Desenvolvimento

Referral program design - referrer / referee incentive structure, viral mechanics, fraud and abuse controls, attribution, and channel placement. Use when: referral program, refer a friend, viral loop design, K-factor, advocacy referrals, partner referrals, customer referral incentives, referral attribution, viral coefficient.

Sales and marketing enablement asset creation system that generates structured materials from pitch decks to objection handlers to ROI calculators. Use when: sales enablement, create battle cards, pitch deck, sales assets, talk tracks, objection handling, sales collateral, marketing assets.

Full spec-driven setup workflow for building a brand new app from scratch with an AI coding agent. Triggers on "new:" prefix, "I want to build a new app", "starting a new project", "help me spec out a new app", "new project". Always use when the user is starting a greenfield project — even without the exact prefix. Generates CLAUDE.md at project root and the complete vibe/ folder. Reads BRIEF.md a

Creates a polished 3-4 page GTM executive brief and plan with a 4-slide PowerPoint deck. Orchestrates market analysis, positioning, competitive intel, channel strategy, and launch planning into exec-ready deliverables. Use when: GTM plan, go-to-market plan, GTM strategy, GTM brief, executive GTM plan, GTM deck, GTM presentation, launch plan deck, product GTM strategy, platform GTM, developer platf

Progressively migrates legacy prototype routes and features to a clean architecture layer slice-by-slice, verifying them against characterization tests, running purity/drift checks, and executing completion certifications.

Use when user reports a bug, wants to file an issue, mentions "triage", when investigating a production problem before fixing it, when planning a fix that needs a TDD-shaped GitHub issue, or when a bug needs root-cause analysis before assignment.

Pipeline de chamada de variantes, formato VCF, decodificação de genótipos e análise de SNPs com GATK/bcftools.

Esta skill oferece um conselho de revisão de código multiperspectiva, onde consultores analisam, revisores questionam e um presidente sintetiza o veredito. É ideal para decisões de arquitetura, auditorias de segurança e revisões profundas, não para geração de código simples ou correções de sintaxe.

Especializado em regressão, correlação e diagnósticos em R, cobrindo intervalos de confiança, testes t, testes de normalidade, correlação de Pearson/Spearman/Kendall e IC da transformação z de Fisher.

Prepares a vibe-* project for deployment to 7 platforms: Railway, Render, Fly.io, Heroku, Vercel, Netlify, GitHub Pages. Detects stack automatically (FastAPI, Express, Next.js, Django, React, Vue, static). Patches source files (port binding to $PORT, adds /health endpoint, production CORS). Generates platform config files scoped per service — backend, web, worker. Inlines non-secret env vars direc

First-time Qualflare setup for this project. Detects languages and test frameworks, writes .qualflare/test-state.md, and configures the optional Stop hook. Use when the user runs /qf-init or asks to "set up Qualflare" or "initialize Qualflare".

Run the execution + quality polish + delivery stages of review-loop against one of three entry modes: resume an approved session (`--session`), execute a user-supplied plan (`--plan`), or run a pure-CR pass on the current working tree (`--review-only`). Supports batched runs via `--stop-after <stage>`. Use when you already have a plan, or only want CR on existing code.