Pesquisa e Web

Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use for web browsing, form submission, web scraping, or UI testing. NOT for static content (use curl/wget).

Universal self-review protocol for all Rune teammates. Adapts checklist per agent role (worker, fixer, reviewer, researcher, forger, aggregator). Enforces completeness verification, hallucination detection, codebase rule compliance, and value assessment before any task can be marked complete. Use when: Any teammate is about to mark a task complete or send a Seal. Keywords: self-review, inner-flame

Use when summoning Rune agents, when encountering "agent not found" errors, when selecting which review agents to use, or when checking agent capabilities and tools. Quick reference for all 116 agents across 8 categories (74 core in agents/ — investigation, meta-qa, qa, research, review, utility, work + 42 extended in registry/ — investigation, review, testing, utility, work). Plus 13 shared resou

Researches the user's market, competitors, and competitive positioning to build a complete ICP profile. Shows findings for user approval before proceeding. Triggers: /profile, "research my market", "who are my competitors". Reads: ./gtm/company.md, ./gtm/icp.md. Writes: updates ./gtm/icp.md with competitive positioning. Standalone: yes (asks for domain if company.md missing).

Melhora sistematicamente o código através de ciclos estruturados de análise, mutação e avaliação, adaptado de ALMA. É útil para iterar na qualidade do código, otimizar implementações e depurar problemas persistentes, substituindo o tentar e corrigir ad-hoc por reflexão disciplinada e rastreamento de variantes.

Build multiple AI agents that work together. Use when you need a supervisor agent that delegates to specialists, agent handoff, parallel research agents, support escalation (L1 to L2), content pipeline (writer + editor + fact-checker), or any multi-agent system. Also used for CrewAI alternative, AutoGen alternative, LangGraph multi-agent, agents that talk to each other, specialist agents with a su

用於廣泛 .NET 工作的核心路由技能。此技能將偵測本機安裝的 .NET SDK 版本（要求 .NET 6+），並根據使用者的問題，將任務引導或準備載入其他合適的子技能（例如 Minimal APIs, MVC, Web API, EF Core）。

Recursive Language Model (dspy.RLM) that explores large contexts via a sandboxed Python REPL -- the LM writes code, queries sub-LMs, and iterates until it produces a final answer. Use when your input is too large for the context window, the model needs to explore data iteratively, you need recursive self-refinement with code execution, or you have research-style tasks requiring programmatic invest

Entry point for the Signal Prospecting Kit. Deep onboarding: researches the user's company from their domain, captures ICP, stack, and voice. Routes to /profile for market research. Triggers: /start, first run, "help me set up". Reads: ./gtm/ (all files). Writes: ./gtm/company.md, ./gtm/icp.md, ./gtm/voice.md. Standalone: yes.

Auditoria abrangente de SEO para e-commerce, cobrindo páginas de produtos, coleções, SEO técnico, análise de arquivos de log e pesquisa de concorrentes. Ideal para solicitações de auditoria de SEO, revisão de e-commerce, otimização de páginas ou melhoria de rankings orgânicos.

Um armazenamento persistente com escopo de projeto para pesquisa aprofundada em tópicos extensos, ideal para questões substantivas como comparar bibliotecas ou avaliar ferramentas. Não deve ser usado para notas de plano, fatos pequenos, decisões de nível de código ou ideias.

Pesquisa aprofundada assíncrona via API Gemini Interactions (sem dependência do Gemini CLI). Consultas RAG baseadas em arquivos locais (--context), pré-visualização de custos (--dry-run), saída JSON estruturada e polling adaptativo. Habilidade universal para mais de 30 agentes de IA, incluindo Claude Code, Amp, Codex e Gemini CLI.