DevOps & Cloud Skills

Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.

Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or updating documentation.

Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.

Coordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging that require conversion, material/physics assignment, SimReady conformance, validation, and optional package creation; deploy or verify Content Agents services first when property assignment is enabled; route single-stage work through nested references.

>- 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 scaling, SDG infrastructure, microk8s, azure aks, NVCF deployment, summarization or workload-only operations unless infrastructure setup, scaling, validation, or recovery is requested.

>- flow selection, preflight, submit-time interpolation, monitoring, and output labeling, VDA demo, OSMO workflow, pseudo labeling.

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).

Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the data-services container (`tao_toolkit.data_services` from `versions.yaml`) directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, or auditing PASS/NO_PASS boundary cases.

Track finance investment signal evolution and update logic based on new finance market information. Use when monitoring finance signals and determining if they are strengthened, weakened, or falsified.

Full-stack software development agent for design, implementation, testing, and deployment. Use when the user explicitly asks for end-to-end project creation, feature development, bug fixing, or code refactoring.

Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools.

Provides context about the Roo Code evals system structure in this monorepo. Use when tasks mention "evals", "evaluation", "eval runs", "eval exercises", or working with the evals infrastructure. Helps distinguish between the evals execution system (packages/evals, apps/web-evals) and the public website evals display page (apps/web-roo-code/src/app/evals).

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

Use when building a LaTeX manuscript submission pipeline with templates, latexmk, BibTeX/Biber, chktex, latexindent, CI PDF builds, compile debugging, and submission zip packaging.

| Design and implement repeatable preprocessing pipelines for cleaning, encoding, transforming, and validating ML input data.

Use when working with PTVS Glass tests: setup_glass.py, run_glass.py, Glass.TestAdapter, Newtonsoft.Json assembly mismatches, Azure Pipelines Glass cache, TestScript.xml, glass2.exe, and mixed-mode Python debugger tests.

Guide SDK users through setting up their Java environment for Azure AI Content Understanding. Use this skill when users need help installing the SDK, configuring Azure resources, deploying required models, setting environment variables, or running samples.

Run a specific sample for the Azure AI Content Understanding Java SDK. Use when users want to run a particular sample like Sample02_AnalyzeUrl or Sample03_AnalyzeInvoice.

> Run azure-cosmos integration/customer-workflow tests locally, closely following the CI pipeline (build+install, then failsafe `verify` with a test profile) using one consistent JDK for both steps. (fi-customer-workflows / fi-sm-customer-workflows), reproduce a CI test failure locally, or run a specific cosmos test profile via Maven. Covers the same-JDK build/test requirement, the two-step build/test split, profile→group→file mapping, and the required account env vars.

Convert Kanchi-style dividend investing into a repeatable US-stock operating procedure. Use when users ask for かんち式配当投資, dividend screening, dividend growth quality checks, PERxPBR adaptation for US sectors, pullback limit-order planning, or one-page stock memo creation. Covers screening, deep dive, entry planning, and post-purchase monitoring cadence.

Use when adding, configuring, or troubleshooting NeMo Agent Toolkit logging, tracing, telemetry exporters, OpenTelemetry, Langfuse, LangSmith, Weave, Phoenix, profiling, or observability provider integrations.

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Send and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing). Use when building email sending (Workers binding or REST API), email routing, Agents SDK email handling, or integrating email into any app — Workers, Node.js, Python, Go, etc. Also use for email deliverability, SPF/DKIM/DMARC, wrangler email setup, MCP email tools, or when a coding agent needs to send emails. Even for simple requests like "add email to my Worker" — this skill has critical config details.

Plans migrations from Zscaler ZIA/ZPA, Palo Alto, legacy VPN, SWG, or SASE stacks to Cloudflare One. Use for migration assessments, policy mapping, rollout plans, and parity/gap analysis.

Guides Cloudflare One Zero Trust and SASE work across Access, Gateway, WARP, Tunnel, Cloudflare WAN, DLP, CASB, device posture, and identity. Use when designing, configuring, troubleshooting, or reviewing Cloudflare One deployments. Retrieval-first: use current Cloudflare docs/API schemas instead of embedded product docs.

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Set up Cloudflare Turnstile end-to-end in a project. Scan the codebase, create the widget via the Cloudflare API, embed it where user requests need bot verification (form submissions, SPA actions, API endpoints, download links, comment or vote submissions, etc.), wire canonical server-side siteverify in the customer's existing backend, validate, and persist the skill. Load this when a user asks to add Turnstile, set up CAPTCHA, protect a form or endpoint from bots, or fix a Turnstile integration. Mirrors developers.cloudflare.com/turnstile/spin.

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Fetch brand SVG logos and cloud architecture icons (AWS, Azure, GCP) from theSVG. Use when the user asks for a brand logo, company icon, framework mark, service icon, or any "icon/logo for X" where X is a real brand or cloud service. Returns ready-to-use CDN URLs or raw SVG markup.

Use when the user asks to "run my launch day", "build a launch day runbook / war room", or "decide CONTINUE or ROLLBACK after the push"; produces a pre-conditions gate check (launch-readiness-auditor SHIP verdict + the authoritative date in launch-registry — missing either stops the skill), a dated hour-blocked runbook with owners (morning irreversible pushes, daytime monitoring loop, evening consolidation), a forced observation-window verdict after every irreversible action against pre-declared kill criteria, a P0-P3 incident ladder with rollback playbooks, and T-0 status lines for the registry proposal protocol. Not for channel submission content and platform rules — use community-launch-runner; not for media replies — use press-media-relations. 发布日runbook/作战室/观察窗/回滚裁决/发布日指挥

Deploy an OpenEnv environment to Hugging Face Spaces. Use when asked to deploy, push to Hugging Face, or update a space.

Diagnose and recover failing or stuck Hugging Face Space deployments for OpenEnv environments. Use when deploying envs from `envs/` to the Hub (`openenv` namespace with version suffixes), when Spaces are in `BUILDING`/`APP_STARTING`/`RUNTIME_ERROR`, or when release collections need to be reconciled after targeted redeploys.

Release workflow for deploying OpenEnv environments to Hugging Face Spaces and keeping canonical references in sync.

> Create or review Stratus Red Team attack techniques. Use when asked to add, create, or implement a new attack technique for AWS, Azure, GCP, Entra ID, EKS, or Kubernetes in the stratus-red-team project. Also use when reviewing PRs or code that implements attack techniques — the guidelines serve as a review checklist.

Tests and validates Stratus Red Team attack techniques by executing warmup, detonation, and cleanup phases with comprehensive validation. Validates cloud credentials, parses command output, checks expected outcomes, and generates HTML reports. Use when testing attack techniques, validating TTPs, verifying technique behavior, or when user mentions stratus, warmup, detonate, or technique IDs like aws.*, azure.*, gcp.*, k8s.*, or entra-id.*. Supports AWS, Azure, GCP, Kubernetes, and Entra ID.

EAS service (paid). Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation.

EAS service (paid). Deploy Expo websites and Expo Router API routes to EAS Hosting - export the web bundle, run eas deploy for production and PR preview URLs, manage environment secrets and custom domains, and work within the Cloudflare Workers runtime. Also covers authoring API routes (+api.ts handlers, HTTP methods, request handling, CORS). Use when deploying an Expo web app or API routes, setting up EAS Hosting, or configuring hosting environments and domains. Not for native builds or store releases - use the eas-app-stores skill for those.

EAS service (paid). Deploy Expo apps to the app stores with EAS - build and submit to the iOS App Store, Google Play Store, and TestFlight, configure eas.json build and submit profiles, manage app versions and build numbers, and publish App Store metadata and ASO. Use whenever the user wants to deploy, release, or ship an app to production or the app stores, is preparing a production build, running eas build or eas submit, shipping to TestFlight, bumping version or build numbers, or setting up store listing metadata. For deploying an Expo website or API routes, use the eas-hosting skill.

Migrate a whole ArcGIS Hub site into a PortalJS Arc portal end-to-end. Harvests the Hub /data.json (DCAT-US) inventory, exports every FeatureService layer through the ArcGIS REST query API with resultOffset paging, converts each to the serverless dual tier (PMTiles render + GeoParquet query) with tabular items to Parquet, pushes everything to Cloudflare R2 via Git LFS, appends dual-tier datasets.json entries, and writes a source-vs-derived parity report. Use to move a City or sector ArcGIS Hub open-data portal onto PortalJS with no server-side compute.

Auto-ingest a geospatial file (GeoJSON, Shapefile, GeoPackage, KML/KMZ, FlatGeobuf, CSV-with-geometry) into a PortalJS portal on the user's own machine, with no server. Normalizes CRS to EPSG:4326, derives a PMTiles render tier and a GeoParquet query tier, pushes all three artifacts to Cloudflare R2 via Git LFS, and appends one dual-tier datasets.json entry the showcase auto-renders. Use when the source is a vector geo format that needs a map or spatial-query view.

Deploy a PortalJS portal to PortalJS Arc — Datopian-managed static hosting on Cloudflare. Builds a static export, uploads it, and returns a live SLUG.arc.portaljs.com URL. One command, one target. Use when a portal is ready to publish or redeploy to a live URL.

Migrate Azure/azure-sdk-for-js to a user-specified minimum Node.js version while preserving any existing references above the target.

Regenerate the @azure/ai-projects client from the latest TypeSpec commit on Azure/azure-rest-api-specs. Use when refreshing emitted code, bumping the pinned tsp-location commit, running tsp-client update, or pulling in upstream Foundry spec changes. Handles the rename dance between tsp-location.saved.yaml and tsp-location.yaml, and captures upstream commit descriptions for post-merge validation.

Guide SDK users through setting up their JavaScript / Node.js environment for Azure AI Content Understanding. Use this skill when users need help installing the SDK, configuring Azure resources, deploying required models, setting environment variables, or running samples.

Run a specific sample for the Azure AI Content Understanding JavaScript SDK. Use when users want to run a particular sample like analyzeUrl.js or analyzeInvoice.js.

Use when writing, reviewing, or debugging Terraform/OpenTofu modules, tests, CI, scans, or state ops - diagnoses failure mode (identity churn, secrets, blast radius, CI drift, state corruption) with version-aware guards.

| dstack is an open-source control plane for GPU provisioning and orchestration across GPU clouds, Kubernetes, and on-prem clusters.

Build robust backend systems with modern technologies (Node.js, Python, Go, Rust), frameworks (NestJS, FastAPI, Django), databases (PostgreSQL, MongoDB, Redis), APIs (REST, GraphQL, gRPC), authentication (OAuth 2.1, JWT), testing strategies, security best practices (OWASP Top 10), performance optimization, scalability patterns (microservices, caching, sharding), DevOps practices (Docker, Kubernetes, CI/CD), and monitoring. Use when designing APIs, implementing authentication, optimizing database queries, setting up CI/CD pipelines, handling security vulnerabilities, building microservices, or developing production-ready backend systems.