Category
Best AI and LLM engineering skills, page 101
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 |
|---|---|---|---|---|---|---|---|---|
| 4801 | 4801.Pp Twelvelabs Printing Press CLI for Twelvelabs. An agent skill from mvanhorn/printing-press-library. | mvanhorn/ | 2.1k | — | ~3.7k | Automated safety check: Notes | Apache-2.0 | today |
| 4802 | 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 | today |
| 4803 | 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 | today |
| 4804 | Boltz2 蛋白质结构预测模型的昇腾 NPU 迁移与复现 Skill,适用于在华为 Ascend 910、910B、910C 上准备权重、适配 Lightning 和 CUDA only kernel、完成 Boltz2 端到端结构预测推理,并沉淀可复现的环境与验证命令。 | ascend-ai-coding/ | 174 | — | ~2.8k | Automated safety check: Pass | No licence | today |
| 4805 | 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 | today |
| 4806 | 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 | today |
| 4807 | 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 | today |
| 4808 | 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 | today |
| 4809 | 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 | today |
| 4810 | 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 | today |
| 4811 | 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 | today |
| 4812 | 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 | today |
| 4813 | HuggingFace Diffusers 环境配置指南,用于华为昇腾 NPU。覆盖 CANN 版本检测、PyTorch + torchnpu 安装、Diffusers 库安装及环境验证。当用户需要在昇腾 NPU 上配置 Diffusers 环境时使用。 | ascend-ai-coding/ | 174 | — | ~566 | Automated safety check: Pass | No licence | today |
| 4814 | Diffusers Pipeline 推理指南,用于华为昇腾 NPU。覆盖环境预检、通用 Pipeline 推理(图像/视频模型)、内存优化(CPU offload、attention slicing、VAE slicing)、LoRA 加载与融合、多卡推理和按版本检索 Diffusers API。用户一旦提到在昇腾 NPU 上运行 FLUX、SDXL、Wan、CogVideoX 等… | ascend-ai-coding/ | 174 | — | ~3.2k | Automated safety check: Pass | No licence | today |
| 4815 | 基于 PyTorch 框架的昇腾 NPU 模型推理融合算子优化技能。分析模型代码,识别可替换为 torchnpu 融合算子的计算模式,生成替换方案。触发场景:torchnpu 融合算子替换、MoE/Attention/FFN/Norm 等模块的推理算子适配、torchnpu API 使用咨询。基于仓库已有模型的融合算子经验,按计算语义推荐最佳方案。 | ascend-ai-coding/ | 174 | — | ~1.7k | Automated safety check: Pass | No licence | today |
| 4816 | 基于 PyTorch 框架的昇腾 NPU 模型推理适配与部署基线技能。从 HF 链接或本地模型代码出发,按 cann-recipes-infer 仓库规范适配到 ModelRunner 推理框架,输出可运行的标准模型目录和性能基线数据。触发场景:新模型适配到昇腾 NPU 推理框架、已有模型的部署基线采集、模型迁移和初始跑通验证。 | ascend-ai-coding/ | 174 | — | ~1.8k | Automated safety check: Pass | No licence | today |
| 4817 | 从用户 PyTorch/Python 代码中提取算子实现,构建为算子任务格式的标准化 任务文件。支持两种模式:单 case(单一自包含 .py,getinputs 返回单组)和 多 case(.py + 同名 .json 配对,getinputgroups 返回多组)。 | ascend-ai-coding/ | 174 | — | ~1.4k | Automated safety check: Pass | No licence | today |
| 4818 | 能完成昇腾NPU驱动和固件安装部署,实现安装包正则匹配提取、按需添加可执行权限、Python+Shell双重包校验、系统依赖先验后装、适配CentOS/RHEL/Ubuntu/Debian系统,适用于昇腾NPU驱动和固件安装部署。 | ascend-ai-coding/ | 174 | — | ~663 | Automated safety check: Notes | No licence | today |
| 4819 | 根据设计文档生成 AscendC 算子完整代码实现并完成框架适配。TRIGGER when: 设计文档已完成,需要生成 ophost/opkernel 代码、注册到 PyTorch 框架、编译测试。关键词:代码生成、ophost、opkernel、tiling、kernel、框架适配、算子注册。 | ascend-ai-coding/ | 174 | — | ~2k | Automated safety check: Pass | No licence | today |
| 4820 | Ascend C 算子 mssanitizer 内存检测分析技能。用于检测和分析算子内存问题:非法内存访问、非法释放、内存泄漏、UB地址越界,生成问题报告。自动识别算子工程类型(ops算子仓用GE IR模式,自定义算子用Python模式)。触发关键词:mssanitizer、内存检测、内存泄漏、非法访问、illegal free、内存错误。 | ascend-ai-coding/ | 174 | — | ~3.4k | Automated safety check: Pass | No licence | today |
| 4821 | 自动生成 ATB 到 ACLNN 算子替换的详细设计文档。接收用户提供的 ATB 和 ACLNN 接口文档链接, 输出包含参数映射、开发自测、风险评估的 7 章结构化设计文档。 | ascend-ai-coding/ | 174 | — | ~2.4k | Automated safety check: Pass | No licence | today |
| 4822 | Generate migration deliverables for bringing relevant Megatron changes into MindSpeed after branch alignment and impact mapping are complete. | ascend-ai-coding/ | 174 | — | ~1.3k | Automated safety check: Pass | No licence | today |
| 4823 | Verl 单异步 DAPO 训练配置生成器。触发场景:(1) 启动单异步 DAPO 训练 (2) 生成训练脚本 (3) 配置特性参数 (4) 训练前检查。特性策略:用户未指定时默认开启性能特性(flashattn/dynamicbatch/removepadding/gradientcheckpointing),显存特性(offload/recompute)默认关闭。OOM… | ascend-ai-coding/ | 174 | — | ~1.2k | Automated safety check: Pass | No licence | today |
| 4824 | 昇腾 NPU 平台 vLLM 大模型推理服务一键部署。触发:用户说'部署 模型名'、'NPU 部署模型'、'vllm serve'。流程:SSH检查 → NPU检查 → 配置发现(必须验证) → 用户确认 → 部署 → cron监控 → 验证。约束:(1) 配置必须从官方文档验证,禁止猜测;(2) 后台启动必须用cron监控,禁止手动轮询。支持… | ascend-ai-coding/ | 174 | — | ~1.2k | Automated safety check: Pass | No licence | today |
| 4825 | 面向 Ascend PyTorch Profiler / msprof DB(如 ascendpytorchprofiler.db、msprof.db)的 SQL 分析技能。将自然语言问题(算子耗时、通信、下发、调度、schema/table 查询)转为安全可执行 SQL,并按需从官方文档提取表结构详情。 | ascend-ai-coding/ | 174 | — | ~1.4k | Automated safety check: Pass | No licence | today |
| 4826 | 模型层 Tensor 打点与精度对比工具。用于在模型 forward 过程中捕获模型各层中间 tensor,实现 GPU/NPU 精度对比调试。支持 vLLM、SGLang 推理框架。When to use: When you need to debug precision issues between GPU and NPU,or validate layer-wise tensor… | ascend-ai-coding/ | 174 | — | ~2.4k | Automated safety check: Pass | No licence | today |
| 4827 | MindSpeed-MM multimodal model suite environment setup guide for Huawei Ascend NPU. | ascend-ai-coding/ | 174 | — | ~3.1k | Automated safety check: Pass | No licence | today |
| 4828 | MindSpeed-MM skill router and model index for Huawei Ascend NPU. | ascend-ai-coding/ | 174 | — | ~3.5k | Automated safety check: Pass | No licence | today |
| 4829 | 4829.Mindspeed Mm Vlm Universal VLM (vision-language understanding model) training guide for Huawei Ascend NPU using MindSpeed-MM. | ascend-ai-coding/ | 174 | — | ~5.2k | Automated safety check: Pass | No licence | today |
| 4830 | MindSpeed-MM weight conversion guide using mm-convert CLI tool. | ascend-ai-coding/ | 174 | — | ~2.1k | Automated safety check: Pass | No licence | today |
| 4831 | 4831.Verl Quickstart Generates an executable, end-to-end VERL reinforcement learning quickstart runbook for Ascend/NPU (docker image, dataset preprocessing, model setup, mainppo training, and examples/run.sh flow). | ascend-ai-coding/ | 174 | — | ~592 | Automated safety check: Pass | No licence | today |
| 4832 | 4832.Vllm Ascend Server Deploy vLLM inference services on Ascend NPU servers with automatic model detection and optimized configuration. | ascend-ai-coding/ | 174 | — | ~2.7k | Automated safety check: Pass | No licence | today |
| 4833 | A skill your agent uses for DSPy signatures, InputField, OutputField, typed inputs and outputs, signature classes, and Pydantic-style structured schemas. | OmidZamani/ | 124 | — | ~1.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 4834 | 4834.Geniml Python library for genomic interval ML. An agent skill from jaechang-hits/SciAgent-Skills. | jaechang-hits/ | 371 | — | ~4.3k | Automated safety check: Pass | BSD-2-Clause | 10 days ago |
| 4835 | 4835.Model Discovery Fetch current model names from AI providers (Anthropic, OpenAI, Gemini, Ollama), classify them into tiers (fast/default/heavy), and detect new models. | aiskillstore/ | 430 | — | ~1.9k | Automated safety check: Pass | No licence | today |
| 4836 | Research GitHub, GitLab, and Bitbucket repositories using DeepWiki MCP server. | aiskillstore/ | 430 | — | ~1.2k | Automated safety check: Pass | No licence | today |
| 4837 | 4837.Chatkit Widget A skill your agent uses when integrating OpenAI/ChatKit chat widgets into Next.js/React applications. | aiskillstore/ | 430 | — | ~4.6k | Automated safety check: Pass | No licence | today |
| 4838 | Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. | aiskillstore/ | 430 | — | ~3.3k | Automated safety check: Pass | No licence | today |
| 4839 | Standardize and validate SKILL.md files against the Agent Skills specification (agentskills.io). | aiskillstore/ | 430 | — | ~2.1k | Automated safety check: Notes | No licence | today |
| 4840 | 4840.Vision See and understand images when you (the current model) have no native vision. | aiskillstore/ | 430 | — | ~1.1k | Automated safety check: Pass | No licence | today |
| 4841 | Fetch trending programming models from OpenRouter rankings. An agent skill from MadAppGang/claude-code. | MadAppGang/ | 285 | — | ~3.6k | Automated safety check: Pass | MIT | 6 mo ago |
| 4842 | 4842.Proxy Mode Reference Reference guide for using external AI models via claudish CLI. | MadAppGang/ | 285 | — | ~1.3k | Automated safety check: Pass | MIT | 6 mo ago |
| 4843 | Framework for demonstrating AI capabilities in legal contexts. | lawve-ai/ | 842 | — | ~5.6k | Automated safety check: Pass | AGPL-3.0 | 6 days ago |
| 4844 | Draft matter status reports from emails, call notes, and updates. | lawve-ai/ | 842 | — | ~7.6k | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 4845 | 4845.Forest Plot Styler Analyze data with forest-plot-styler using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation. | aipoch/ | 2k | — | ~3k | Automated safety check: Pass | MIT | 22 days ago |
| 4846 | Select appropriate Ollama models for processing sensitive but legal content. | divinevideo/ | 266 | — | ~1.3k | Automated safety check: Pass | MPL-2.0 | today |
| 4847 | 4847.Comfy CLI Install, manage, and run ComfyUI instances. An agent skill from sundial-org/awesome-openclaw-skills. | sundial-org/ | 663 | — | ~1.5k | Automated safety check: Pass | No licence | 7 mo ago |
| 4848 | 4848.Multi LLM Multi-LLM intelligent switching. An agent skill from sundial-org/awesome-openclaw-skills. | sundial-org/ | 663 | — | ~1.4k | Automated safety check: Notes | No licence | 7 mo ago |
Explore related skills
Topics in AI & LLM Engineering
- Building AI agents546
- Deep learning408
- Embeddings373
- LLM inference and serving372
- Prompt engineering348
- Retrieval-augmented generation348
- LLM evaluation308
- Fine-tuning308
- Speech recognition and synthesis305
- Structured output and tool calling268
- Model routing and gateways257
- LLM cost and token optimization254
- LLM API integration250
- LLM observability242
- LLM guardrails217
- Computer vision195
- Model hubs and datasets179
- GPU and accelerator computing172
- Diffusion and image models165
- Natural language processing134
- Reinforcement learning66
- AI interpretability23
Products these skills work with
Roles that use these skills
Other categories
- Development15,199
- Frontend & Design5,829
- Backend & APIs7,083
- Testing & QA5,062
- DevOps & Cloud5,955
- Databases2,353
- Data & Analytics3,632
- Agent Workflows8,296
- Documents & Office4,290
- Writing & Content3,764
- Marketing & SEO3,901
- Sales & Support1,837
- Research & Science6,076
- Security3,087
- Productivity & Automation4,035
- Business, Finance & HR3,880
- Legal & Compliance1,634
- Education1,086
- Media & Creative4,311
- Mobile2,737
- Product & Project Management2,339
- Knowledge Management1,438
- Game Development1,678