acardozzo
15 verified skills
doc-rx
Evaluates documentation quality and developer experience across 8 dimensions and 32 sub-metrics. Assesses whether someone new can understand, onboard, and contribute to a project. Covers README, API docs, code docs, ADRs, onboarding, changelog, tutorials, and error messages. Produces a scored report with actionable recommendations.
development
project-rx
Project completeness inspector — identifies missing components, capabilities, and infrastructure for your project type. Detects project archetype (SaaS, API Platform, Marketplace, Internal Tool, Mobile Backend, AI Product, CLI, Library) and evaluates against a mandatory component checklist. Use when starting a project, planning features, doing gap analysis, or when the user says "what's missing", "run project-rx", "project audit", "completeness check", "gap analysis", "what should I build next", or "inspect project". Produces a completeness scorecard with prioritized build plan.
tools
data-rx
Prescriptive data model and Supabase evaluation producing scored opportunity maps. Evaluates schema design, RLS policies, migration quality, query patterns, Supabase Auth/Storage/Realtime/Edge Functions usage, and PostgreSQL best practices. Use when: auditing data model, reviewing Supabase setup, scoring database quality, or when the user says "data audit", "run data-rx", "schema review", "supabase check", "RLS audit", "migration review", "database quality", or "data model review". Measures 10 dimensions (40 sub-metrics) with exact thresholds from PostgreSQL docs, Supabase official patterns, Database Design (Date), and Use The Index Luke. Produces per-project scorecards with Supabase feature adoption matrix. Fixed stack: Supabase (PostgreSQL + Auth + Storage + Edge Functions + Realtime + RLS).
testing
test-rx
Evaluates testing strategy and completeness across 8 dimensions (32 sub-metrics): test pyramid balance, test effectiveness, contract/API testing, UI/visual testing, performance/load testing, test data management, CI integration, and test organization. Produces a scored diagnostic with actionable improvement plans.
development
api-rx
Metric-driven API surface design quality evaluation from a consumer's perspective. Use when: evaluating REST API quality, scoring endpoint design, reviewing response contracts, comparing API versions, validating developer experience, or when the user says "grade this API", "evaluate API", "API design review", "score this API", "REST quality", "run api-rx", "API quality check", or "how good is this API". Measures 8 dimensions (32 sub-metrics) with exact thresholds from Richardson Maturity Model, JSON:API, Google AIP, Stripe API model, OAuth 2.1, OpenAPI 3.1, Standard Webhooks, and HTTP Caching RFCs. Produces scorecards with actionable prescriptions.
development
code-rx
Metric-driven code quality evaluation producing objective, repeatable grades and prescriptions. Use when: evaluating code quality, measuring technical debt, scoring a layer/module/codebase, comparing before/after refactoring, validating plan targets, or when the user says "grade this", "evaluate quality", "score this code", "how good is this layer", "measure code quality", "run code-rx", "code quality check", or "what grade does X get". Measures 8 dimensions (29 sub-metrics) with exact thresholds from ISO 25010, SQALE, SonarQube, Robert Martin package metrics, SIG, and CodeClimate. Produces per-layer scorecards and aggregate grades.
tools
sec-rx
Code-level security posture evaluation. Scans for OWASP Top 10 vulnerabilities, authentication flaws, injection vectors, authorization gaps, and data protection issues. Complements arch-rx D9 (architectural security) by inspecting actual source code patterns, dependencies, and security configurations. Produces a scored report across 8 dimensions with 32 sub-metrics mapped to OWASP ASVS and CWE references.
development
rx-dashboard
Shows the rx-suite progress dashboard across all domains and dimensions. Displays which dimensions are at A+, which have active improvement plans, and what to work on next. Use when the user says "rx dashboard", "show progress", "rx status", "what's next", "improvement status", "plan status", "show dashboard", "rx overview", or "what should I work on".
data-ai
project-agno-rx
Specialist evaluation for Agno AI agent projects. Evaluates agent design, tool usage, knowledge/RAG setup, memory management, team coordination, workflow orchestration, deployment readiness, and observability against Agno best practices. Use when building with Agno, auditing agent quality, or when the user says "agno audit", "run project-agno-rx", "evaluate my agents", "agno best practices", or "agent quality check". Measures 10 dimensions (40 sub-metrics) specific to the Agno framework.
tools
ux-rx
Prescriptive UX/UI evaluation producing scored opportunity maps for Next.js + shadcn/ui projects. Evaluates user experience against Nielsen Heuristics, WCAG 2.2, Core Web Vitals, Laws of UX, and Atomic Design. Use when: auditing UX quality, evaluating accessibility, reviewing component usage, identifying missing shadcn components, improving form UX, or when the user says "ux audit", "run ux-rx", "evaluate UX", "accessibility check", "improve user experience", "shadcn review", "how to reach A+ UX", or "UX opportunities". Measures 11 dimensions (44 sub-metrics). Fixed stack: Next.js App Router + shadcn/ui + Tailwind CSS. Leverages shadcn registry to recommend ready-to-use components. Outputs per-page scorecards with before/after Mermaid diagrams.
development
ops-rx
Prescriptive operational and SRE maturity evaluation producing scored diagnostic maps. Evaluates whether you can OPERATE a system reliably in production — beyond architecture and code quality. Measures 8 dimensions (32 sub-metrics) against Google SRE, DORA, FinOps, and AWS Well-Architected frameworks. Produces per-dimension scorecards with actionable prescriptions and aggregate grades.
development
rx-execute
Executes rx improvement plans step by step with verification. Reads versioned plans from docs/rx-plans/{domain}/{dimension}/, implements each step, verifies acceptance criteria, then re-runs the rx skill to confirm score improvement. Auto-generates next version plan if target not reached. Use when the user says "execute rx plan", "implement improvements", "rx execute", "fix dimension", "improve score", or references a specific plan file.
testing
arch-rx
Prescriptive architectural decision evaluation producing scored ADR opportunity maps. Complements code-rx by evaluating runtime architecture against POSA, EIP, 12-Factor, CNCF, NIST Zero Trust, SLSA, and Well-Architected Frameworks. Use when: identifying where to add queues, async processing, circuit breakers, caching, protocol changes, multi-tenancy, or AI/ML patterns; evaluating security architecture; or when the user says "prescribe architecture", "run arch-rx", "pattern fit", "architectural opportunities", or "how to reach A+ architecture". Measures 11 dimensions (44 sub-metrics). Stack-agnostic — adapts to Node.js, Go, JVM, Python, Rust, .NET.
development
rx-plan
Generates versioned improvement plans from rx report results. Creates one plan per dimension that scores below A+ (97). Plans are saved to docs/rx-plans/{domain}/{dimension}/v{N}-{date}-plan.md. Use after running any rx skill, or when the user says "create plan from report", "rx plan", "plan improvements", "generate improvement plan", "what should I fix first", "create roadmap", "improvement plan", "plan from audit", or "next steps from rx".
testing
clean-rx
Codebase garbage collector — finds dead code, unused deps, orphan files, stale configs, and tech debt across Python, Next.js, and Supabase projects. Produces a prioritized cleanup plan with safe removal steps. Use when the user says "cleanup", "run clean-rx", "find dead code", "remove unused", "tech debt audit", "garbage collect", "what can I delete", "lixo", or "clean project". Leverages LSP, madge, depcheck, and knip for deep dead code detection.
development