Drive Lightning AI from your agent: cloud GPU Studios, batch and multi-machine jobs, autoscaled deployments, ephemeral sandboxes, the LLM gateway, durable artifact links, live cost estimates, and billing and spend reports. Includes pipelines and LitData dataset workflows.
Plugin lightning from marketplace lightning-ai in Lightning-AI/skills. Commands read from the repo's manifest — 30 days ago.
lightning-artifactsPublish a local file (HTML report, PDF, image, dataset sample, build output) to Lightning AI and get a durable, public lightning.ai/artifacts/ link that never expires and renders inline in the browser. Also lists the artifacts drive, unpublishes (revokes) links and deletes the files behind them, all
lightning-billingRead and manage Lightning AI billing - credit balances for a user, org or teamspace (with transaction history), spend reports broken down by resource type, user, teamspace, day or single resource (jobs, Studios, deployments, sandboxes, storage, LLM/assistant tokens), monthly credits purchased vs rem
lightning-cost-estimationEstimate and compare what a workload costs on Lightning AI - fetch live per-hour GPU/CPU machine prices from the accelerator catalog for every cloud (Lightning Cloud, AWS, GCP, Lambda Labs, Nebius, Voltage Park), size hardware for a model, then quote a training run, fine-tune, serving deployment or
lightning-deploymentsDeploy and operate services on Lightning AI - run Docker containers or HuggingFace models (vLLM) behind autoscaled HTTPS endpoints, manage replicas, releases, endpoint auth, and logs. Use when the user wants to deploy an API, model server, or container to lightning.ai, or manage an existing deployme
lightning-jobsLaunch and manage batch jobs on Lightning AI - run commands on cloud CPUs/GPUs from a Docker image or a Studio snapshot, monitor status, show live progress with an ETA and setback tracking (status-line bar + Monitor events), fetch logs, SSH into a running job or multi-machine worker, collect artifac
lightning-litdataPreprocess and stream training datasets with LitData, choose raw or optimized storage, configure media serialization, resume data loaders, and diagnose cloud I/O, caching and multi-worker failures. Use when the user works with litdata, StreamingDataset, StreamingRawDataset, StreamingDataLoader, opti
lightning-llm-gatewayCall hosted LLMs (OpenAI GPT, Anthropic Claude, Google Gemini, open-weights models) through the Lightning AI models API / LLM gateway - chat, streaming, multi-turn conversations, images, and model metadata; plus the teamspace model checkpoint registry. Use when the user wants to run inference throug
lightning-pipelinesBuild, update, schedule, inspect and troubleshoot Lightning AI pipelines with dependent CPU/GPU jobs, Studio snapshots and shared data. Use when the user wants a multi-step workflow, recurring training, schedule replacement, or logs from a specific pipeline run.
lightning-sandboxesRun code in Lightning AI Sandboxes - fast, isolated ephemeral VMs with optional persistence, snapshots, custom images, Docker-in-sandbox (docker / docker compose), network egress policies, file I/O, public port URLs, and interactive PTY sessions. Use when the user wants to execute untrusted or exper
lightning-studiosManage Lightning AI Studios (cloud dev machines with CPUs/GPUs) - create, start, stop, delete studios, switch machine types, run commands in them (including long detached runs with live progress tracking), upload/download files, and SSH in. Use when the user wants to work with lightning.ai Studios,
Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.
44 skills · 1 MCP server
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
Build, manage, and deploy Wix sites and apps. Includes CLI development skills and Wix MCP server for site management, eCommerce, CMS, dashboard extensions, and more.
37 skills · 1 MCP server
Build, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs-goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).
6 skills · 8 commands · 4 agents · hooks
DevOps, cloud, and deployment specialists - Kubernetes, Terraform, AWS, Azure, GCP, and SRE
Data curation and processing at scale including NeMo Curator and Ray Data. Use when preparing training datasets or processing large-scale data.
98 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.