Agent skills for Machine Learning Engineers

104 agent skills are labelled for Machine Learning Engineers work. They are listed by code score, out of 100.

All 104

pathways-workload google/skills
Debugs failed, crashing or hung Pathways on Cloud workloads (JAX training or inference on Cloud TPU in GKE, run as a JobSet, PathwaysJob or LeaderWorkerSet). Reads Cloud Logging f…

Verified93A
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring google/skills
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating…

Verified86A
gke-ai-troubleshooting-tpu-vbar-oom google/skills
Diagnoses and prevents vbar_control_agent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TP…

Verified86A
google-cloud-solution-hybrid-search-alloydb google/skills
Discovers requirements and generates architectural, design, and deployment guidance for dynamic hybrid search systems by combining semantic search and keyword search. Optimized fo…

Verified86A
litert-google-tensor google/skills
Compiles LiteRT (.tflite) models ahead-of-time for Google Tensor TPUs (Tensor G5 on Pixel 10, Tensor G6 on Pixel 11) locally on Linux x86_64 or on Google Colab (--colab on macOS,…

Verified84B
agent-platform-deploy google/skills
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying m…

Verified83B
google-cloud-solution-guided-gke-ai-migration google/skills
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user ha…

Verified83B
retail-product-search google/adk-recipes
Creates product search agents with semantic search and RAG on Google Cloud (Vector Search on Gemini Enterprise Agent Platform, BigQuery, embeddings). Use when the user wants to "b…

Verified83B
arize-dataset github/awesome-copilot
Creates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI. Use when the…

Verified82B
rag-architect alirezarezvani/claude-skills
Design a RAG pipeline: chunk size, embedding model, vector database and retrieval quality metrics. Use whenever the user builds search over their docs, picks a vector store or fin…

Verified82B
gke-ai-troubleshooting-jobset-interruption google/skills
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node r…

Verified82B
pytorch-fsdp2 Orchestra-Research/AI-Research-SKILLs
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU…

Verified82B
litert-lm android/skills
Builds an Android app that runs an open text LLM on the device, on the CPU or the GPU, with the LiteRT-LM Kotlin API (com.google.ai.edge.litertlm:litertlm-android). Use this skill…

Verified82B
assessing-vector-and-embedding-weaknesses mukul975/Anthropic-Cybersecurity-Skills
Test RAG vector stores (Pinecone, Qdrant, Weaviate, Chroma, pgvector, FAISS) for embedding inversion, cross-tenant data leakage, and data poisoning per OWASP LLM08:2025. Use when…

Verified81B
detecting-ai-model-prompt-injection-attacks mukul975/Anthropic-Cybersecurity-Skills
Detects prompt injection using regex signature matching, heuristic scoring for structural anomalies, and DeBERTa-based transformer classification, flagging direct injections (syst…

Verified81B
gke-ai-troubleshooting-node-unresponsive-timeout google/skills
Diagnose and mitigate GKE TPU or GPU nodes stuck in NotReady / NodeStatusUnknown ("Kubelet stopped posting node status") due to host kernel panics, hardware lockups, or disabled n…

Verified81B
arize-instrumentation github/awesome-copilot
Adds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then implement instrumentation after user confirmat…

Verified80B
timesfm-forecasting google-research/timesfm
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy…

80B
hf-cloud-sagemaker-production-defaults huggingface/skills
Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to cr…

Verified80B
hf-cloud-serving-image-selection huggingface/skills
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an im…

Verified80B
litert-runtime android/skills
Configures and implements LiteRT (.tflite) on-device inference on Android in Kotlin using the CompiledModel API on CPU and GPU. Use this skill for any Android LiteRT or .tflite ta…

Verified80B
orchestrating-llm-attacks-with-pyrit mukul975/Anthropic-Cybersecurity-Skills
Build automated multi-turn adversarial attacks against conversational LLM targets using Microsoft PyRIT's RedTeamingOrchestrator, CrescendoOrchestrator (gradual escalation), and T…

79B
red-teaming-llms-with-garak mukul975/Anthropic-Cybersecurity-Skills
Runs NVIDIA garak probe suites (jailbreak, prompt injection, data leakage, toxicity, and more) against an LLM endpoint - Hugging Face models, OpenAI-compatible APIs, or Bedrock -…

79B
agent-platform-endpoint-management google/skills
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when tr…

79B
huggingface-vision-trainer huggingface/skills
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 a…

79B
aks-gpu-inference microsoft/skills
Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence. WHEN: 'Insufficient nvidia.com/gpu', GPU pod Pending, model-load OOM, DCGM/VRAM, KAITO Workspac…

79B
capacity microsoft/skills
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on cap…

79B
eval-driven-dev github/awesome-copilot
Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze…

78B
agent-platform-tuning google/skills
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform,…

78B
huggingface-llm-trainer huggingface/skills
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 mod…

78B
foundry-agent-sync github/awesome-copilot
Create and synchronize prompt-based AI agents directly within Azure AI Foundry via REST API, from a local JSON manifest. Unlike scaffolding skills that only generate local code, t…

77B
defending-llms-with-guardrails mukul975/Anthropic-Cybersecurity-Skills
Deploys Llama Guard 3 safety classification, NeMo Guardrails programmable dialogue rails, and LLM Guard input/output scanner pipelines as complementary runtime defenses that inspe…

77B
post-training-miles davila7/claude-code-templates
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 alignme…

77B
developing-genkit-js google/skills
Provides guidance on developing AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScrip…

77B
google-cloud-solution-rag-enterprise-search-gke-sqldb google/skills
Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable enterprise search system in Google Cloud. U…

77B
experiment-queue wanshuiyin/Auto-claude-code-research-in-sleep
SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when user says "batch experiments", "…

77B
evolving-ai-agents Orchestra-Research/AI-Research-SKILLs
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing…

77B
agents-cli-aqua google/adk-recipes
Work with the Ambient Quality Agent (AQuA) added to this agents-cli project: augment the agents-cli agent with AQuA or attach the agent to an AQuA deployed elsewhere, read the qua…

77B
learn rohitg00/ai-engineering-from-scratch
Interactive lesson tutor for the AI Engineering from Scratch curriculum. Reads LEARNING.md, fetches the next lesson, teaches it section by section in the terminal, quizzes at the…

76B
foundry-agentic-loop github/awesome-copilot
Build agentic solutions on Microsoft Foundry, GitHub and Azure: hosted agents, toolbox tools and skills, Foundry IQ grounding and a React/FastAPI app. Three modes: rapid prototypi…

76B
pinecone-rag github/awesome-copilot
Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend. ALWAYS USE THIS SKILL when the user mentions Pinecone, wants to index doc…

76B
evaluation-lm-evaluation-harness davila7/claude-code-templates
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, o…

76B
mechanistic-interpretability-nnsight davila7/claude-code-templates
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiment…

76B
agent-platform-inference google/skills
Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.)…

76B
gke-ai-troubleshooting-handle-disruption-gpu-tpu google/skills
Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when d…

76B
microsoft-foundry microsoft/skills
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted a…

76B
developing-genkit-python google/skills
Provides guidance on developing AI-powered applications using Genkit Python (0.13) and migrating Genkit Python 0.12 projects to 0.13. Use when building AI agents, flows, tools, st…

75B
gke-ai-troubleshooting-tpu-mxla-hang google/skills
Diagnose GKE Cloud TPU multi-slice training hangs (Megascale `HANG_DETECTED` logs and hang monitored events) using the ML Diagnostics `Megascale XLA (MXLA) Hang Analyzer` (`gcloud…

75B
gke-ai-troubleshooting-tpu-partition-overlap google/skills
Diagnose and resolve GKE TPU slice creation failures (SliceCreationFailed) caused by partition overlap conflicts where requested TPU partitions or their nodes are already used by…

75B
gke-ai-troubleshooting-tpu-performance-degradation google/skills
Diagnose GKE Cloud TPU training throughput drops and step-time regressions (15%+ TPU duty-cycle drop) using ML Diagnostics Workload Monitoring (`gcloud alpha mldiagnostics monitor…

75B
document-workflows andrewyng/context-hub
Use this skill for building end-to-end document processing workflows and pipelines using LandingAI ADE. Trigger when users need to: (1) Process batches of documents in parallel or…

75B
hf-cloud-python-env-setup huggingface/skills
Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMak…

75B
hf-cloud-sagemaker-iam-preflight huggingface/skills
Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource th…

75B
huggingface-community-evals huggingface/skills
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…

75B
huggingface-spaces huggingface/skills
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference provi…

75B
caveman-setup JuliusBrussee/caveman
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.

74B
dataset-curation wshobson/agents
Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training format, applying chat templates, configuring…

74B
arize-experiment github/awesome-copilot
Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows u…

74B
arize-prompt-optimization github/awesome-copilot
Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-dri…

74B
optimization-flash-attention davila7/claude-code-templates
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encoun…

74B
senior-prompt-engineer alirezarezvani/claude-skills
Improve prompts and measure LLM quality: fix inconsistent prompts, build eval sets, score RAG retrieval, check agent tool configs. Use whenever the user's prompt, chatbot or RAG a…

74B
agent-platform-model-registry google/skills
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model R…

74B
agent-platform-tuning-management google/skills
Manages GenAI tuning jobs in Agent Platform. Use this to list, get, or cancel ongoing model tuning jobs. Don't use for fine-tuning models (use `agent-platform-tuning`), deploying…

74B
gke-ai-troubleshooting-tpu-vm-repair-stuck google/skills
Diagnose GKE TPU VM instances stuck in Compute Engine repair (REPAIRING state) after host errors, maintenance events, or faulty host reports in single-host, multi-host, dynamic sl…

74B
ai-sdk midudev/autoskills
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or t…

74B
azure-ai-voicelive-dotnet microsoft/skills
Azure AI Voice Live SDK for .NET. Build real-time voice AI applications with bidirectional WebSocket communication. Use for voice assistants, conversational AI, real-time speech-t…

74B
mastra mastra-ai/skills
Comprehensive Mastra framework guide for building agents, workflows, tools, memory, workspaces, and storage with current APIs. Use for native capability discovery, logging, tracin…

74B
eval-harness-first wshobson/agents
Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning…

73B
arize-link github/awesome-copilot
Generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs. Produces clickable URLs for sharing Arize resource…

73B
implementing-llm-guardrails-for-security mukul975/Anthropic-Cybersecurity-Skills
Implements input/output validation guardrails for LLM applications using NVIDIA NeMo Guardrails (Colang), custom Python validators for PII detection, and the Guardrails AI framewo…

73B
evaluation-nemo-evaluator davila7/claude-code-templates
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker,…

73B
openai-docs openai/skills
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help…

73B
miles-rl-training Orchestra-Research/AI-Research-SKILLs
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 alignme…

73B
hf-cloud-sagemaker-deployment-planner huggingface/skills
Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — includ…

73B
huggingface-lora-space-builder huggingface/skills
Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playgrou…

73B
train-sentence-transformers huggingface/skills
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, pa…

73B
writing-evals openclaw/clawhub
Scaffolds evaluation suites for the Axiom AI SDK. Generates eval files, scorers, flag schemas, and config from natural-language descriptions. Use when creating evals, writing scor…

73B
deploy-model microsoft/skills
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy)…

73B
llm-generation lobehub/lobehub
Use for application prompts, generateObject/generateText, model selection and generation tracing. Excludes provider adapters and agent snapshots.

72B
post-training-torchforge davila7/claude-code-templates
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experime…

72B
gke-ai-troubleshooting-tpu-reservation-stockout google/skills
Diagnose and resolve cluster-wide GKE TPU node pool creation or scale-up failures caused by Compute Engine reservation stockouts (GCE_STOCKOUT, ZONE_RESOURCE_POOL_EXHAUSTED) when…

72B
monitor-experiment wanshuiyin/Auto-claude-code-research-in-sleep
Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

72B
evaluating-llms-harness Orchestra-Research/AI-Research-SKILLs
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, o…

72B
nnsight-remote-interpretability Orchestra-Research/AI-Research-SKILLs
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiment…

72B
gepa-optimize-anything gepa-ai/gepa
Automatically improve any text artifact that can be scored — prompts, programs/code, configs, specs, regex/SQL/schemas, agent scaffolds, or encoded search solutions — with optimiz…

72B
continuous-llm-red-teaming-with-promptfoo mukul975/Anthropic-Cybersecurity-Skills
Wires Promptfoo and DeepTeam into CI/CD for automated, repeatable red-teaming of LLM apps against OWASP LLM Top 10, OWASP Agentic, and MITRE ATLAS presets, failing the build when…

71B
detecting-indirect-prompt-injection mukul975/Anthropic-Cybersecurity-Skills
Detect and defend against indirect prompt injection hidden in web pages, documents, and images consumed by an agent, via content extraction (HTML/PDF/OCR), normalization, and scan…

71B
mechanistic-interpretability-transformer-lens davila7/claude-code-templates
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when r…

71B
chief-ai-officer-advisor alirezarezvani/claude-skills
Use for AI strategy decisions: API vs fine-tune vs build, EU AI Act or US state risk classification, when self-hosting pays off, or AI hiring order. Runs model_buildvsbuy_calculat…

71B
agent-platform-architecture google/skills
Designs, engineers, and validates enterprise Gemini platform architectures. Use when designing multi-project hierarchies (Host, Central Governance Hub, Runtime Spoke, Tool/MCP Spo…

71B
agent-platform-eval-flywheel google/skills
Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when generating synthetic user scenarios, evaluating an…

71B
gke-ai-troubleshooting-tpu-slice-mig-stuck-updating google/skills
Diagnose and resolve GKE TPU Dynamic Slice creation and JobSet scheduling failures blocked by underlying Compute Engine managed instance groups (MIGs) stuck in an updating or unst…

71B
experiment-bridge wanshuiyin/Auto-claude-code-research-in-sleep
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现…

71B
project-development muratcankoylan/Agent-Skills-for-Context-Engineering
This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or ag…

71B
custom-investigation google/adk-recipes
Run a custom investigation: review a chosen slice of conversations instead of a random sample, by writing a SQL selector over the observed agent's telemetry, and optionally narrow…

71B
firebase-ai-logic-basics firebase/agent-skills
Integrates Firebase AI Logic (formerly Vertex AI for Firebase) into mobile and web apps (Android, iOS, Web, and Flutter) to call Gemini models from client code. Use when provision…

71B
caveman-manage JuliusBrussee/caveman
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.

70B
detecting-model-extraction-attacks mukul975/Anthropic-Cybersecurity-Skills
Detect MITRE ATLAS AML.T0024 attacks (model stealing, inversion, membership inference) performed via inference-API abuse, by monitoring per-principal query volume/distribution, ra…

70B
mechanistic-interpretability-saelens davila7/claude-code-templates
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering int…

70B
post-training-slime davila7/claude-code-templates
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing t…

70B
compute-future-reservations google/skills
Evaluates future GPU and TPU reservation feasibility and calendar-mode booking options in Google Compute Engine (GCE). Use when planning future AI/ML training runs, checking reser…

70B
gke-ai-troubleshooting-tpu-metrics-monitoring google/skills
Monitors and troubleshoots GKE TPU workloads, nodes, and node pools using GKE system metrics and PromQL. Use when monitoring TensorCore duty cycle, TPU memory, node readiness, mul…

70B
optimizing-attention-flash Orchestra-Research/AI-Research-SKILLs
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encoun…

70B
finetuning microsoft/skills
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deploymen…

70B

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.