Pesquisa e Web

Deprecated name; the skill formerly here is now opinionated-research:interactive-research. Retained as a context-level notice because Claude Code now ships a built-in deep-research workflow that runs one-shot, non-interactive fan-out research (no conversation after the report). interactive-research instead runs a persistent agent team you can keep questioning once the report lands. Guidance for Cl

Esta skill é usada para acionar, testar ou executar manualmente os scripts de busca de emprego, incluindo e-mails diários ou remotos. Ela é ativada por frases como "executar trabalhos diários" ou "testar a busca remota".

Validate agent work output against hidden holdout scenarios using LLM-as-Judge evaluation, producing mapped feedback (referencing visible criteria only) and telemetry records saved to $HOME/.ai-first-kit/. Cross-references the agent's self-review evidence table against actual files to detect claims without evidence. Use when the user says 'validate holdouts', 'test gates against holdouts', 'run ho

Capture a FlowGoal contract as a project-local `.flow/goals/<id>.goal.yaml` file with outcome, acceptance criteria (with verification commands), specification elements (non-goals, failure modes, interface contracts), constraints, evaluator binding, continuation policy, and lifecycle frontmatter. Use when /flow:start passes the Spec Validation Gate, when /flow:goal create is invoked, or when /flow:

PM DeepResearch — product manager's deep competitive research skill (Layer 1 orchestration) over the Lapis MCP core. Produces decision-oriented, evidence-complete competitive reports.

Multi-locale ASO optimization. Per-locale keyword research, cultural adaptation, cross-localization strategy, CJK-specific considerations. Triggers on: "localization", "localize", "translation", "multi-locale", "international".

Análise de categorias de Mais Vendidos da Amazon para pesquisa e seleção de produtos de e-commerce. Ativa quando usuários analisam categorias da Amazon, encontram produtos de alto potencial, pesquisam concorrentes ou avaliam oportunidades de entrada no mercado.

Dual-model deep research with adversarial cross-audit. Claude and Codex each run their own deep-research skill independently on the same question, then each audits the OTHER's citations (claim-support: PASS/WEAK/FAIL → trust-score + verdict), and Codex synthesizes one trust-weighted final report with a disagreement ledger. All 5 notes (2 reports, 2 audits, 1 final) + an index land in a persistent

Um sistema de memória entre conversas que usa a metáfora de um "Palácio da Memória" (alas, salas, túneis). Ele oferece à IA contexto persistente entre sessões, armazenando notas de pesquisa, decisões e descobertas em uma hierarquia de arquivos estruturada.

Keyword research and strategy for iOS and Android apps. Analyzes keyword difficulty, search volume, relevance, and optimal placement across metadata fields. Platform-aware indexing rules. Triggers on: "keywords", "keyword research", "keyword strategy", "search terms".

Automate Scrape Do tasks via Rube MCP (Composio). Always search tools first for current schemas.

Deep, multi-source, fact-checked research reports — entirely on the Claude subscription, no API keys. Plans a TOC + acceptance criteria, fans out parallel Task subagents that search the live web (native WebSearch/WebFetch), gap-fills weak sections, then synthesizes a long-form report with inline [n] citations and a Sources list whose every URL is DETERMINISTICALLY verified against URLs that actual