Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Cloud & DevOps
Publish a GrowthBook feature flag draft revision, resolve merge conflicts, revert to a prior revision, or discard a draft. Use when the user says "publish this draft", "push this live", "go live with revision X", "there's a merge conflict on my flag", "rebase my draft", "fix the merge conflict on flag X", "revert flag X to a previous version", "roll back this flag change", "discard this draft", or "abandon these changes". For requesting or submitting an approval review before publish, use flag-review. For listing and inspecting drafts, use flag-revisions.
Create or manage a multi-step ramp schedule for a GrowthBook feature flag rule — progressively increasing traffic exposure over time with defined intervals between steps. Use when the user says "gradually roll this out", "increase traffic from 5% to 100% over a week", "set up a ramp schedule", "advance to the next ramp step", "pause the rollout", "roll back the ramp", or "set a cutoff date on this rollout". For rollouts that also need guardrail metric monitoring and automatic signals, use flag-monitoring — it builds on this skill with monitoring configuration. For simple on/off time windows, use flag-schedule.
Diagnose and fix failing GitHub Checks on PR work by default: fetch evidence, write ephemeral ci-fails report, apply fixes, verify locally. Run automatically — do not wait for user to ask. Never merge without authorize merge. Companion to /heyeddi fails.
Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo container, run it, and verify HSB connectivity by pinging 192.168.0.2. Use for Holoscan Sensor Bridge setup, build, container launch, and first-connectivity bring-up.
Use this skill whenever the user wants to isolate a piece of code, animation, or 3D experiment into a standalone JOYCO Lab experiment and publish it. Triggers include: "isolate this", "publish this to the lab", "create a lab experiment", "extract this animation/effect/scene", "submit to JOYCO lab", "make this an experiment". Also trigger when the user shows you a self-contained visual effect, animation, 3D scene, canvas sketch, or interactive component and wants to share or showcase it. Even if they don't say "lab" explicitly — if there's isolatable creative/technical code and a desire to share it, use this skill.
Diagnose and fix stalled agent loops using the joelclaw CLI. Use when loops appear stuck, stories aren't progressing, or the event chain broke. Triggers on "loop stalled", "why isn't the loop progressing", "diagnose loops", "fix stuck loop", "loop not moving", "what happened to the loop", "stories stuck at pending", or any request to debug loop infrastructure.
Use this skill WHEN monetizing AI agents with autonomous payments, listing agents on decentralized marketplace, or deploying at scale. OUTCOMES: agents earning revenue automatically (50+ USDM/day), trustless escrow protection (95%+ success rate), marketplace discovery (50+ available agents), scalable execution (1000+ concurrent jobs). Triggers on: 'monetize my agent', 'setup agent payments', 'list on marketplace', 'A2A transactions', 'deploy agent at scale', 'MIP-003 implementation'. NOT for: general chatbots, simple REST APIs, centralized payments. Framework-agnostic (CrewAI, AutoGen, PhiData, LangGraph), self-hosted, MiCA compliant.
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive allocation
Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.
Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw. Trigger keywords - nemoclaw local inference, ollama nemoclaw, vllm nemoclaw, local model server, openai compatible endpoint, switch nemoclaw inference model, change inference runtime, nemoclaw additional model, nemoclaw sub-agent model, openclaw sub-agent, agents.list, sessions_spawn, vlm-demo, nemoclaw tool calling, ollama tool calls, vllm tool-call-parser, raw json in tui, nemoclaw inference options, nemoclaw onboarding providers, nemoclaw inference routing.
Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when deploying NemoClaw to a remote VM, onboarding a Brev instance, or migrating away from the legacy `nemoclaw deploy` wrapper. Trigger keywords - deploy nemoclaw remote gpu, nemoclaw brev cloud deployment, nemoclaw plugins, openclaw plugins, install openclaw plugin, nemoclaw onboard from dockerfile, nemoclaw brev web ui, nemoclaw getting started, brev quickstart, nvidia nemotron agent, nemoclaw sandbox hardening, container security, docker capabilities, process limits.
Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.
Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration, nemoclaw integration policy examples, post-install policy setup, openshell approval workflow, policy preset, nemoclaw approve network requests, sandbox egress approval tui.
Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.
Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.
Use this skill when the user asks to create, review, debug, or modernize Azure Pipelines YAML for CI/CD, especially .NET builds, Azure App Service deploys, or IIS/on-premises deploys. Prefer bundled templates and verify task syntax against Microsoft docs when version-specific accuracy matters.
Deploy and manage Netlify projects using Next.js with serverless functions, environment variables, and continuous deployment. Use this skill when working with Netlify deployments, configuring netlify.toml, managing Netlify Functions, debugging webhooks, setting environment variables, or troubleshooting deployment issues for Next.js applications on Netlify. Essential for Twilio-Aldea and similar serverless SMS/telephony projects. v2.0 includes official Netlify documentation, production patterns from Twilio-Aldea (webhook timeout solutions, background functions), and TypeScript code examples.
Install, check on, or upgrade a self-hosted Nowledge Mem server (the headless Docker deployment) using the `nmemctl` lifecycle controller. Use this whenever the user mentions running their own Nowledge Mem instance, self-hosting Mem on a NAS, VPS, homelab, or server, deploying `nowledgelabs/mem` from Docker Hub, troubleshooting their Mem container, or upgrading a Mem server to a newer version. Trigger even when the user says "my Mem server", "self-hosted Mem", "the docker version of Mem", "memory server on my Synology / Proxmox / Raspberry Pi", or just describes a container that's at `docker.io/nowledgelabs/mem` without naming the product. Do NOT trigger for the Mem desktop app, Mem Cloud, or anything that doesn't touch the operator's own server.
Use the Observe CLI (`observe`) to investigate production systems and pull telemetry. Reach for this skill whenever the user wants to: search or tail logs; query metrics (CPU, memory, latency, error rate, request volume, custom app metrics); explore traces and spans; correlate events across services, hosts, containers, or Kubernetes resources; investigate or triage alerts (what fired, why, what's still active, related signals); debug an incident or production issue; check service or system health; figure out what's happening with a customer, deployment, or user; find which services emit a given tag or label; slice production data by service, environment, region, host, pod, status code, etc.; or pull any observability data out of the platform for analysis, dashboards, or scripting. Also covers the underlying primitives the CLI exposes (datasets, OPAL queries, knowledge-graph tag search, alerts, monitors, AI agent skills, auth) when the user asks about them directly.
Instruments Java, Python, Node.js, .NET, and Go applications with OpenTelemetry SDKs to send traces, metrics, and logs to Coralogix. Use for SDK-side OTel setup, OTLP exporter env vars, Coralogix resource attributes, APM transaction samplers, Kubernetes Operator injection, or debugging missing traces, metrics, logs, or no telemetry from an application. Not for OTel Collector config (use opentelemetry-collector), OTTL authoring (use opentelemetry-ottl), eBPF instrumentation, or Lambda layers.
Use when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS, including Kubernetes clusters, inference endpoint deployment, OSMO deployment, workload submission readiness, and infrastructure failure recovery. Trigger keywords: physical ai infrastructure, resilient scaling, SDG infrastructure, microk8s, azure aks, NVCF deployment, NIM Operator, OSMO deploy, workflow scaling. Don't trigger for: OSMO log summarization or workload-only operations unless infrastructure setup, scaling, validation, or recovery is requested.
Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. Trigger keywords: video data augmentation, data enrichment, auto labeling, VDA demo, OSMO workflow, pseudo labeling.
Govern Power Automate flows and Power Apps at scale using the FlowStudio MCP cached store. Classify flows by business impact, detect orphaned resources, audit connector usage, enforce compliance standards, manage notification rules, and compute governance scores — all without Dataverse or the CoE Starter Kit. Load this skill when asked to: tag or classify flows, set business impact, assign ownership, detect orphans, audit connectors, check compliance, compute archive scores, manage notification rules, run a governance review, generate a compliance report, offboard a maker, or any task that involves writing governance metadata to flows. Requires a FlowStudio for Teams or MCP Pro+ subscription — see https://mcp.flowstudio.app
Pro+ subscription required. Tenant-wide Power Automate monitoring using the FlowStudio MCP cached store: failure rates, run-health trends, maker/app inventory, inactive owners, and compliance/health reports. Use only for aggregated tenant views. For one environment, one flow, run control, or root-cause debugging, use power-automate-mcp, power-automate-debug, or the server monitor-flow bundle. Requires FlowStudio for Teams or MCP Pro+.
Guidance for starting and configuring QEMU virtual machines with proper serial console access. This skill should be used when tasks involve starting QEMU VMs, configuring serial console or telnet access, booting ISO images, or troubleshooting VM startup issues. Covers pre-flight checks, idempotent startup procedures, and intelligent readiness verification.
Upload files to Cloudflare R2, AWS S3, or any S3-compatible storage (like MinIO) and generate secure, time-limited presigned download links with configurable expiration, typically set to 5 minutes. Use when the user needs to upload a file to cloud storage and get a shareable link, or mentions R2, S3, presigned URLs, temporary links, or file uploads with expiration.
NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).
Upload, sync, and manage files across cloud storage providers using rclone. Use when uploading files (images, videos, documents) to S3, Cloudflare R2, Backblaze B2, Google Drive, Dropbox, or any S3-compatible storage. Triggers on "upload to S3", "sync to cloud", "rclone", "backup files", "upload video/image to bucket", or requests to transfer files to remote storage
Query and manage Sentry error-tracking data — list and search issues, drill into events and stack traces, inspect projects and releases, resolve/ignore issues, and pull stats. Use this whenever the user mentions a Sentry issue, crash, error group, or exception; pastes a sentry.io or self-hosted Sentry URL; asks "why is this erroring", "how many times has this happened", "what's the top error in {project}", "resolve this issue", or wants a Sentry-based digest — even if they don't say "API". Always start from this skill when interacting with this service — its bundled scripts and recipes are the fastest path.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.