Skills

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.

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.

Generates candidate names for products, features, projects, or companies against a clear brief. Explores naming styles (descriptive, evocative, coined, compound), checks each for pronounceability and unwanted meanings, and suggests domain and handle patterns to verify. Returns a shortlist with rationale rather than an undifferentiated list.

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.

Designs and implements visual regression testing for web UIs. Recommends a tooling approach (Playwright snapshots, Storybook + a diffing service, or a dedicated platform), writes screenshot tests with stable selectors and masked dynamic regions, sets sensible diff thresholds, and integrates the suite into CI with baseline management to reduce flaky failures.

Reviews and rewrites resumes and CVs to be clear, achievement-focused, and ATS-friendly. Rewrites bullet points using strong action verbs and quantified impact, aligns wording to a target job description, flags gaps and red flags, and checks formatting for applicant tracking system compatibility.

Generates platform-tailored social media posts from a single idea or announcement. Adapts length, tone, hashtags, and formatting for X, LinkedIn, Instagram, and threads. Produces hook-first copy, variant options for A/B testing, and a suggested posting cadence while respecting each platform's conventions and character limits.

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.

Reviews claims in a document for accuracy and verifiability. Extracts discrete factual statements, rates each as supported, unsupported, or needs-verification, flags logical inconsistencies and unsourced numbers, and suggests what evidence would confirm or refute each claim. Designed to reduce hallucinated or outdated facts before publishing.

Turns a messy list of tasks into a ranked, actionable plan. Applies a chosen framework (Eisenhower urgent/important, RICE, MoSCoW, or value/effort) consistently, surfaces dependencies and quick wins, groups work into a realistic today/this-week plan, and explains the ranking so the user can adjust the weighting.

Inspects messy tabular data and produces a repeatable cleaning plan plus code. Detects and fixes common issues: inconsistent types, duplicate rows, missing values, malformed dates, mixed encodings, whitespace and casing problems, and outliers. Outputs pandas or Polars code, a summary of changes, and a validation checklist.

Designs recommendation systems end to end: candidate generation, ranking, and re-ranking. Covers collaborative filtering, content-based and embedding retrieval, two-tower models, cold-start strategies, feature stores, offline/online evaluation (NDCG, recall@k), and feedback loops. Produces an architecture and evaluation plan tailored to the product.

Turns a script, concept, or product idea into a shot-by-shot storyboard. Breaks the narrative into scenes and panels with framing, camera movement, action, and dialogue notes, and generates image-model prompts for each panel so teams can visualize a video, ad, or explainer before production.

Facilitates agile retrospectives that produce action, not just venting. Suggests a format suited to the team's mood, synthesizes raw notes into themes, distinguishes signal from one-off complaints, and turns discussion into specific, owned, time-boxed action items with follow-up on prior ones.

Generates consumer-driven contract tests between services so that API providers and consumers stay compatible as they evolve independently. Produces Pact-style contracts, provider verification stubs, and CI wiring, and flags breaking changes before they reach production.

Develops a distinctive, consistent brand voice and tone system. Defines voice attributes, do/don't guidance, vocabulary and grammar rules, tone shifts by context (marketing, support, errors), and worked before/after examples. Produces a practical style guide teams and AI assistants can apply across every touchpoint.

Writes reusable, well-structured Terraform modules with clean input/output interfaces, sensible defaults, validation rules, and examples. Covers module composition, variable typing and validation, remote state and backends, provider version pinning, and testing with terraform validate/plan and tools like Terratest. Emphasizes least-privilege IAM and safe defaults.

Advises on how to evolve APIs without breaking clients. Compares versioning strategies (URI, header, media-type), classifies changes as breaking or non-breaking, and produces deprecation timelines, migration guides, and compatibility shims so teams can ship changes safely.

Models complex application logic as explicit finite state machines and statecharts. Identifies states, events, guards, and side effects; prevents impossible states; and generates implementations (e.g., XState-style) with diagrams. Ideal for wizards, checkout flows, connection lifecycles, and any feature where implicit boolean flags cause bugs.

Designs chaos engineering experiments to validate system resilience. Defines steady-state hypotheses, blast-radius limits, fault injections (latency, errors, instance/zone loss, resource exhaustion), abort conditions, and observability checks. Produces a safe, incremental experiment plan and success criteria for game days and automated chaos.