Dados e Análise

Documentação completa da plataforma Supabase, cobrindo autenticação, banco de dados, armazenamento, edge functions, assinaturas em tempo real, IA/embeddings, cron jobs, filas e gerenciamento da plataforma. Inclui integrações com frameworks como Next.js, React e SvelteKit.

Generate probe-skeleton YAML files at `lineage/{repo}/probes/{P-NNN}.yaml` from `feature-flows.yaml`'s uncovered test-matrix cells. Each skeleton carries the feature_id + test_class + cross-references + a TODO-marked arrange/act/observe/assert block the maintainer fills in. Accelerates probe corpus growth — slice 4 of dynamic-verification ADR. Local-only per APPROACH.md section 5 rule 12.

Query the Raider.IO API for Mythic+ scores, run history, dungeon rankings, character profiles, and guild data. Use this skill when the user asks about M+ scores, key levels, dungeon runs, push targets, Raider.IO profiles, M+ rankings, weekly keys, or asks "what keys do I need". Also use when the user mentions raider.io, rio score, or asks about M+ meta/comps based on leaderboard data.

Exports approved outreach emails into the user's preferred format: sequencer CSV, plain text, or formatted for specific tools. Triggers: /push, "export emails", "push to instantly", "push to outreach". Reads: ./gtm/prospects.md, ./gtm/icp.md (for stack info). Writes: output files in ./gtm/export/. Standalone: yes.

Convert raw scanner findings into atomic work items in the backlog. Assigns priority, category, effort, and identifies file conflicts.

Analisa, limpa e descreve arquivos CSV e dados tabulares, detectando tipos de dados, valores nulos, duplicatas e outliers. Também gera resumos executivos em texto simples ou markdown.

Esta skill é ativada quando o usuário se refere ao YouTube, transcrições ou resumos de vídeos, conteúdo do YouTube, ou busca extrair informações de vídeos.

Realiza análise técnica abrangente utilizando mais de 12 indicadores, incluindo RSI, MACD, Bandas de Bollinger, suporte/resistência e padrões gráficos, através da API Finskills.

Analyze Strava-derived fitness notes that already exist in an Obsidian vault, then generate deeper dashboards, proxy training-load metrics, trend reports, and visual summaries. Use when the user wants post-sync analysis of existing workout notes rather than fetching new data from Strava.

Use this skill whenever the user wants to build, train, evaluate, or iterate on a supervised machine learning or deep learning model. Triggers include: any mention of training or fitting a model with labeled data, dataset preparation, hyperparameter tuning, cross-validation, model checkpointing, experiment tracking, overfitting, loss curves, metrics, or prediction visualization. Also trigger when

Help a backend engineer gather cross-repo context from browser DevTools network calls, trace API ownership to the right microservice, understand frontend data expectations, and determine exactly what backend changes are needed. Use when user pastes a DevTools network call, asks "which service owns this", wants to understand FE dependencies, or says "be-api-trace" or "trace this API".

Oferece inteligência para SEO local, abrangendo rastreamento de ranking por geo-grade, auditoria de perfil GBP, inteligência de avaliações em diversas plataformas, verificação NAP multiplataforma, mapeamento de concorrentes e geração de esquema LocalBusiness. A capacidade é de três níveis: gratuito, DataForSEO para inteligência completa e DataForSEO + Google para cobertura máxima.