Search
AI & LLM Engineering · For developers
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 2209 | 2209.GPU Optimizer GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile. | Mathews-Tom/ | 329 | — | ~3.5k | Automated safety check: Notes | MIT | 5 days ago |
| 2210 | Java/Maven single-module deep documentation generator. An agent skill from LeoYeAI/openclaw-master-skills. | LeoYeAI/ | 2.2k | — | ~3.4k | Automated safety check: Pass | MIT | 2 mo ago |
| 2211 | 2211.Neolata Mem Graph-native memory engine for AI agents — hybrid vector+keyword search, biological decay, Zettelkasten linking, trust-gated conflict resolution, explainability, episodes, compression & consolidation. | LeoYeAI/ | 2.2k | — | ~4.1k | Automated safety check: Pass | MIT | 2 mo ago |
| 2212 | 2212.Veadk Skills 根据用户的功能需求，完成与 VeADK 相关的功能。 | LeoYeAI/ | 2.2k | 1 repo | ~293 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 2213 | A skill your agent uses when selecting Sentence Transformers inference backends or exporting/optimizing models for PyTorch, ONNX, or OpenVINO. | VectorSpaceLab/ | 331 | — | ~766 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 2214 | 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/ | 331 | — | ~1.3k | Automated safety check: Pass | BSD-3-Clause | 1 mo ago |
| 2215 | 2215.Embeddings Add embeddings to Unstructured elements with provider-specific encoders, credential-safe configuration, and metadata-preserving enrichment checks. | VectorSpaceLab/ | 331 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 2216 | 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/ | 331 | — | ~1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 2217 | 2217.Hunyuan Video Use this operating skill for Tencent-Hunyuan/HunyuanVideo text-to-video setup, checkpoint layout, inference commands, Gradio launch, and CUDA/FP8/xDiT troubleshooting. | VectorSpaceLab/ | 331 | — | ~1.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 2218 | 2218.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/ | 331 | — | ~1.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 2219 | 2219.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/ | 331 | — | ~1k | Automated safety check: Pass | MIT | 1 mo ago |
| 2220 | 2220.Repo Development 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/ | 331 | — | ~746 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 2221 | 2221.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 |
| 2222 | 2222.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 |
| 2223 | 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 |
| 2224 | 2224.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 |
| 2225 | 2225.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 |
| 2226 | 2226.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 |
| 2227 | 2227.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 |
| 2228 | 2228.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 |
| 2229 | 2229.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 |
| 2230 | 2230.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 | 6 days ago |
| 2231 | 2231.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 | 6 days ago |
| 2232 | 2232.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 | 6 days ago |
| 2233 | 2233.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 | 6 days ago |
| 2234 | 2234.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 | 6 days ago |
| 2235 | 2235.Phx Verify Verify Elixir/Phoenix changes — compile, format, and test in one loop. | oliver-kriska/ | 565 | — | ~1.3k | Automated safety check: Pass | MIT | 6 days ago |
| 2236 | 2236.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 | 6 days ago |
| 2237 | 2237.Gf Lint SystemVerilog lint checker with structured output for orchestration. | codejunkie99/ | 117 | — | ~1.5k | Automated safety check: Notes | Unknown | 25 days ago |
| 2238 | 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 |
| 2239 | 2239.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 |
| 2240 | 2240.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 | yesterday |
| 2241 | 2241.Roo Fix Volatile Msg Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path). | OnlyTerp/ | 114 | — | ~1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 2242 | 2242.Release Release a package to NPM. An agent skill from tetherto/qvac. | tetherto/ | 685 | — | ~1.6k | Automated safety check: Warn | Apache-2.0 | yesterday |
| 2243 | 2243.Review Run a comprehensive code review with 4 specialized reviewers (security, correctness, performance, consistency) in parallel. | tetherto/ | 685 | — | ~3.3k | Automated safety check: Warn | Apache-2.0 | yesterday |
| 2244 | 在已经过独立验证的 CLIProxyAPI upstream 之上部署 NewAPI 计费层，把 Codex/Claude/Gemini/Qwen 等订阅账号包装成可计费的 OpenAI 兼容 API。本 Skill 不负责新建裸 CLIProxyAPI；负责 NewAPI Docker 部署、容器到宿主桥接、模型计费倍率、参数化额度修正、多账号 OAuth… | majiayu000/ | 287 | — | ~1.7k | Automated safety check: Warn | MIT | 3 days ago |
| 2245 | 2245.Golem Add LLM Rust Adds provider-backed AI capabilities to a Rust Golem agent. An agent skill from golemcloud/golem. | golemcloud/ | 1.5k | — | ~712 | Automated safety check: Pass | Unknown | yesterday |
| 2246 | 2246.Langgraph LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool… | yonatangross/ | 292 | — | ~4.2k | Automated safety check: Pass | MIT | yesterday |
| 2247 | Ankh 蛋白质语言模型昇腾 NPU 迁移 Skill，适用于 Ankh base/large、Ankh3 large/XL 以及同类基于 HuggingFace Transformers 与 PyTorch 的蛋白模型从 CUDA/GPU 到华为 Ascend NPU 的环境检查、代码适配、权重加载、验证脚本补齐与文档沉淀。 | ascend-ai-coding/ | 174 | — | ~2.1k | Automated safety check: Pass | No licence | yesterday |
| 2248 | 昇腾 TensorFlow Community 迁移适配 Skill，适用于将基于 TensorFlow 2.x 的模型原生部署到华为 Ascend NPU，而不经过 TF 到 PyTorch 转换，覆盖 aarch64 源码编译 TF 2.6.5、tfplugin 安装、自动迁移工具使用、手动适配与精度验证。 | ascend-ai-coding/ | 174 | — | ~2.1k | Automated safety check: Pass | No licence | yesterday |
| 2249 | BoltzGen 昇腾 NPU 迁移与复现 Skill，适用于在华为 Ascend NPU 上部署 BoltzGen 生成式蛋白设计与逆折叠流程，覆盖环境准备、权重缓存、cuEquivariance 兼容、源码适配和端到端推理验证。 | ascend-ai-coding/ | 174 | — | ~3.8k | Automated safety check: Pass | No licence | yesterday |
| 2250 | DeepFRI 的 TensorFlow 到 PyTorch 转换与昇腾 NPU 迁移 Skill，适用于蛋白质功能预测场景下的 TF 模型分析、PyTorch 重写、权重逐层映射、NPU 推理与精度验证，尤其适合需要在 Ascend 上运行 DeepFRI CNN 或 GCN 路径时使用。 | ascend-ai-coding/ | 174 | — | ~2.4k | Automated safety check: Pass | No licence | yesterday |
| 2251 | DeepFRI TensorFlow 原生昇腾 NPU 迁移 Skill，适用于不做 TF 到 PyTorch 转换、而是直接使用 TensorFlow 2.6.5 与 npudevice 在华为 Ascend 上运行 DeepFRI 的场景，覆盖源码编译、tfplugin 安装、代码适配、推理与 CPU 对比验证。 | ascend-ai-coding/ | 174 | — | ~2.1k | Automated safety check: Pass | No licence | yesterday |
| 2252 | DiffSBDD 昇腾 NPU 迁移 Skill，适用于将基于等变扩散模型的结构化药物设计项目从 CUDA 迁移到华为 Ascend NPU，覆盖环境搭建、依赖安装、torchscatter 源码编译、代码适配以及 de novo 推理验证。 | ascend-ai-coding/ | 174 | — | ~898 | Automated safety check: Pass | No licence | yesterday |
| 2253 | GENERator DNA 序列生成模型的昇腾 NPU 迁移 Skill，适用于将基于 HuggingFace Transformers 的 Causal LM 从 CUDA 迁移到华为 Ascend NPU，覆盖环境搭建、依赖安装、代码适配、多进程处理和 sequence recovery 验证。 | ascend-ai-coding/ | 174 | — | ~827 | Automated safety check: Pass | No licence | yesterday |
| 2254 | OligoFormer 昇腾 NPU 迁移 Skill，适用于将基于 PyTorch Transformer 的 siRNA 效能预测模型迁移到华为 Ascend NPU，覆盖环境搭建、RNA-FM 依赖安装、代码适配、推理验证与可选训练流程。 | ascend-ai-coding/ | 174 | — | ~1.3k | Automated safety check: Pass | No licence | yesterday |
| 2255 | ProteinBERT 昇腾 NPU 部署与迁移 Skill，适用于将 TensorFlow 或 Keras 版 ProteinBERT 转成基于 PyTorch 与 torchnpu 的实现，覆盖权重转换、embedding 提取、微调训练、注意力可视化和 GPU 与 NPU 精度验证。 | ascend-ai-coding/ | 174 | — | ~1.9k | Automated safety check: Pass | No licence | yesterday |
| 2256 | TensorFlow 或 Keras 模型改写到 PyTorch 的通用 Skill，适用于在华为 Ascend NPU 或其他依赖 PyTorch 生态的平台上完成层级映射、权重转换、逐层数值验证和端到端精度对比，尤其适合 ProteinBERT、DeepFRI 这类科学模型的跨框架迁移。 | ascend-ai-coding/ | 174 | — | ~3.4k | Automated safety check: Pass | No licence | yesterday |
