Category
Best AI and LLM engineering skills, page 99
AI & LLM Engineering skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 4705 | A skill your agent uses for sentence-transformers CrossEncoder pair scoring, reranking, rank API usage, retrieve-and-rerank handoffs, multimodal reranker routing, and activation/softmax/numlabels… | VectorSpaceLab/ | 331 | — | ~807 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4706 | 4706.Routing Use this when configuring, validating, or debugging LiteLLM Router model groups, fallbacks, retries, cooldowns, budgets, routing strategies, health-check routing, aliases, tag filtering… | VectorSpaceLab/ | 331 | — | ~879 | Automated safety check: Pass | Unknown | 1 mo ago |
| 4707 | 4707.Runtime Optimization Use this sub-skill for Torch-TensorRT runtime performance controls, CUDA Graphs, output allocation, caches, TensorRT-RTX runtime settings, mutable modules, refit, weight streaming, and benchmark… | VectorSpaceLab/ | 331 | — | ~1k | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 4708 | 4708.SDK Core A skill your agent uses for direct LiteLLM Python SDK work: chat/text completions, async calls, streaming, embeddings, structured outputs, tools, token/cost checks, caching, callbacks, import/smoke… | VectorSpaceLab/ | 331 | — | ~1.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 4709 | 4709.Self Supervised A skill your agent uses for PaddleViT's DINO self-supervised vision-transformer pretraining, multi-crop data contracts, teacher/student configuration, single- or multi-GPU launch planning… | VectorSpaceLab/ | 331 | — | ~3.2k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4710 | Use this vLLM sub-skill for structured outputs, JSON/regex/grammar constraints, tool calling, reasoning parsers, chat-template/tool-parser routing, streaming tool-call deltas, and parser/backend… | VectorSpaceLab/ | 331 | — | ~823 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4711 | Build and review OpenRLHF supervised/preference training plans for SFT, reward models, DPO, IPO, and cDPO. | VectorSpaceLab/ | 331 | — | ~1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4712 | 4712.Swin Transformer Use this repo skill for Microsoft Swin-Transformer image-classification model, config, data, checkpoint, SimMIM, Swin-MoE, and optional CUDA acceleration workflows. | VectorSpaceLab/ | 331 | — | ~1.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 4713 | 4713.Tools And Actions 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/ | 331 | — | ~2.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 4714 | 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/ | 331 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4715 | 4715.Tools Studio Bench 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/ | 331 | — | ~910 | Automated safety check: Pass | Unknown | 1 mo ago |
| 4716 | 4716.Torch Points3d Use Torch Points3D for point-cloud deep learning APIs, datasets/transforms, Hydra training/evaluation, checkpoints, sparse backend decisions, and registration workflows. | VectorSpaceLab/ | 331 | — | ~1.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 4717 | 4717.Torch Tensorrt A skill your agent uses for Torch-TensorRT tasks: compiling PyTorch models with TensorRT, dynamic-shape/export workflows, runtime optimization, Triton/C++/distributed deployment, debugging… | VectorSpaceLab/ | 331 | — | ~1.5k | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 4718 | 4718.Torchmetrics Use TorchMetrics to choose, inspect, and combine metric families for PyTorch evaluation, including core API, domain metrics, model-based metrics, and wrappers. | VectorSpaceLab/ | 331 | — | ~964 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4719 | 4719.Torchrl Use TorchRL for TensorDict-first reinforcement-learning environments, collectors, replay buffers, modules, objectives, LLM/RLHF/VLA workflows, services, rendering, and maintainer-safe repository… | VectorSpaceLab/ | 331 | — | ~1.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 4720 | 4720.Torchvision A skill your agent uses when working with TorchVision models, weights, transforms, TVTensors, datasets, image IO, visualization utilities, vision ops, detection helpers, or official reference… | VectorSpaceLab/ | 331 | — | ~1.1k | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 4721 | 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/ | 331 | — | ~871 | Automated safety check: Pass | AGPL-3.0 | 1 mo ago |
| 4722 | Train or fine-tune ColBERT models, prepare and validate triples, use scored distillation examples, and plan GPU/resource settings. | VectorSpaceLab/ | 331 | — | ~850 | Automated safety check: Pass | MIT | 1 mo ago |
| 4723 | 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/ | 331 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4724 | 4724.Training And Models Use Towhee's optional PyTorch Trainer, TrainingConfig YAML, NNOperator training bridge, and towhee.models package boundaries safely. | VectorSpaceLab/ | 331 | — | ~676 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4725 | 4725.Training References A skill your agent uses when planning or auditing TorchVision reference training/evaluation workflows for classification, quantization, detection, segmentation, video classification, optical flow… | VectorSpaceLab/ | 331 | — | ~684 | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 4726 | 4726.Training Workflows 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/ | 331 | — | ~733 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4727 | 4727.Ultralytics 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/ | 331 | — | ~1.2k | Automated safety check: Pass | AGPL-3.0 | 1 mo ago |
| 4728 | Use this sub-skill for MLAlgorithms clustering, Gaussian mixtures, PCA, t-SNE, RBM feature learning, metrics/distances, and packaged demo dataset loaders. | VectorSpaceLab/ | 331 | — | ~1.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 4729 | 4729.Video Camera Demos Guide safe video-file, webcam, and optional half-precision demo use for pytorch-yolo-v3. | VectorSpaceLab/ | 331 | — | ~626 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4730 | 4730.Yolov5 A skill your agent uses for clone-run Ultralytics YOLOv5 workflows: detection, segmentation, classification, export, benchmarks, datasets, weights, and Flask REST serving. | VectorSpaceLab/ | 331 | — | ~1.6k | Automated safety check: Pass | AGPL-3.0 | 1 mo ago |
| 4731 | 4731.Phx Investigate Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix. | oliver-kriska/ | 565 | — | ~1.1k | Automated safety check: Pass | MIT | 5 days ago |
| 4732 | 4732.Phx Investigate Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix. | oliver-kriska/ | 565 | — | ~1k | Automated safety check: Pass | MIT | 5 days ago |
| 4733 | 4733.Phx Investigate Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix. | oliver-kriska/ | 565 | — | ~1k | Automated safety check: Pass | MIT | 5 days ago |
| 4734 | 4734.Phx Investigate Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix. | oliver-kriska/ | 565 | — | ~1k | Automated safety check: Pass | MIT | 5 days ago |
| 4735 | 4735.Phx Review Review changed Elixir/Phoenix code read-only. An agent skill from oliver-kriska/claude-elixir-phoenix. | oliver-kriska/ | 565 | — | ~1.1k | Automated safety check: Pass | MIT | 5 days ago |
| 4736 | 4736.Phx Review Review changed Elixir/Phoenix code read-only. An agent skill from oliver-kriska/claude-elixir-phoenix. | oliver-kriska/ | 565 | — | ~1.1k | Automated safety check: Pass | MIT | 5 days ago |
| 4737 | 4737.Phx Triage Triage review findings interactively — approve, skip, or prioritize; Use after $elixir-phoenix:phx-review to filter… | oliver-kriska/ | 565 | — | ~948 | Automated safety check: Pass | MIT | 5 days ago |
| 4738 | 4738.Phx Verify Verify Elixir/Phoenix changes — compile, format, and test in one loop. | oliver-kriska/ | 565 | — | ~1.3k | Automated safety check: Pass | MIT | 5 days ago |
| 4739 | 4739.Phx Watch PR 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/ | 565 | — | ~1k | Automated safety check: Pass | MIT | 5 days ago |
| 4740 | 4740.Gf Lint SystemVerilog lint checker with structured output for orchestration. | codejunkie99/ | 117 | — | ~1.5k | Automated safety check: Notes | Unknown | 24 days ago |
| 4741 | 4741.Gf Sim SystemVerilog simulator with structured output for orchestration. | codejunkie99/ | 117 | — | ~1.7k | Automated safety check: Notes | Unknown | 24 days ago |
| 4742 | Drive the trusty-mpm session manager (binary tm) to spawn, observe, command, and decommission durable tmux-backed Claude Code sessions in isolated workspaces. | bobmatnyc/ | 156 | — | ~3.9k | Automated safety check: Pass | Elastic-2.0 | 1 mo ago |
| 4743 | 4743.Trusty Search Hybrid code search (BM25 + vector + KG) with RRF fusion. An agent skill from bobmatnyc/claude-mpm. | bobmatnyc/ | 156 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4744 | 4744.Config Authoring 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/ | 197 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 4745 | 4745.Workflow Development [BETA] Implement custom AEM Workflow Java components on AEM 6.5 LTS. | adobe/ | 197 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 4746 | 4746.Workflow Development [BETA] Implement custom AEM Workflow Java components on AEM as a Cloud Service. | adobe/ | 197 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 4747 | 4747.Brownfield Adoption Step-by-step process for adopting Cavekit on an existing codebase. | hashgraph-online/ | 1.3k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | today |
| 4748 | 4748.Chunking A skill your agent uses when splitting extracted text into chunks for LLM context windows or RAG ingestion. | hashgraph-online/ | 1.3k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 4749 | 4749.Complexity Detection 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/ | 1.3k | — | ~1k | Automated safety check: Pass | Apache-2.0 | today |
| 4750 | 4750.Eval Quality and performance evaluation with baseline comparison. | hashgraph-online/ | 1.3k | — | ~2k | Automated safety check: Pass | Apache-2.0 | today |
| 4751 | 4751.Extracting Keywords 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/ | 1.3k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | today |
| 4752 | Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai | hashgraph-online/ | 1.3k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
Explore related skills
Topics in AI & LLM Engineering
- Building AI agents546
- Deep learning407
- Embeddings375
- LLM inference and serving373
- Prompt engineering347
- Retrieval-augmented generation346
- LLM evaluation306
- Fine-tuning306
- Speech recognition and synthesis304
- Structured output and tool calling267
- Model routing and gateways256
- LLM cost and token optimization254
- LLM API integration251
- LLM observability240
- LLM guardrails217
- Computer vision195
- Model hubs and datasets179
- GPU and accelerator computing174
- Diffusion and image models165
- Natural language processing130
- Reinforcement learning66
- AI interpretability23
Products these skills work with
Roles that use these skills
Other categories
- Development15,214
- Frontend & Design5,827
- Backend & APIs7,095
- Testing & QA5,045
- DevOps & Cloud5,975
- Databases2,347
- Data & Analytics3,623
- Agent Workflows8,310
- Documents & Office4,299
- Writing & Content3,744
- Marketing & SEO3,900
- Sales & Support1,809
- Research & Science6,061
- Security3,085
- Productivity & Automation4,039
- Business, Finance & HR3,855
- Legal & Compliance1,617
- Education1,078
- Media & Creative4,318
- Mobile2,746
- Product & Project Management2,329
- Knowledge Management1,439
- Game Development1,660