Pesquisa e Web

Multi-agent planning workflow using Agent Teams. Combines brainstorm, research, validation, synthesis, shatter assessment, forge enrichment, and review into a single orchestrated pipeline with dependency-aware task scheduling.

Analisa ações de Taiwan usando TWSE OpenAPI, TPEX/MOPS, Yahoo Finance, pesquisa web/notícias e sinais de sentimento contrarian para produzir relatórios de pesquisa estruturados.

Guia especializado para desenvolver ASP.NET Core Web APIs (baseadas em Controller). Suporta padrões de desenvolvimento modernos do .NET 6 (LTS) ao .NET 10 (LTS), cobrindo design de controllers, Problem Details, tratamento global de exceções e versionamento de API.

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).

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.

Use when designing SEO strategy, conducting keyword research, auditing technical SEO issues (crawlability, indexability, Core Web Vitals, structured data), planning content strategy for organic search, analysing search performance data, evaluating competitor positioning, building link acquisition plans, advising on site architecture for search, handling international SEO or hreflang, diagnosing ra

Gerencia compras de supermercado no Willys.se, incluindo busca de produtos, navegação por categorias e gerenciamento do carrinho. Use para encontrar mantimentos, adicionar/remover itens ou visualizar o carrinho.

Use when asked for "deep research", "thorough analysis", "comprehensive report", "investigate", "due diligence", or when multiple sources are needed to answer complex questions. Produces well-sourced research reports through iterative refinement.

Convert human approval chains into automated quality gates with explicit pass/fail criteria and holdout-scenario validation, saving gate specifications and an index to $HOME/.ai-first-kit/. Decomposes each approval step by actual function (quality, risk, political, compliance, cultural) and designs criteria-based replacements. Use when the user says 'replace approvals', 'design quality gates', 'au

Evaluate a FlowGoal against its evidence ledger and update lifecycle status to one of {pass, incomplete, fail, needs_human_review, blocked} by running deterministic verification commands first, then (when stopHookEnforcement=evaluator-loop or explicit /flow:goal evaluate invocation) dispatching the goal-evaluator-judge agent for fuzzy rubric criteria. Use when /flow:goal evaluate is invoked, when

Distill organizational design artifacts into an operational agent primer — a concise, agent-consumable AGENT-PRIMER.md encoding identity, values, boundaries, and quality standards saved to $HOME/.ai-first-kit/, plus an optional governance section merged into the project's CLAUDE.md. Also supports a full artifact dump (ORG-DESIGN-DUMP) that concatenates all artifacts into a single reference documen

PRISM v2.1.1 é uma estrutura orquestrada por LLM para auditorias e pesquisas estruturadas, multi-sessão e multi-fornecedor. Ela é ativada quando usuários invocam a mecânica PRISM por nome ou construtos específicos como 'auditoria PRISM', 'Master file', 'Prompt Strategy', 'Vendor Triangulation' ou 'P1-P7'.