Explorar skills

Tutoria especializada em compreensão de leitura de chinês para o ensino fundamental, focada em questões divergentes (sentimentos, raciocínio, associação, imersão em personagens). Guia as crianças com um método de 4 passos, sem dar respostas diretas.

Uma skill para gerenciamento unificado da memória do projeto, que atualiza, poda, reflete e mantém o conhecimento. Ela combina varredura de conversas, deduplicação, detecção de contradições, pontuação de confiança e verificações de consistência.

Use this skill when the user runs /start, says "start", "enable the SDLC workflow", "I want to build", "I want to fix", "set up", "get started", or otherwise signals they want to activate or re-enable the SDLC workflow. Handles three distinct paths based on marker state — fresh install (opt-in activation), re-enable after suspension (reconciliation), and already-enabled (hand off to /plan). Power

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

Propose and write new tests for source files changed in the current session. Detects which functions are already covered and only proposes tests for gaps. Use when the user runs /qf-cover, asks to "add test coverage", asks to "write tests", reacts to the Qualflare hook suggestion, or explicitly invokes this skill. Pass --all to cover an entire file/directory regardless of what changed.

Casamento de padrões múltiplos em strings em O(n + m + z) através de uma trie aumentada com links de falha estilo KMP.

Fetch relevant, high-quality, free-to-use images from the web. Accepts a description/query, or scans the current directory for context. Sources from Unsplash, Pexels, and Pixabay APIs (if keys configured) with a zero-config WebSearch fallback.

Record tacit knowledge — quirks, pitfalls, dependencies, decisions, root causes — as tagged Markdown entries in `.claude/knowledge/entries/`. Use this skill whenever discoveries are made during work, when the user shares undocumented system behavior, or at plan completion to capture lessons learned. Also use when Claude Code makes a mistake pointed out by the user — record what happened, why it wa

Traga sua própria chave de API OpenAI, Google ou OpenRouter para o DeepRead. Todo o processamento de documentos é roteado através da sua conta, sem custo de LLM do DeepRead e ignorando totalmente a cota de páginas, usando a mesma API e endpoints.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs, when task are finished - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Avalie sua posição no espectro entre modo fundador e modo gerente, com base nos frameworks de Brian Chesky e Paul Graham. Ideal para fundadores e CEOs que desejam verificar se estão liderando como fundadores ou se desviando para o modo gerente.

Run the Moonjelly Reef pulse, an orchestrator to scan and dispatch all automated work on autopilot.