Cloud, CI/CD, monitoring, and deployment (6.8K skills)
Analyze agent runs that fail before any work begins. By checking execution counts, tool calls, outputs, and conversation logs, this skill classifies startup failures and directs investigation toward system setup, resources, or input processing.
Configure how Dynamo routes requests to workers, then check model discovery and a chat response. Supports local and Kubernetes setups, including routing based on cached model data, with clear commands, results, and limitations.
Set up NVIDIA infrastructure for synthetic data generation on MicroK8s or Azure AKS. Coordinate Kubernetes, inference services, and OSMO workflow execution, with prerequisite checks, deployment validation, capacity planning, and failure investigation before workloads are retried.
Set up NemoClaw, create an isolated sandbox for OpenClaw, and start the first agent conversation in a browser or terminal. Follow onboarding for model connections, optional search and messaging, and network policy settings.
Deploy a runnable prototype to the hosting service you choose, such as Sites or Vercel. Use the available deployment tool, return a working shareable URL, and identify any remaining manual steps.
Manage Mixpanel Headless login and connection settings, check credentials, and switch accounts, projects, or workspaces. Save named combinations of these settings as targets so an agent can select the intended connection together.
Set up and operate NVIDIA AI-Q Blueprint locally or on your own infrastructure. Choose a deployment mode, configure credentials, check service health, troubleshoot failures, and provide a verified server address for aiq-research.
Check whether a next-generation sequencing workflow has the tools, packages, reference data, and databases it needs. Generate installation and resource setup plans, record available resources, and compare them before rerunning an analysis.
Check whether a Dynamo deployment is ready for disaggregated serving, where input processing and token generation run separately. Read-only probes inspect transport settings, GPU networking capabilities, and NIXL transfer-test readiness, then report gaps and next steps.
Prepare and deploy Expo apps to iOS and Android stores or the web using EAS, Expo's build and deployment services. Covers production builds, store submissions, beta distribution, preview deployments, and automated release workflows.
Create and edit EAS workflow YAML files to automate builds and deployments for Expo projects. Check required settings, job dependencies, and dynamic values against the latest schema, which defines the accepted configuration.
Choose Cloudflare services and implement applications using guidance for compute, storage, AI, networking, and security. The skill directs the agent to relevant references and current official documentation for configuration, APIs, limits, and pricing.
Investigate failed CircleCI jobs, identify the first meaningful error, and distinguish reproducible defects from temporary failures. Apply focused fixes to configuration, test setup, or build code, then explain validation criteria and remaining uncertainty.
Develop and deploy Cloudflare Workers, manage related storage and services, and troubleshoot configuration with Wrangler. The skill checks official documentation and configuration definitions before preparing commands, with guidance for local development, environments, secrets, and logs.
Inspect CircleCI runs, identify failing steps, and validate configuration locally using the CircleCI CLI, its command-line tool. It also guides targeted reruns and pipeline launches, reporting results, permission gaps, and next steps.
Build remote MCP servers, which let AI agents call external tools, on Cloudflare Workers. This skill covers server code, tool definitions, OAuth authentication, local testing, deployment, and connecting a Codex client.
Improve CircleCI build and test pipelines by identifying slow or unreliable jobs, then adjusting caching, data sharing between jobs, triggers, and parallel execution. Receive incremental configuration changes with expected effects, validation criteria, and rollback guidance.
Set up and use CircleCI Chunk for AI-assisted build and delivery workflows. Chooses web or command-line steps for configuration, failed-build troubleshooting, environment setup, and task execution, then reports results and unmet prerequisites.
Set up, update, and authenticate the Boltz command-line tool. Check installation and version status, resolve command lookup problems, and recover from login failures or restrictions imposed by the agent’s execution environment.
Guide an app release through version updates, merging, Git tags that mark a release version, and publication checks. Follow the specified package update commands and rerun the release workflow when a tag needs another attempt.
Load missing API keys, tokens, and other secrets from Infisical into shell environment variables. Retrieve individual values by environment or folder, or make project secrets available to a single command without logging their contents.
Set up the iPolloWork server in Daytona, connect an Electron desktop client through public preview URLs, and check service health and logs. Supports cloud feature validation with separate server and desktop test environments.
Set up an iPolloWork development environment in a Daytona cloud sandbox and access the real Electron app through a browser. Follow procedures for connection URLs, logs, restarts, code updates, and common startup problems.
Compare Sentry issues across selected time windows and releases to find new or recurring problems and changes in frequency or affected users. Prioritize findings using user impact and the strength of available evidence.