Explorar skills

Retrieve the most relevant SkillMesh cards from a registry and inject a Codex-ready context block before coding. Use when a task spans many domains and you want top-K routing instead of loading the full skill catalog.

Build AI that recommends products, articles, or content based on user preferences. Use when building product recommendations, you-might-also-like features, personalizing feeds, content discovery, ranking by user preference, suggesting related items, building a recommendation engine, collaborative filtering with LLMs, re-ranking search results by relevance, curating personalized playlists, next-bes

Verify and validate AI output before it reaches users. Use when you need guardrails, output validation, safety checks, content filtering, fact-checking AI responses, catching hallucinations, preventing bad outputs, or quality gates. Also used for - AI output looks right but is wrong, how to validate JSON from LLM, LLM returns invalid data, catch bad AI outputs before users see them, output quality

Tier-1 strategy-consultant analysis tailored for fintech / payments / lending / fraud problems — approval rates, fraud loss, delinquency, regulatory friction. Same five frameworks with fintech-aware MECE defaults, vocabulary, and root-cause priors.

Use when the task requires precise computation, math, or data manipulation — the LM writes Python code that executes in a sandbox instead of reasoning in natural language. Common scenarios - math word problems, data manipulation tasks, precise calculations the LLM gets wrong in natural language, statistical analysis, or any task where writing and executing code gives better results than reasoning

Isolate the 20% of inputs driving 80% of results, and explicitly name what you're deprioritizing. Outputs a blockquote (vital 20%) plus a list (deprioritized 80%). Use for ruthless prioritization, "what should we focus on", or step 4 of a strategic analysis.

Configura o motor de jogo e a versão do projeto. Fixa o motor em CLAUDE.md, detecta lacunas de conhecimento e preenche a documentação de referência do motor via WebSearch quando a versão está além dos dados de treinamento do LLM.

Sentiment & Reputation Guard — comprehensive brand reputation audit through search engines and LLM perception analysis. Analyzes online reviews, forums, news, and social media to score brand reputation 0-100 across four dimensions: Search Sentiment, SERP Control, Platform Presence, and LLM Sentiment. Auto-detects industry niche (crypto, iGaming, SaaS, agency, ecommerce, fintech, etc.) and tailors

Reduce your AI API bill. Use when AI costs are too high, API calls are too expensive, you want to use cheaper models, optimize token usage, reduce LLM spending, route easy questions to cheap models, or make your AI feature more cost-effective. Also used for GPT-4 costs too much for production, AI bill keeps growing, how to reduce OpenAI costs, optimize LLM token usage, smart model routing saves mo

Captura uma captura de tela da Visualização de Cena do Unity Editor e a retorna como uma imagem para inspeção visual direta pelo LLM.

Scaffold a new AI feature powered by DSPy. Use when adding AI to your app, starting a new AI project, building an AI-powered feature, setting up a DSPy program from scratch, or bootstrapping an LLM-powered backend. Also used for DSPy quickstart, DSPy hello world, first DSPy program, getting started with DSPy, new to AI development, add AI to existing Python app, AI feature from zero to working, sc

Converte URLs base de documentação, llms.txt ou llms-full.txt em Agent Skills instaláveis com o CLI txtskills. Use quando um usuário pedir para gerar, publicar e, opcionalmente, instalar uma nova skill a partir da documentação.