflows: CLI/Python model usage, data/config setup, train/val, prediction/results, export/deployment, tracking/solutions, model-family…

VectorSpaceLab/AREX-Skill

Use this sub-skill for MLAlgorithms clustering, Gaussian mixtures, PCA, t-SNE, RBM feature learning, metrics/distances, and packaged demo dataset loaders.

VectorSpaceLab/AREX-Skill

Guide safe video-file, webcam, and optional half-precision demo use for pytorch-yolo-v3.

VectorSpaceLab/AREX-Skill

Review changed Elixir/Phoenix code read-only. An agent skill from oliver-kriska/claude-elixir-phoenix.

oliver-kriska/claude-elixir-phoenix

Review changed Elixir/Phoenix code read-only. An agent skill from oliver-kriska/claude-elixir-phoenix.

oliver-kriska/claude-elixir-phoenix

Watch an Elixir/Phoenix PR with an Amp Orb keep-alive lease until required non-deployment CI is green and review threads are resolved.

oliver-kriska/claude-elixir-phoenix

SystemVerilog lint checker with structured output for orchestration.

codejunkie99/Gateflow-Plugin

SystemVerilog simulator with structured output for orchestration.

codejunkie99/Gateflow-Plugin

Hybrid code search (BM25 + vector + KG) with RRF fusion. An agent skill from bobmatnyc/claude-mpm.

bobmatnyc/claude-mpm

Create, modify, review, and harden configuration for the Adobe Dispatcher Apache HTTP Server module and Apache HTTPD in AEM as a Cloud Service environments only.

adobe/skills

[BETA] Implement custom AEM Workflow Java components on AEM 6.5 LTS.

adobe/skills

[BETA] Implement custom AEM Workflow Java components on AEM as a Cloud Service.

adobe/skills

Step-by-step process for adopting Cavekit on an existing codebase.

hashgraph-online/awesome-codex-plugins

Classify a task or feature as quick, standard, or thorough so the rest of the pipeline (budget sizing, model routing, review depth) can right-size itself.

hashgraph-online/awesome-codex-plugins

Quality and performance evaluation with baseline comparison.

hashgraph-online/awesome-codex-plugins

A skill your agent uses when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search.

hashgraph-online/awesome-codex-plugins

How to design the numbered prompt pipeline that drives Hunt phases in Cavekit.

hashgraph-online/awesome-codex-plugins

RAG workflow skill. An agent skill from diegosouzapw/awesome-omni-skills.

diegosouzapw/awesome-omni-skills

Build RAG systems for construction knowledge bases. An agent skill from datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

Apple Intelligence skills for on-device AI features including Foundation Models, Visual Intelligence, App Intents, and intelligent assistants.

gustavscirulis/snapgrid

Recommends the right Datadog products for a codebase and/or a stated goal — grounded in a tech-stack→product map and a use-case→product map built from Datadog product capabilities and common…

datadog-labs/agent-skills

Write effective prompts for LLMs — structure, few-shot examples, chain-of-thought, system prompts, and output parsing.

spencerpauly/awesome-cursor-skills

Paddle-based deep learning workflows from the course materials, including DNN/RNN text-style baselines and the CNN/LeNet image classification case using folder-labeled digit images.

Drchronx/ai-agent-research-starter-kit

Chinese sentiment analysis workflows using dictionary scoring, traditional machine learning classifiers, and LLM API calls.

Drchronx/ai-agent-research-starter-kit

Basic Chinese NLP and text analysis workflows for PDF text/table extraction, jieba tokenization, word and sentence frequency, word clouds, TF-IDF, Word2Vec, sentence embeddings, and text similarity.

Drchronx/ai-agent-research-starter-kit

Caches a codebase to reduce token usage

kurealnum/dotfiles

Guide for selecting the most appropriate foundation MLIP model based on simulation requirements.

learningmatter-mit/AtomisticSkills

Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model.

learningmatter-mit/AtomisticSkills

Interactive Archon integration for knowledge base and project management via REST API.

Microck/ordinary-claude-skills

Retrieval-augmented generation (RAG) skill for the D&D 5e System Reference Document (SRD).

Microck/ordinary-claude-skills

Structured recovery and escalation when an agent hits a retry loop.

ntorga/agent-starter-kit

Implement a task step by step with automated LLM-as-Judge verification at the end of each phase

NeoLabHQ/context-engineering-kit

Design RAG pipelines: chunking, retrieval evaluation, and architecture.

borghei/Claude-Skills

Implement LDA topic modeling to discover latent topics in document collections.

asgard-ai-platform/skills