Skills

Diagnoses failing Kubernetes workloads from symptoms, events, logs, and manifests. Works through a systematic checklist (pod status, events, resource limits, probes, scheduling, networking) to identify the root cause of issues like CrashLoopBackOff, ImagePullBackOff, OOMKilled, and pending pods, then recommends concrete fixes and verification steps.

Designs a customer churn prediction approach end to end: framing the target and prediction window, engineering behavioral and tenure features, choosing suitable models and evaluation metrics for imbalanced data, and planning how predictions feed retention actions. Focuses on leakage-free design and metrics that match the business goal.

Analyzes Terraform plan output and state to find configuration drift between declared infrastructure and what actually exists. Explains each drifted resource in plain language, flags risky or destructive changes, and recommends whether to reconcile in code, import, or apply, so teams can keep state and reality aligned safely.

Designs and drives computer-use agents that operate a desktop or browser directly via screenshots and UI actions (click, type, scroll, navigate). Plans multi-step GUI workflows, handles verification and recovery between steps, and structures guardrails for safe autonomous execution. Built for models exposing computer use as a native client-side tool.

Finds, validates, and fixes security vulnerabilities end to end, going beyond audit-only review to produce verified patches. Reproduces the issue, proposes a minimal fix, and confirms the vulnerability is closed without breaking existing behavior. Models a CodeMender-style workflow where multiple agents detect, validate, and patch code security issues at scale.

Designs and implements secure, ergonomic Model Context Protocol servers with precise tool schemas, transport selection, authentication boundaries, error contracts, and tests.

Defines repeatable quality evaluation for LLM outputs using representative datasets, scoring rubrics, model-graded checks, human review sampling, and regression thresholds.

Optimizes prompts and agent workflows for finite context windows by prioritizing evidence, compressing history, managing retrieval budgets, and measuring token-cost trade-offs.

Designs low-risk secret rotation for applications and agents, covering inventory, overlapping credentials, automation, audit evidence, emergency revocation, and rollback.

Designs durable API evolution plans with compatibility guarantees, deprecation policy, version negotiation, consumer communication, migration tooling, and operational telemetry.

Reviews Model Context Protocol servers for excessive permissions, unsafe tool design, prompt injection exposure, secret handling, authorization gaps, and auditability.

Simulates realistic adversarial behavior against AI features to uncover prompt injection, data exfiltration, unsafe tool use, jailbreak, and authorization failures before launch.

Converts a design specification or screenshot into accessible, responsive production UI while preserving component boundaries, design tokens, semantic structure, and states.

Tests AI agent tool use with realistic fixtures, malformed inputs, permission boundaries, deterministic assertions, and recovery checks for failed or partially completed actions.

Diagnoses failing browser and end-to-end tests by correlating assertions, traces, screenshots, network activity, timing, and application state into reproducible fixes.

Reviews cloud and AI infrastructure spend to identify measurable savings while preserving reliability, performance, security, ownership, and product requirements.

Converts product safety requirements into practical agent and LLM policies with abuse cases, escalation paths, safe defaults, audit events, and acceptance criteria.

Guides containment, evidence collection, root-cause analysis, customer communication, and remediation when an AI agent takes an unsafe, incorrect, or unauthorized action.

Evaluates retrieval quality for search and RAG systems using grounded test sets, relevance metrics, failure taxonomy, chunking experiments, and actionable remediation.

Plans safe database schema and data migrations with backwards compatibility, staged rollout, validation, rollback, performance safeguards, and application coordination.

Designs durable memory for AI agents, including what to retain, how to retrieve it, privacy boundaries, expiration policies, and evaluation criteria for useful recall.