Search
AI & LLM Engineering · By VectorSpaceLab
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy… | VectorSpaceLab/ | 330 | — | ~1.2k | Automated safety check: Pass | Unknown | 1 mo ago |
| 2 | Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime… | VectorSpaceLab/ | 330 | — | ~1.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 3 | A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend. | VectorSpaceLab/ | 330 | — | ~500 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4 | 4.Autogen A skill your agent uses for maintaining, migrating, debugging, and safely operating Microsoft AutoGen Python 0.7.x applications, including AgentChat, Core runtimes, extensions, Studio, Magentic-One… | VectorSpaceLab/ | 330 | — | ~1.5k | Automated safety check: Pass | Unknown | 1 mo ago |
| 5 | A skill your agent uses when selecting Sentence Transformers inference backends or exporting/optimizing models for PyTorch, ONNX, or OpenVINO. | VectorSpaceLab/ | 330 | — | ~766 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 6 | 6.Chunking Configure and validate Unstructured post-partition chunking for RAG, embedding, and downstream processing. | VectorSpaceLab/ | 330 | — | ~974 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 7 | Use this sub-skill for Torch-TensorRT model compilation, dynamic input planning, torch.export workflows, save/load formats, raw TensorRT engines, and compile-time troubleshooting. | VectorSpaceLab/ | 330 | — | ~1.3k | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 8 | Use this RAGs sub-skill to inspect, edit, update, delete, and troubleshoot generated RAG agent configuration and cache state. | VectorSpaceLab/ | 330 | — | ~756 | Automated safety check: Pass | MIT | 1 mo ago |
| 9 | Use this DeepCTR sub-skill for SparseFeat, DenseFeat, VarLenSparseFeat, hashing, embedding sharing, input dictionaries, and tabular or sequence feature-column validation. | VectorSpaceLab/ | 330 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 10 | Use this sub-skill when constructing torchvision datasets, validating dataset roots and downloads, wrapping datasets for transforms v2, decoding or encoding images with torchvision.io, or using… | VectorSpaceLab/ | 330 | — | ~760 | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 11 | 11.Deepctr Use this DeepCTR repo skill for CTR/recommender feature columns, Keras models, sequence/session models, multitask models, and legacy TensorFlow Estimator workflows. | VectorSpaceLab/ | 330 | — | ~630 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 12 | 12.Detection A skill your agent uses for PaddleViT object detection workflows with DETR, Swin, or PVTv2: validate COCO data, select configs, build/train/evaluate models, reason about transforms, losses… | VectorSpaceLab/ | 330 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 13 | 13.Diffusers A skill your agent uses for Hugging Face Diffusers tasks: pipeline inference, schedulers, adapters/loaders, training recipes, modular pipelines, conversion helpers, CLI checks, and repo maintenance. | VectorSpaceLab/ | 330 | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 14 | 14.Embeddings Add embeddings to Unstructured elements with provider-specific encoders, credential-safe configuration, and metadata-preserving enrichment checks. | VectorSpaceLab/ | 330 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 15 | 15.Espnet A skill your agent uses when working with ESPnet speech AI toolkit: installation, ESPnet2 recipes and training, pretrained inference/model zoo, ESPnet3 stage workflows, and repository testing. | VectorSpaceLab/ | 330 | — | ~1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 16 | Build ONNX export and validation commands, package/load timm models via Hugging Face Hub or local directories, use Torch Hub compatibility, and safely clean or average checkpoints. | VectorSpaceLab/ | 330 | — | ~1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 17 | 17.Feast A skill your agent uses for Feast feature store tasks: feature repositories, definitions, CLI, retrieval, materialization, serving, RAG/vector search, integrations, and Feast contributor workflows. | VectorSpaceLab/ | 330 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 18 | Use this operating skill for Tencent-Hunyuan/HunyuanVideo text-to-video setup, checkpoint layout, inference commands, Gradio launch, and CUDA/FP8/xDiT troubleshooting. | VectorSpaceLab/ | 330 | — | ~1.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 19 | 19.Imgaug A skill your agent uses when working with imgaug image augmentation pipelines, aligned annotations, stochastic parameters, dtype/data utilities, or multicore augmentation for computer-vision data. | VectorSpaceLab/ | 330 | — | ~1.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 20 | Use this sub-skill for Ultralytics YOLO predict workflows, source handling, streaming and batching, Results extraction, saving/plotting/cropping, and thread-safe inference. | VectorSpaceLab/ | 330 | — | ~1.4k | Automated safety check: Pass | AGPL-3.0 | 1 mo ago |
| 21 | Use torchtune generation, Eleuther evaluation, and quantization workflows safely after checkpoints exist. | VectorSpaceLab/ | 330 | — | ~1k | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 22 | A skill your agent uses when running RobustVideoMatting inference, loading weights, using convertvideo or TorchHub, converting image/video inputs, or reasoning about exported model runtimes. | VectorSpaceLab/ | 330 | — | ~1.2k | Automated safety check: Pass | GPL-3.0 | 1 mo ago |
| 23 | Load local files or raw text into LlamaIndex Documents, split them into metadata-aware nodes, and run ingestion pipelines with cache/docstore controls. | VectorSpaceLab/ | 330 | — | ~931 | Automated safety check: Pass | MIT | 1 mo ago |
| 24 | 24.Lie Tensor A skill your agent uses for PyPose LieTensor and manifold computation: choose SO3, SE3, Sim3, or RxSO3 group/algebra representations; construct, batch, convert, compose, act, retract, differentiate… | VectorSpaceLab/ | 330 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 25 | 25.Litellm A skill your agent uses for LiteLLM Python SDK, AI Gateway proxy, model routing, provider endpoint mapping, MCP/A2A agent tooling, pass-through routes, guardrails, virtual keys, spend tracking, and… | VectorSpaceLab/ | 330 | — | ~1.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 26 | 26.Make It 3D Use this repo skill for Make-It-3D single-image 3D creation, including CUDA asset setup, alpha-image validation, coarse NeRF optimization, refinement, rendering, export, and troubleshooting. | VectorSpaceLab/ | 330 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 27 | 27.Mmdetection A skill your agent uses when working with MMDetection 3.x for object detection, instance/panoptic segmentation, tracking-adjacent configs, model zoo configs, inference, visualization… | VectorSpaceLab/ | 330 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 28 | 28.Model API A skill your agent uses when working with RobustVideoMatting MattingNetwork APIs, recurrent states, model variants, refiners, tensor shapes, and safe synthetic forward checks. | VectorSpaceLab/ | 330 | — | ~1.1k | Automated safety check: Pass | GPL-3.0 | 1 mo ago |
| 29 | Use torchsummary.summary and torchsummary.summarystring to inspect PyTorch nn.Module shapes, parameter counts, devices, dtypes, and memory estimates. | VectorSpaceLab/ | 330 | — | ~847 | Automated safety check: Pass | MIT | 1 mo ago |
| 30 | Use this sub-skill for MLflow Models, pyfunc, flavor APIs, signatures, input examples, dependencies, local serving/prediction, and mlflow.evaluate workflows. | VectorSpaceLab/ | 330 | — | ~675 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 31 | Use torchtune model/tokenizer builders, PEFT modules, losses, conversion utilities, and modeling components safely. | VectorSpaceLab/ | 330 | — | ~1.2k | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 32 | Use this sub-skill for MLAlgorithms NeuralNet construction, activations, losses, parameters, constraints, regularizers, optimizers, convolutional/recurrent layers, and DQN wiring. | VectorSpaceLab/ | 330 | — | ~941 | Automated safety check: Pass | MIT | 1 mo ago |
| 33 | Use this operating sub-skill to create, adapt, and troubleshoot ManimML neural-network scenes: NeuralNetwork containers, feed-forward and convolutional layers… | VectorSpaceLab/ | 330 | — | ~1.3k | Automated safety check: Pass | MIT | 1 mo ago |
| 34 | Use torchvision.ops for boxes, NMS, ROI pooling/alignment, detection helper concepts, and extension-dependent troubleshooting. | VectorSpaceLab/ | 330 | — | ~698 | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 35 | A skill your agent uses for Feast RAG, vector search, vector-indexed fields, vector online stores, document embedding/chunking, retrieveonlinedocuments APIs, DocEmbedder, FeastVectorStore, and… | VectorSpaceLab/ | 330 | — | ~622 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 36 | 36.Rags Use this repo skill for RAGs, a Streamlit app that builds configurable LlamaIndex RAG agents from natural-language setup, data sources, and model settings. | VectorSpaceLab/ | 330 | — | ~1k | Automated safety check: Pass | MIT | 1 mo ago |
| 37 | A skill your agent uses when modifying PEFT itself, preparing a PEFT pull request, adding a new PEFT method, selecting contributor tests, or checking PEFT contribution/style/backward-compatibility… | VectorSpaceLab/ | 330 | — | ~746 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 38 | 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/ | 330 | — | ~807 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 39 | 39.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/ | 330 | — | ~879 | Automated safety check: Pass | Unknown | 1 mo ago |
| 40 | 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/ | 330 | — | ~1k | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 41 | 41.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/ | 330 | — | ~1.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 42 | 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/ | 330 | — | ~3.2k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 43 | 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/ | 330 | — | ~823 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 44 | Build and review OpenRLHF supervised/preference training plans for SFT, reward models, DPO, IPO, and cDPO. | VectorSpaceLab/ | 330 | — | ~1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 45 | Use this repo skill for Microsoft Swin-Transformer image-classification model, config, data, checkpoint, SimMIM, Swin-MoE, and optional CUDA acceleration workflows. | VectorSpaceLab/ | 330 | — | ~1.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 46 | 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/ | 330 | — | ~2.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 47 | 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/ | 330 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 48 | 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/ | 330 | — | ~910 | Automated safety check: Pass | Unknown | 1 mo ago |
