Category
Best AI and LLM engineering skills, page 87
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 |
|---|---|---|---|---|---|---|---|---|
| 4129 | 4129.Council Multi-persona debate for founder decisions. An agent skill from assafkip/kipi-system. | assafkip/ | 112 | — | ~962 | Automated safety check: Pass | MIT | 2 days ago |
| 4130 | 4130.Z Sci Viz Lab 可视化科普 skill。当用户要求"可视化科普""互动科普实验""科学交互演示""把XX做成互动页面""像挂谷猜想那样做个科普页"时使用。把任何数学或科学概念(如挂谷猜想、日食、月食、太阳系、四季、月相、潮汐)变成电脑和手机都能访问的单页互动实验:先事实核验,再建直觉模型,给出正式定义,设计参数滑杆加实时反馈的互动实验,写清边界说明与来源追溯,最后用 Vite 打包单文件并发布到… | tjxj/ | 548 | — | ~647 | Automated safety check: Pass | No licence | 19 days ago |
| 4131 | 4131.GPU Use 查看远程服务器 GPU 使用情况。SSH 连接服务器,展示每张卡的显存占用、运行进程、所属容器。当用户说查看 GPU、显卡占用、显存使用时使用 | majiayu000/ | 287 | — | ~761 | Automated safety check: Notes | MIT | 3 days ago |
| 4132 | Autonomously build a complete Power Automate flow from a description. | microsoft/ | 984 | — | ~2.5k | Automated safety check: Notes | MIT | yesterday |
| 4133 | Lists Power Platform connections in the current environment. | microsoft/ | 984 | — | ~439 | Automated safety check: Notes | MIT | yesterday |
| 4134 | Check Power Platform environment routing status and understand default environment resolution. | microsoft/ | 984 | — | ~754 | Automated safety check: Notes | MIT | yesterday |
| 4135 | A skill your agent uses when the user wants to discover and verify available Entra ID app registrations, wire one to a Power Apps Wrap mobile app, or create one through the Wrap page and update… | microsoft/ | 984 | — | ~2.8k | Automated safety check: Notes | MIT | yesterday |
| 4136 | Set up Power Automate CLI prerequisites. An agent skill from microsoft/power-platform-skills. | microsoft/ | 984 | — | ~3.5k | Automated safety check: Notes | MIT | yesterday |
| 4137 | A skill your agent uses when the user wants to enable, disable, turn on or off, opt out of, opt in to, or check the status of power-automate telemetry / usage data. | microsoft/ | 984 | — | ~635 | Automated safety check: Notes | MIT | yesterday |
| 4138 | 4138.Mc Rhythm Section Rhythm section arranging and MIDI programming (节奏组与打ち込み) - drums, bass and harmony instruments as one unit, and how to make programmed parts sound played. | jtydhr88/ | 154 | — | ~3.2k | Automated safety check: Pass | MIT | 19 days ago |
| 4139 | Cost guardrail for AWS DevOps Agent that covers ALL AWS services and native agent tools. | aws/ | 103 | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 4140 | 4140.Model Sovereignty This skill should be used when the user asks about "local models", "custom models", "fine-tuning", "self-hosting models", "model selection", "which model should I use", "data privacy and models"… | Habitat-Thinking/ | 114 | — | ~1k | Automated safety check: Pass | Unknown | 21 days ago |
| 4141 | 4141.Golem Add LLM Effect Adding provider-backed LLM text generation to an Effect-based Golem agent with effect/unstable/ai and an Effect AI provider. | golemcloud/ | 1.5k | — | ~3.3k | Automated safety check: Pass | Unknown | yesterday |
| 4142 | Adding LLM and AI capabilities to a MoonBit Golem agent. An agent skill from golemcloud/golem. | golemcloud/ | 1.5k | — | ~1.5k | Automated safety check: Pass | Unknown | yesterday |
| 4143 | 4143.Golem Add LLM Scala Adding LLM and AI capabilities to a Scala Golem agent. An agent skill from golemcloud/golem. | golemcloud/ | 1.5k | — | ~1.7k | Automated safety check: Pass | Unknown | yesterday |
| 4144 | 4144.Golem Add LLM TS Adding LLM and AI capabilities to a TypeScript Golem agent. An agent skill from golemcloud/golem. | golemcloud/ | 1.5k | — | ~1.3k | Automated safety check: Pass | Unknown | yesterday |
| 4145 | Understanding and parsing Golem CLI structured output. An agent skill from golemcloud/golem. | golemcloud/ | 1.5k | — | ~1.6k | Automated safety check: Pass | Unknown | yesterday |
| 4146 | Pre-creating Effect-based Golem agent instances with golem agent new. | golemcloud/ | 1.5k | — | ~1.4k | Automated safety check: Pass | Unknown | yesterday |
| 4147 | Pre-creating MoonBit Golem agent instances via CLI. An agent skill from golemcloud/golem. | golemcloud/ | 1.5k | — | ~1k | Automated safety check: Pass | Unknown | yesterday |
| 4148 | Creating a new Rust Golem agent instance with golem agent new. | golemcloud/ | 1.5k | — | ~983 | Automated safety check: Pass | Unknown | yesterday |
| 4149 | Creating a new Scala Golem agent instance with golem agent new. | golemcloud/ | 1.5k | — | ~1k | Automated safety check: Pass | Unknown | yesterday |
| 4150 | Creating a new TypeScript Golem agent instance with golem agent new. | golemcloud/ | 1.5k | — | ~981 | Automated safety check: Pass | Unknown | yesterday |
| 4151 | 4151.Xs Transcriber 音声ファイルをテキストに文字起こしするスキル。mp3/wav/m4a/ogg/flac形式に対応。whisperベースのtranscribertoolを使用し、tiny/base/small/medium/largeの5つのモデルから精度と速度のバランスを選択可能。長時間音声はバックグラウンド実行に対応。「文字起こしして」「音声をテキストに変換して」で使用。 | karaage0703/ | 136 | — | ~548 | Automated safety check: Pass | MIT | 18 days ago |
| 4152 | 4152.RAG Retrieval Retrieval-Augmented Generation patterns for grounded LLM responses. | yonatangross/ | 292 | — | ~4.4k | Automated safety check: Pass | MIT | yesterday |
| 4153 | A skill your agent uses when implementing staking contracts, reward distribution systems, or yield farming. | ccashwell/ | 131 | — | ~1.7k | Automated safety check: Pass | MIT | 11 days ago |
| 4154 | 4154.Nanogpt Training Train GPT-2 scale models (~124M parameters) efficiently on a single GPU. | benchflow-ai/ | 1.8k | — | ~882 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 4155 | 4155.Trl Reference for the TRL (Transformer Reinforcement Learning) library codebase. | benchflow-ai/ | 1.8k | — | ~989 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 4156 | Toolkit for structuring hypotheses, variants, guardrails, and measurement plans. | gtmagents/ | 414 | 1 repo | ~837 | Automated safety check: Pass | Apache-2.0 | 6 mo ago |
| 4157 | 4157.Conversational UX Design voice and conversational interfaces — dialog flows, error recovery, and persona. | Owl-Listener/ | 2.9k | — | ~1.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 4158 | 4158.Pp Bandsintown Turn Bandsintown's two read-only endpoints into a tour-routing brain: local cache, calendar-gap detection, lineup... | mvanhorn/ | 2.1k | — | ~3k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 4159 | 4159.Pp Ollama Cloud Routes every prompt to the right hosted Ollama model. An agent skill from mvanhorn/printing-press-library. | mvanhorn/ | 2.1k | — | ~2.9k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 4160 | 4160.Pp Posthog Every PostHog resource in one CLI — with offline search, agent-native output, and cross-resource analytics no... | mvanhorn/ | 2.1k | — | ~3.2k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 4161 | 4161.Scholar Compute Design and execute computational social science analyses across 11 modules: text-as-data/NLP (STM, BERTopic, Wordfish, BERT, conText embedding regression, LLM annotation + DSL bias correction… | joshzyj/ | 168 | — | ~15k | Automated safety check: Pass | Unknown | 23 days ago |
| 4162 | 4162.Scholar Hypothesis Develop theoretically grounded hypotheses and draft publication-ready Theory sections. | joshzyj/ | 168 | — | ~11k | Automated safety check: Pass | Unknown | 23 days ago |
| 4163 | 4163.Scholar Open Implement open science practices for a social science study. | joshzyj/ | 168 | — | ~14k | Automated safety check: Pass | Unknown | 23 days ago |
| 4164 | Get one actionable improvement for your AI product based on the latest GenAI PM briefs. | menkesu/ | 434 | — | ~1.8k | Automated safety check: Pass | Unknown | 5 days ago |
| 4165 | 4165.Sc Clustering Load when building the neighbour graph, embedding (UMAP/t-SNE/diffmap/PHATE), and clustering (Leiden/Louvain) on a normalised single-cell AnnData. | TianGzlab/ | 161 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | 4 days ago |
| 4166 | 4166.Sc Metacell Load when aggregating single cells into metacells (sample-aware coarse-grained pseudo-cells) on a normalised scRNA AnnData via SEACells or KMeans on a low-D embedding. | TianGzlab/ | 161 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 4 days ago |
| 4167 | 4167.Spatial Integrate Load when removing batch effects from multi-batch spatial AnnData with PCA using Harmony, BBKNN, or Scanorama. | TianGzlab/ | 161 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 4 days ago |
| 4168 | DL cell/nucleus segmentation for fluorescence and brightfield microscopy. | jaechang-hits/ | 374 | 1 repo | ~3.5k | Automated safety check: Pass | BSD-3-Clause | 12 days ago |
| 4169 | Computer vision for bio-image preprocessing, feature detection, real-time microscopy. | jaechang-hits/ | 374 | 1 repo | ~3.9k | Automated safety check: Pass | Apache-2.0 | 12 days ago |
| 4170 | PyTorch Geometric (PyG) for graph neural networks: node/graph classification, link prediction with GCN, GAT, GraphSAGE, GIN. | jaechang-hits/ | 374 | 1 repo | ~5.1k | Automated safety check: Pass | MIT | 12 days ago |
| 4171 | 4171.Transformers Bio NLP HuggingFace Transformers with biomedical LMs (BioBERT, PubMedBERT, BioGPT, BioMedLM) for scientific NLP: NER (genes, diseases, chemicals), relation extraction, QA, text classification, abstract… | jaechang-hits/ | 374 | 1 repo | ~4.9k | Automated safety check: Pass | Apache-2.0 | 12 days ago |
| 4172 | 4172.Npu Torchair Infer Migrate any HuggingFace model to Ascend NPU torchair graph mode (torch.compile) and benchmark it for accuracy and performance against NPU eager and CPU eager. | ascend-ai-coding/ | 174 | — | ~1.3k | Automated safety check: Pass | No licence | yesterday |
| 4173 | 4173.Torch Npu Comm Test 通过 PyTorch torch.distributed 接口测试昇腾 NPU 通信算子性能。支持指定任意 tensor shape、dtype,使用 torchrun 启动,贴近真实训练场景的通信算子测试与性能分析。Use for testing collective communication operators (AllReduce, AllGather, ReduceScatter… | ascend-ai-coding/ | 174 | — | ~2.2k | Automated safety check: Pass | No licence | yesterday |
| 4174 | 4174.Vllm Ascend vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU. | ascend-ai-coding/ | 174 | — | ~2.7k | Automated safety check: Pass | No licence | yesterday |
| 4175 | Track daily PRs and Issues from vllm-project/vllm and vllm-project/vllm-ascend, filter by model (DeepSeek/Qwen/GLM/MiniMax/Kimi) and tech topics (PD disaggregation, MTP, quantization, graph mode… | ascend-ai-coding/ | 174 | — | ~731 | Automated safety check: Pass | No licence | yesterday |
| 4176 | 4176.Voice Agents Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. | benjaminasterA/ | 375 | 1 repo | ~519 | Automated safety check: Pass | MIT | 2 days ago |
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