DevOps

Identifies security vulnerabilities, generates structured audit reports with severity ratings, and provides actionable remediation guidance.

Use when implementing infrastructure as code with Terraform across AWS, Azure, or GCP.

Use when the user wants to integrate a Kafka client into an existing application or scaffold a Java Kafka client project (Maven or Gradle based) for Confluent…

Use when the user wants to build a Python Kafka producer or consumer, add Schema Registry to existing Python code, migrate from raw JSON to schema-backed…

Software supply chain security — dependency confusion, CI/CD pipeline attacks, lockfile integrity, and build artifact verification.

Use when a user wants to wire an OpenTelemetry collector into a Managed ClickStack service on ClickHouse Cloud, either by deploying a new local collector…

Configures best-practice, high-signal alerting policies for Cloud Run resources on Google Cloud (services, jobs, and worker pools) based on seasoned SRE…

Use when fixing NeMo Agent Toolkit documentation path-check failures, especially failed `ci/scripts/path_checks.py` output, slash-delimited text mistaken for…

Manages GenAI tuning jobs in Agent Platform.

Sequential squash-merge of stacked PR chains into an epic branch.

Native stacked pull requests through the github/gh-stack extension.

Run GPU workloads on Modal — training, fine-tuning, inference, batch processing.

Diagnose and fix tests that pass sometimes and fail other times.

Check progress for a detached KERMT run (pretrain, finetune, or any kermt_run_detached invocation).

Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech.

Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology.

Agent Platform Model Tuning.

Workflow 1.5: Bridge between idea discovery and auto review.

Deploy and run ML experiments on local or remote GPU servers.

Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU.

Build, deploy, run, and benchmark Filament binaries on connected Android devices or emulators.

Create dark-themed, animated technical diagrams as self-contained HTML+SVG files — flowcharts whose connectors visibly flow, and architecture diagrams where…

Coordinates subagent review, fixes, and verification during implementation; use when the user explicitly asks for Garfield on an active code slice, but not…

Cloud security posture management and container security assessment for AWS, Azure, GCP, and Kubernetes.