Cloud, CI/CD, monitoring, and deployment (6.8K skills)
Diagnose Superset connection, host, terminal, authentication, and update problems using status checks and logs. Get a matching fix, approve changes before they run, and verify whether the original problem is resolved.
Diagnose failed GitHub Actions runs by finding the first meaningful error, separating code problems from infrastructure issues and intermittent failures, and comparing the base branch. Get a focused report explaining the PR’s involvement and recommended next steps.
Investigate a possible incident in Superset’s hosted services by checking deployments, error spikes, and service health. Produce a proposed severity and status page update for human review, without changing services or publishing messages.
Configure a repository for Superset so new isolated Git workspaces have dependencies, environment files, and service access ready. Create lifecycle scripts in .superset/config.json and verify the setup by starting a real test workspace.
Package a CARLA server built with UE 5.8 for distribution, choosing which maps to include. Inspect the resulting files for mismatched containers, missing road data, and exposure settings that can cause runtime failures.
Start a CARLA simulator server from a downloaded release, packaged build, or source checkout. It selects the launch mode, supports headless or windowed operation, checks client connectivity, and guides clean shutdown.
Start, inspect, and stop a CARLA UE 5.8 server. Choose an editor-based server, packaged build, or full editor; configure headless operation and ports; and enable native ROS 2 integration when the build supports it.
Build distributable CARLA releases or asset packages containing selected maps and props. It prepares content for runtime use, checks output files, supports destination changes, and preserves native ROS 2 support when explicitly enabled.
Package a CARLA Leaderboard agent into a Docker image for submission. It checks required directories and Python package files, supports ROS variants, and verifies that dependencies import and the agent loads inside the image.
Set up a CARLA driving evaluation environment for Leaderboard 1.0, 2.0, or 2.1. Match the simulator and scenario_runner versions, configure Python paths, and verify that the required components load correctly.
Downloads CARLA release packages, nightly builds, source code, or Docker images, then reports their locations and environment variables for follow-up setup. Supports extra maps and resumable downloads, helping prepare the files needed for subsequent installation or building.
Set up ScenarioRunner, CARLA’s scenario engine, with a branch matched to your simulator version. Install dependencies, configure Python search paths, and verify imports to address setup failures before running scenarios.
Deploy language model APIs and run batch generation with vLLM. Configure GPU memory use, quantization—lower precision model storage—and distribution across GPUs, then test response times and monitor how many requests the server handles.
Configure machine learning training and batch jobs across multiple clouds with SkyPilot. The skill guides GPU selection, lower-cost cloud and region choices, and automatic recovery when discounted spot instances are interrupted.
Guides setup and operation of Lambda Labs GPU instances for machine learning training and inference. Covers SSH access, persistent storage, API automation, and multi-GPU or multi-node training, including how to retain checkpoints and terminate idle instances.
Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.
Run Python code and Shell commands in an isolated Cube Sandbox environment. The skill covers file access, host directory mounting, network restrictions, and pausing and resuming execution while preserving the sandbox's memory state.
Update release base versions for supported packages, keep matching version fields in sync, and verify generated versions. The workflow covers committing and pushing the changes, with guidance for release steps after merging.
Move an ongoing task to a new HumanLayer session on another machine. The skill saves and pushes changes, writes handoff notes, prepares the destination, transfers selected secret files, and checks that the remote session starts.
Prepare an Ant Design Mobile package release by checking the version, build, and package contents. After the user publishes to npm manually, verify the published package and create its Git tag and bilingual GitHub Release.
Build infrastructure as code with Terraform across AWS, Azure, and GCP. Create reusable modules, manage state records that track resources, configure environments and providers, and validate proposed changes before applying an explicitly approved plan.
Define reliability targets for production services and calculate error budgets, the allowed amount of failure. Create monitoring rules, incident response runbooks, capacity plans, and automation scripts, with failure experiments to check recovery behavior.
Create Dockerfiles, automated build and deployment pipelines, Kubernetes configurations, and infrastructure templates. The skill also prepares deployment checks, rollback procedures, and incident response runbooks to support application releases and production operations.
Analyze and tune PostgreSQL databases using query execution plans, which show how queries run. This skill guides index design, JSONB searches, replication setup, maintenance, and monitoring, with checks to compare behavior before and after changes.