Explorar skills

Esta skill permite ler, pesquisar e resumir o histórico de conversas do Claude Code. É usada para encontrar discussões passadas, revisar tópicos antigos, resumir trabalhos, extrair aprendizados ou relembrar valores, portas ou comandos específicos.

Background dual-agent collaboration with Codex CLI. Sends tasks to Codex via `codex exec` in the background, captures JSONL output, and integrates results without blocking Claude Code. No tmux, no Terminal windows. Use when asked to "codex collab", "dual agent", "pair with codex", "codex tmux", "collaborate with codex", "let codex help", or "spiral coding".

Build full-paper Chinese-English side-by-side, figure/table-aware, source-grounded Markdown readers for journal or conference papers from PDF, DOI, arXiv, publisher HTML, or pasted text. Use whenever the user asks to translate or read a paper, make 中英文对照/原文对照/全文翻译解读, extract figures or tables into the right positions, preserve figure/table placement near relevant prose, or keep exact source anchor

Generate a GEO audit report from collected sub-agent + verifier-script outputs. Produces two artifacts: (1) Markdown audit document and (2) HTML technical guide (sidebar-navigated, scrollable, dark theme). Saves into the working directory with date-stamped filenames. Triggers on: GEO report, generate report, audit report, technical guide, share with team.

Guia para aprimorar o código frontend com a capacidade de renderizar saídas de IA/LLM (Markdown, LaTeX, blocos de código) de forma segura e precisa na interface do usuário.

Utilize para auditar aplicações web quanto à conformidade com WCAG, realizar verificações de acessibilidade em URLs (incluindo rotas autenticadas), gerar relatórios de achados, preencher VPATs/ACRs ou obter soluções concretas para violações. O padrão é WCAG 2.2 Nível AA, com AAA opcional.

Navigate and extract reusable design patterns from the Hermes Agent source code for application in our project. It covers ten subsystems: bootstrap/CLI, conversation engine, prompt/context, tool system, gateway/messaging, skills, terminal backends, memory/persistence, RL training, and integrations (ACP/MCP/plugins). Use this skill whenever a user wants to study, reference, or adapt architectural p

Resgata sessões anteriores do Claude Code que ficaram perdidas após uma pasta de projeto ser movida ou renomeada. Use esta skill sempre que o usuário mencionar perda de histórico de chat, não conseguir encontrar sessões antigas em /resume, tiver movido sua pasta de projeto, quiser trazer contexto de conversas passadas para uma nova sessão, ou quiser arquivar/exportar conversas do Claude como markdown.

Translate text, files, and conversations between any languages. Auto-detects source language. Preserves formatting (markdown, code blocks, tables). Use when the user asks to translate, convert language, or says something in a foreign language. Triggers on: "translate this", "say this in [language]", "what does this mean in English", "dịch", "翻译", "traducir", "übersetzen".

Query the wiki and render the answer as portable, GitHub-flavored markdown saved under vault/output/. Trigger when the user asks to "export X as markdown", "produce a markdown brief", "save the answer to the output folder", "give me a plain markdown version of …", or invokes /llm-wiki-stack:llm-wiki-markdown directly. Reuses the llm-wiki-query reading contract, then strips Obsidian-only syntax so

Query market data from Yahoo Finance — prices, fundamentals, earnings, options, dividends, history. Pure data tool for any ticker (US, HK, A-shares, crypto, forex, ETFs). Use before analysis, not instead of it.

Generate beautiful HTML slide presentations from markdown or plain text. Dark theme, smooth animations, speaker notes. Output is a single HTML file that opens in any browser. Use when the user asks to create slides, a presentation, a deck, or a pitch. Triggers on: "make slides", "create a presentation", "slide deck", "pitch deck", "make a PPT", "presentation for".