Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
7,508 skills from 198 repositories · updated 18 minutes ago
553 skills
- knowledge-distillationOrchestra-Research/AI-Research-SKILLsCompress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.DevOpsNo warnings★ 13.8K↓ —
- run-experimentwanshuiyin/Auto-claude-code-research-in-sleepDeploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.DevOpsNo warnings★ 17.8K↓ —
- tensorrt-llmOrchestra-Research/AI-Research-SKILLsOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.DevOpsNo warnings★ 13.8K↓ —
- experiment-bridgewanshuiyin/Auto-claude-code-research-in-sleepWorkflow 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 "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.DevOpsNo warnings★ 17.8K↓ —
- model-mergingOrchestra-Research/AI-Research-SKILLsMerge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.DevOpsNo warnings★ 13.8K↓ —
- kqlmicrosoft/skillsKQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.OfficialDevOpsNo warnings★ 3.1K↓ —
- entra-agent-idmicrosoft/skillsMicrosoft Entra Agent ID (preview) for creating OAuth2-capable AI agent identities via Microsoft Graph beta API. Covers Agent Identity Blueprints, BlueprintPrincipals, Agent Identities, required permissions, sponsors, and Workload Identity Federation. Includes Microsoft Entra SDK for AgentID (containerized sidecar) for polyglot agent authentication (Docker/Kubernetes), 3P agent integration, autonomous and interactive agent patterns. Triggers: "agent identity", "agent id", "Agent Identity Blueprint", "BlueprintPrincipal", "entra agent", "agent identity provisioning", "Graph agent identity", "entra sidecar", "agent id sidecar", "auth sidecar", "3P agent", "third-party agent identity", "polyglot agent auth".OfficialDevOpsNo warnings★ 3.1K↓ —
- langsmith-observabilityOrchestra-Research/AI-Research-SKILLsLLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.DevOpsNo warnings★ 13.8K↓ —
- fine-tuning-openvla-oftOrchestra-Research/AI-Research-SKILLsFine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.DevOpsNo warnings★ 13.8K↓ —
- nemo-evaluator-sdkOrchestra-Research/AI-Research-SKILLsEvaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.DevOpsNo warnings★ 13.8K↓ —
- llamaguardOrchestra-Research/AI-Research-SKILLsMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.DevOpsNo warnings★ 13.8K↓ —
- agent-platform-migrate-from-ai-studiogoogle/skillsGuides agents and users through migrating from Gemini API in Google AI Studio to Gemini Enterprise Agent Platform (formerly Vertex AI). Use this skill when moving applications to Google Cloud, to leverage Cloud credits, or to unify inferencing with other Cloud infrastructure (IAM, billing, telemetry).OfficialDevOpsNo warnings★ 21.5K↓ —
- phoenix-observabilityOrchestra-Research/AI-Research-SKILLsOpen-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.DevOpsNo warnings★ 13.8K↓ —
- azure-vmssickn33/agentic-awesome-skillsManage Azure Virtual Machines and scale sets. Configure availability sets and managed disks. Use when deploying compute resources on Azure.DevOpsNo warnings★ 48.2K↓ —
- serving-llms-vllmOrchestra-Research/AI-Research-SKILLsServes LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.DevOpsNo warnings★ 13.8K↓ —
- llama-cppOrchestra-Research/AI-Research-SKILLsRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.DevOpsNo warnings★ 13.8K↓ —
- gptqOrchestra-Research/AI-Research-SKILLsPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.DevOpsNo warnings★ 13.8K↓ —
- verl-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.DevOpsNo warnings★ 13.8K↓ —
- serverless-modalwanshuiyin/Auto-claude-code-research-in-sleepRun GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.DevOpsNo warnings★ 17.8K↓ —
- run-experimentwanshuiyin/Auto-claude-code-research-in-sleepDeploy and run ML experiments on local or remote GPU servers. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.DevOpsNo warnings★ 17.8K↓ —
- gguf-quantizationOrchestra-Research/AI-Research-SKILLsGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.DevOpsNo warnings★ 13.8K↓ —
- modal-serverless-gpuOrchestra-Research/AI-Research-SKILLsServerless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.DevOpsNo warnings★ 13.8K↓ —
- microsoft-docsmicrosoft/skillsUnderstand Microsoft technologies by querying official documentation. Use whenever the user asks how something works, wants tutorials, needs configuration options, limits, quotas, or best practices for any Microsoft technology (Azure, .NET, M365, Windows, Power Platform, etc.)—even if they don't mention "docs." If the question is about understanding a concept rather than writing code, this is the right skill.OfficialDevOpsNo warnings★ 3.1K↓ —
- cost-analysismicrosoft/skillsAnalyze actual Azure spend, bill changes, and AKS or AI costs. WHEN: "Azure cost breakdown", "most expensive resources", "why did my bill increase", "cost spike", "unexpected charge", "Cosmos DB charges", "Foundry model costs", "AKS cluster cost", "namespace cost", "enable AKS cost analysis", "idle AKS capacity". DO NOT USE FOR: forecasts, pricing estimates, rightsizing, commitments, or budgets.OfficialDevOpsNo warnings★ 3.1K↓ —
serving-llms-vllm
Orchestra-Research/AI-Research-SKILLs
DevOpsUpdated Oct 11, 2026
From the author
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill serving-llms-vllm -a claude-code
Installs to .claude/skills/serving-llms-vllm/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 93
Security100
Provenance90
Maintenance100
Licence100
Adoption65
Files (5)
- SKILL.md
- references/optimization.md
- references/quantization.md
- references/server-deployment.md
- references/troubleshooting.md