Skill UI

Automates the process of monitoring on-page SEO health. It captures comprehensive baselines of SEO-critical elements—including titles, meta descriptions, H tags, Open Graph tags, and Core Web Vitals—and detects any regressions or unexpected changes over time. Use this tool after deployments, content updates, or major structural changes to ensure SEO consistency.

This guide provides a systematic, safe workflow for refactoring rapidly developed or AI-generated fullstack applications. It focuses on identifying and removing dead code, fixing broken imports, and consolidating repetitive logic while strictly maintaining existing API contracts, routes, and core functionality. Use this before launch to ensure a stable, maintainable production baseline, following a 'surgery, not demolition' philosophy.

This skill diffs a live web page's accessibility violations against a specified baseline. It can compare changes against uncommitted local stashes or a specific Git branch. The report focuses exclusively on changes, highlighting new violations introduced, violations that have been fixed, and the count of pre-existing issues. Ideal for CI/CD pipelines and development auditing.

Generates a complete, structured load and performance testing plan for any service. This skill guides the definition of test objectives, establishes measurable SLO thresholds (p99, error rate, throughput), and designs multi-scenario tests (Baseline, Stress, Spike, Soak). It is essential for teams needing to set clear pass/fail criteria, select appropriate tooling (k6, Locust), and integrate performance gates into CI/CD pipelines.

A comprehensive tool for establishing performance baselines across multiple dimensions. It measures Core Web Vitals (LCP, CLS, INP), API latency (p50, p95, p99), and development build efficiency. Essential for detecting performance regressions before merging code, ensuring stability in CI/CD pipelines, and comparing alternative stack implementations.

A comprehensive tool for automated User Interface (UI) testing. It records and replays entire browser sessions, ensuring every test generates a verifiable, replayable artifact (RVF). Use it to validate complex user flows, catch frontend regressions, and establish reliable baselines for continuous integration (CI) pipelines. Supports visual comparison and structured validation steps.

This skill monitors for regressions on deployed URLs following deployments, merges, or dependency upgrades. It performs comprehensive checks including HTTP status, console errors, network failures, performance metrics (LCP/CLS/INP), and crucial API endpoint health, ensuring service stability in production or staging environments. Supports quick checks, continuous monitoring, and differential comparison against baselines.

This tool detects cost regressions by comparing two cost-summary JSON snapshots (baseline vs. current). It is essential for PR-gate workflows, checking for unexpected spending increases using three orthogonal signals: total percentage change, absolute dollar increase, and disproportionate growth in specific token classes (e.g., cache writes).

This skill analyzes historical benchmark run data stored in JSON files. It surfaces key performance drift metrics over time, including win rate, average latency, p99 latency, and LLM-baseline cost. It is crucial for detecting subtle performance degradations or regressions that standard smoke tests might miss, ensuring stability across releases or corpus expansions.

A comprehensive, end-to-end methodology designed for software engineers and AI agents to safely and systematically integrate machine learning models into existing non-ML codebases. It guides users through critical phases, including problem framing, data readiness, architectural decoupling (via APIs/services), baseline model implementation, and final MLOps pipeline setup.