Skills

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

Defines versioned data contracts between producers and consumers, with ownership, schemas, quality expectations, compatibility rules, and operational change management.

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

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

Designs reliable AI-assisted business and engineering automations with triggers, approvals, idempotency, observability, exception handling, and human handoff points.

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

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

Synthesizes interviews, support tickets, reviews, and survey responses into evidence-based themes, opportunities, representative quotes, confidence levels, and product actions.

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

Produces structured test plans for features and releases. Defines scope and objectives, derives test cases from requirements and acceptance criteria, covers functional, edge, negative, performance, and accessibility cases, sets entry/exit criteria, and maps risk to test priority. Outputs a clear plan with a traceability matrix linking tests to requirements.

Writes idempotent Ansible playbooks and roles from a described target state. Structures tasks with proper handlers, variables, and templates; favors modules over shell commands; applies role-based layout and inventory grouping; and adds check-mode safety and tags. Produces playbooks that are re-runnable without unintended side effects.

Sets up and maintains Git hooks for a repository. Recommends a manager (Husky, Lefthook, or pre-commit), wires up pre-commit and commit-msg hooks for linting, formatting, type checks, secret scanning, and conventional-commit validation, and keeps hooks fast with staged-file filtering. Produces config plus a short contributor guide.

Generates and refactors dbt models for analytics engineering. Writes staging, intermediate, and mart models following layered conventions, adds schema.yml tests and descriptions, applies incremental and materialization strategies, and structures sources and refs correctly. Produces SQL plus YAML that fits dbt best practices and is ready to run.

Explains what a SQL query does in plain language and how it executes. Breaks down joins, subqueries, CTEs, and window functions step by step, describes the result set, reads EXPLAIN/EXPLAIN ANALYZE output to identify slow scans and missing indexes, and flags correctness pitfalls. Helps developers understand, review, and trust unfamiliar SQL.

Creates accessible color palettes for brands and UIs from a brief or a seed color. Produces primary, secondary, and neutral scales with hex values, suggests semantic tokens (success, warning, error, info), and checks foreground/background pairings against WCAG contrast ratios. Outputs ready-to-use CSS variables or design tokens.

Produces operational runbooks for services and common incidents. Documents prerequisites, step-by-step diagnosis and remediation, exact commands, verification checks, rollback steps, and escalation paths. Structures each runbook so an on-call engineer can follow it under pressure, and keeps destructive steps clearly flagged with safeguards.

Translates requirements and user stories into behavior-driven development scenarios in Gherkin. Writes clear Given/When/Then steps, covers happy paths, edge cases, and negative cases, uses scenario outlines with examples for data-driven tests, and keeps steps declarative and reusable. Optionally scaffolds step definitions for Cucumber or Behave.

Produces production-ready nginx configuration for common scenarios: reverse proxy, load balancing, TLS termination, static file serving, HTTP/2, gzip/brotli, caching, rate limiting, and security headers. Explains each directive, warns about risky defaults, and includes a validation step so the config can be tested before reload.

Drafts long-form blog posts from a topic, outline, or set of notes. Handles title and hook generation, logical section structure, SEO-aware headings, tone matching, internal linking suggestions, and a clear call to action. Produces publish-ready Markdown with meta description and suggested tags.

Decodes and reviews JSON Web Tokens and their surrounding auth flow for correctness and security. Explains header and claims, checks algorithm and key handling, validates expiration and audience/issuer claims, and flags common pitfalls such as the alg:none attack, weak secrets, missing validation, and over-long token lifetimes. Never treats token contents as trusted secrets to echo back.

Designs caching strategies across the stack to cut latency and load. Chooses cache layers (browser, CDN, application, database), picks patterns (cache-aside, read-through, write-through, write-behind), sets TTLs and eviction policies, and plans invalidation to avoid staleness and stampedes. Produces a layered plan with keys, TTLs, and invalidation rules.