Skill rating

Manages containers, builds images, configures pods and networks with Podman. Use when running containers, creating Containerfiles, grouping services in pods, or managing container resources.

Audit a deployed web app for secrets exposed to the browser: hardcoded API keys/tokens in JS, secrets in HTML meta/attributes/comments, publicly reachable source/config/deploy files, and header/CORS m

Provisioning infrastructure via cloud IaC (Terraform/OpenTofu/CloudFormation/Pulumi) and local dev environments (Docker Compose, env vars). Use for IaC design or multi-cloud provisioning.

Manage container registries including ECR, ACR, GCR, and Docker Hub.

Secure Docker images and container runtime configurations.

Scan container images for vulnerabilities using Trivy, Grype, and cloud-native tools.

Administer PostgreSQL databases. Configure replication, backups, and performance tuning. Use when managing PostgreSQL deployments.

Deploy containers on ECS and Fargate. Configure task definitions, services, and load balancing. Use when running containerized workloads on AWS.

Define and run multi-container Docker applications using Docker Compose.

Build, test, and deploy applications using GitHub Actions workflows.

Configure object storage with S3, GCS, and MinIO. Implement lifecycle policies and access controls. Use when managing object storage.

Configure nginx and Traefik as reverse proxies. Implement SSL termination and routing. Use when setting up application gateways.

Configure Grafana Loki for log aggregation and analysis.

Deploy an API gateway for LLM traffic with load balancing, rate limiting, key management, semantic caching, fallback routing, and cost tracking.

Configure NFS servers and clients. Implement network file sharing for Linux systems. Use when setting up shared storage.

Operate MySQL-compatible databases on PlanetScale with branching workflows, safe migrations, and production rollouts.

Deploy and manage vLLM for high-throughput LLM inference. Configure continuous batching, tensor parallelism, quantization, and OpenAI-compatible API endpoints for production LLM serving.

Deploy and manage the ELK Stack (Elasticsearch, Logstash, Kibana) for log aggregation and analysis.

Configure GitLab CI/CD pipelines and runners for automated building, testing, and deployment.

Manage Red Hat OpenShift clusters and deployments.

Configure CircleCI workflows and orbs for continuous integration and deployment.

Create and manage Jenkins CI/CD pipelines, configure agents, manage plugins, and automate builds.

Configure Redis for caching and data storage. Set up clustering, persistence, and Sentinel. Use when implementing Redis caching or queues.

Design and implement CI/CD pipelines, Docker configurations, deployment strategies, and infrastructure automation with production-ready patterns.

Prove a deploy landed — the served revision is the commit you meant, its env is present, and the product does its job — instead of trusting the deploy command's exit code. Also catches server drift be

Deploy, configure, and maintain a self-hosted Headscale control server on Linux or Docker. Use when setting up a new Headscale instance, troubleshooting deployment issues, or configuring server settin

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production A

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed a

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GP

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable

Architect, build, and debug Kafka Streams apps (JVM-embedded stream processing). Use when user mentions KStream, KTable, topology, TopologyTestDriver, StreamsBuilder, interactive queries, GlobalKTable

Builds a production-style Express.js REST API with JWT authentication, PostgreSQL, layered middleware, and Docker Compose for local development. Use when the user asks to scaffold a secure Node.js/Exp

Manually dispatch and iterate on the Release Canary workflow that smoke-tests published OpenShell artifacts (install.sh on macOS/Ubuntu/Fedora, Helm chart on kind) after each Release Dev publish. Use

Paperclip is a self-hosted Node.js server and web dashboard that runs a team of AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw) as a company, with an org chart, goals, tasks, mon

Verification loop for Quarkus projects: build, static analysis (Checkstyle, PMD, SpotBugs), tests with JaCoCo coverage, OWASP dependency and container security scans, GraalVM native compilation, healt

Vite build tool patterns including config, plugins, HMR, env variables, proxy setup, SSR, library mode, dependency pre-bundling, and build optimization. Activate when working with vite.config.ts, Vite

Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizin

Reduces container attack surface by building application images on Google distroless base images that ship only the application runtime - no shell, package manager, or OS utilities - using multi-stage

Implements supply chain integrity verification for container builds with the in-toto framework: generating signing keys, defining a supply chain layout, recording pipeline steps as signed link metadat

Integrates OWASP ZAP (Zed Attack Proxy) into GitHub Actions and GitLab CI pipelines, covering baseline, full, and API scan configuration against running applications, ZAP finding interpretation, scan

Analyzes and simulates BGP hijacking scenarios in authorized lab environments to assess route origin validation, RPKI deployment, and BGP monitoring defenses against prefix hijacking and route leak at

Audits container and pod configuration for escape-enabling misconfiguration using the Kubernetes Python client - privileged flags, dangerous capability grants, host path mounts, shared namespaces, and

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language suppor

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-sourc

Verify or integrate Jet Browser when a project needs isolated WPE WebKit sessions, native input, screenshots, ordered JSONL automation, or reproducible runtime checks.

Review a Dockerfile for image size, layer caching and running as root, and suggest fixes.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language suppor

Build Quarkus native executables (Mandrel/GraalVM), fix native failures with reflection registration, test the native binary, and produce container images and Kubernetes/OpenShift manifests. Use for n

Add or use full agent harness runtimes like Claude Code, Codex, Pi, Cursor, Mastra, or ACP agents inside Agent-Native.