Explorar skills

When the agent is about to output long markdown (weekly reports, PR reviews, design comparisons, concept explainers, flowcharts, design systems and other deliverables meant for human reading), proactively evaluate whether to render it as HTML instead. Based on the 20 examples from ThariqS/html-effectiveness. Only proposes when a clear high-value scenario is detected; with user consent, generates t

Use this skill during /plan (between scope validation and writing the plan artifact) to inject domain-specific context, gap questions, and regulatory concerns into the plan. Triggers automatically when the plan skill evaluates the task and scope.md against the domain registry in domains/_index.json using semantic judgment — no keyword list required. Produces a ## Domain context section in the plan

ALWAYS activate this skill before implementing EVERY feature, plan, or fix.

Google Search Console analysis and comprehensive SEO auditing. Site crawling, PageSpeed Insights, indexing API, on-page analysis, schema validation, hreflang, security headers, content quality, mobile SEO. Requires gsc-analyzer extension. Triggers on: /creo gsc, Google Search Console, GSC, site audit.

Run all 9 quality lenses against every phase and skill file in the Moonjelly Reef. For each lens, dispatches one sub-agent per file in parallel, then advances to the next lens. Use when doing a periodic quality review of the reef's phase files.

Download, split, and deeply read academic PDFs. Use when asked to read, review, or summarize an academic paper. Splits PDFs into 4-page chunks, reads them in small batches, and produces structured reading notes, avoiding context window crashes and shallow comprehension.

Generate a commit message from staged changes and let the user review before committing. Use when the user wants to commit changes or create a git commit.

Previsão da estrutura e interpretação da confiança de AlphaFold/ESMFold.

Fundamentos do RDKit: análise de SMILES, propriedades moleculares, busca de subestruturas, impressões digitais e similaridade química. Use ao realizar operações de quimioinformática em Python.

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

MOFA2 é uma análise fatorial multi-ômica não supervisionada que realiza decomposição de variância, interpretação de fatores e separação de sinais compartilhados/específicos. É ideal para integrar múltiplas camadas ômicas.

Conduza pesquisas de marketing de produto utilizando a plataforma de personas sintéticas da Ditto, que oferece mais de 300 mil personas de IA com 92% de sobreposição com grupos focais reais. A plataforma abrange validação de posicionamento, teste de mensagens, inteligência competitiva, pesquisa de preços, validação de GTM, teste de lançamento de produto, desenvolvimento de persona de comprador e rastreamento de marca, além de perguntas rápidas e anexos de mídia.