Best Claude skills for AI engineering
AI engineering skills help you build with models: prompt design, evals, fine-tuning, RAG, agent architecture and skill authoring itself. Hugging Face, Google and Orchestra Research publish large packs, and meta-skills help you write better skills.
606 ai engineering skills · ranked live · November 2026
The top 10. Ranked by the Alyn Score.
- 1#1
Anthropic
Skills
Anthropic
MCP Builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to…
Pack192k3.8MScore 93 - 2#2
Anthropic
Skills
Skill Creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to…
Pack192k3.8MScore 93 - 3#3
Matt Pocock
Domain Modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
Pack321k33MScore 92 - 4#4
Jesse Vincent
Superpowers
Jesse Vincent
Subagent Driven Development
Use when executing implementation plans with independent tasks in the current session
Pack316k3.9MScore 92 - 5#5
Anthropic
Skills
Claude API
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the…
Pack192k3.8MScore 91 - 6#6
affaan-m
Agent Architecture Audit
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering…
Pack301k1.7MScore 89 - 7#7
Agentic Os
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management…
Pack301k1.7MScore 89 - 8#8
AI Regression Testing
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where…
Pack301k1.7MScore 89 - 9#9
JuliusBrussee
Caveman Setup
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.
Pack119k4.8MScore 88 - 10#10
Corey Haines
Marketingskills
Corey Haines
Marketing Psychology
When the user wants to apply psychology to marketing, or asks why buyers behave or value things as they do, or whether a persuasion tactic is honest: biases, mental models, anchoring…
Pack60k6.3MScore 86
What makes a great ai engineering skill.
Eval steps so changes are measured, not vibed.
Current library versions and APIs.
Cost and context awareness for long-running agents.
All 606 ai engineering skills.
OpenAI
Skills
OpenAIsecurity-threat-model
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only…
Anthropic
Claude Plugins Official
Anthropicsession-report
Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.
thedotmackclaude-mem-install
Use this when setting up claude-mem on Grok Bot: local worker plus CMEM Pro observer (default), optional host-login observer, or remote cmem.ai. No Cursor required.
thedotmackhow-it-works
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".
Microsoftairunway-aks-setup
Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway"…
Microsoftazure-aigateway
Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate…
thedotmackbuild-and-release
Fully automate building and releasing a coding task.
thedotmackdo
thedotmackhost-observer
Use this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation XML, never prose.
NVIDIA
Skills
NVIDIAkermt-finetune
Finetune a pretrained KERMT encoder on a labeled CSV. Validate the checkpoint and data, prepare features, and run containerized training. Use a local checkpoint or optionally download a…
thedotmacklearn-codebase
Prime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project, or when the user asks to "learn the codebase", "read the codebase", "prime", or…
thedotmackmake-plan
../../../plugin/skills/make-plan/SKILL.md
thedotmackmem-search
Use this when the user asks to search memory, "did we already solve this?", "how did we do X last time?", or wants work from previous sessions.
Hugging Face
Skills
Hugging Facehuggingface-community-evals
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers /…
Hugging Face
Skills
Hugging Facehuggingface-llm-trainer
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling…
Hugging Face
Skills
Hugging Facehuggingface-paper-publisher
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based…
Hugging Face
Skills
Hugging Facehuggingface-vision-trainer
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any…
Hugging Face
Skills
Hugging Facetrain-sentence-transformers
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase…
NVIDIA
Skills
NVIDIAcodonfm-finetune
Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning. Use when a user explicitly asks to fine-tune…
davila7context-window-management
Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context…
Orchestra Research
AI Research SKILLs
Orchestra Researchhuggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision…
Orchestra Research
AI Research SKILLs
Orchestra Researchhuggingface-tokenizers
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies…
Hugging Face
Skills
Hugging Facehuggingface-tool-builder
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API…
Orchestra Research
AI Research SKILLs
Orchestra Researchimplementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational…
NVIDIA
Skills
NVIDIAkermt-infer
Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts with a redirect to…
NVIDIA
Skills
NVIDIAkermt-pretrain-scratch
Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrain_ddp.py…
Orchestra Research
AI Research SKILLs
Orchestra Researchmamba-architecture
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and…
Orchestra Research
AI Research SKILLs
Orchestra Researchmiles-rl-training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or…
Orchestra Research
AI Research SKILLs
Orchestra Researchnanogpt
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT…
Orchestra Research
AI Research SKILLs
Orchestra Researchnemo-curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII…
Orchestra Research
AI Research SKILLs
Orchestra Researchnnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on…
Orchestra Research
AI Research SKILLs
Orchestra Researchopenrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with…
Orchestra Research
AI Research SKILLs
Orchestra Researchpeft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters…
Orchestra Research
AI Research SKILLs
Orchestra Researchpyvene-interventions
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching…
Orchestra Research
AI Research SKILLs
Orchestra Researchray-data
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine…
Orchestra Research
AI Research SKILLs
Orchestra Researchrwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at…
AI engineering skills, explained.
Also searched as: llm skills, prompt engineering skill, fine-tuning skills, skill creator, hugging face skills.
What are the best Claude skills for AI engineering?
Right now the top-ranked ai engineering skills on Alyn are MCP Builder (Anthropic), Skill Creator (Anthropic), Domain Modeling (Matt Pocock). Rankings combine GitHub stars, installs, freshness and depth, and update live.
How do I create my own skill?
Write a folder with a SKILL.md file: YAML frontmatter with name and description, then instructions. See Alyn's guide on creating skills.
Do self-written skills help?
The SkillsBench study found curated skills raised pass rates by 16.2 points on average, while skills the model wrote for itself gave no benefit on average. Quality matters.
How do I install a ai engineering skill?
Run npx skills add owner/repo in your project, or copy the folder with SKILL.md into ~/.claude/skills. Every skill on this page has a ready-to-copy command.
More in Build
AI engineering skills for your agent