DevOps

Helps migrate self-managed Apache Kafka workloads to Amazon MSK Express.

Meta's 86M prompt injection and jailbreak detector.

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL).

Design app specs, deploy to App Platform, watch deployments, and read logs.

Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone animated HTML files with SVG graphics, flowing…

Inspect and explain bmad-loop run artifacts under `.bmad-loop/runs/`.

Autonomous cloud-cost analyst across Neon, Vercel, Railway and GitHub Actions - pulls per-object usage, attributes it to the biggest drivers, root-causes…

Build and release Go binaries that are reproducible and verifiable: version stamping, -trimpath builds, cross-compilation, GoReleaser, checksums, SBOMs…

Continuous integration for Go projects: GitHub Actions pipelines, caching, golangci-lint setup, test/coverage gates, vulnerability scanning, SAST (CodeQL…

Go testing patterns for production-grade code: subtests, test helpers, fixtures, golden files, httptest, testcontainers, fuzz testing, and testing/synctest.

Manage NAP workspaces, prompts, templates, credentials, service tokens, agent files, providers, tags, shares, schedules via REST, and build applications whose…

Evidence-driven penetration and attack-surface engineering for web applications, APIs, networks, identity systems, Active Directory, cloud, containers…

Open-source intelligence (OSINT) collection, passive reconnaissance, attack-surface mapping, phishing campaign analysis, credential exposure auditing, and…

Diagnose app errors, unreachable Droplets, database connection failures, and DNS issues on DigitalOcean, read-only first.

App-level security audit and hardening for Capacitor apps.

Testing guide for Capacitor apps and plugins.

End-to-end LLM accuracy evaluation on AMD ROCm (ROCm-only) — docker container setup OR host (no-docker) runtime, vLLM/SGLang/ATOM serving, lm-eval / lighteval…

Responds to security incidents in cloud environments (AWS, Azure, GCP) by performing identity-based containment, cloud-native log analysis, resource…

Diagnose HitKeep traffic drops, spikes, source shifts, and suspicious changes.

Meta's 7-8B specialized moderation model for LLM input/output filtering.

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML…

Operate a live AWS workload with AWS DevOps Agent — incident investigation, root-cause analysis, and release-readiness review — for startups with no dedicated…

Always use when user asks to create, generate, or build an AWS architecture diagram, cloud infrastructure diagram, or system diagram with AWS services.

Expert FinOps guidance for cloud, AI, and SaaS technology spend.