Explorar skills

Comprehensive guide for PyTorch Lightning - LightningModule, Trainer, distributed training, PyTorch 2.0 torch.compile integration, Lightning Fabric, and production best practices

Use após uma fase de implementação para autoavaliar limites de responsabilidade, necessidade, ramificações defensivas, nomenclatura, testes, escopo de iteração da documentação e problemas da mesma classe antes da entrega final.

SEO content strategy, writing, and auditing. Plans topic clusters, writes search-optimized articles, and audits existing pages. Use for blog posts, landing page copy, content calendars, keyword research, SEO audits, and content strategy planning. Use when the user says "SEO", "content plan", "write blog post", "optimize for search", "keyword research", "audit page", "content calendar", "write an a

Draft, refine, prune, split, or rewrite Contexts and Dictionaries for the Context-Anchored Specifications framework. Use this skill whenever the user (or a subagent you spawn) is asked to define a Context, draft an initial Dictionary from a Spec File, add or refine a term and its definition, prune the Dictionary at a recurring spec review, document Relationships between Contexts, or split a Contex

Помогает писать системные промпты для LLM. Используй когда нужно написать prompt, system prompt, системный промпт, инструкцию для модели.

Establish governance practices for responsible AI development including fairness, transparency, and accountability. Use this skill when a team building AI features needs a governance framework for responsible development.

Lightweight web search via DuckDuckGo with BM25 relevance ranking. Use when asked to search the web, look something up, find recent information, research a topic, or browse the internet. Trigger phrases: search the web, look up, find information about, google, browse the web, web search, find recent, what is the latest on.

Batch domain availability checker via whois.com with Playwright browser automation. Handles anti-bot/CAPTCHA challenges by bringing browser to foreground for manual verification. Supports any TLD. Use when (1) checking if domains are available for registration, (2) batch-checking multiple domain candidates, (3) verifying domain availability before purchase, or (4) exporting domain check results to

Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust signals, form optimization, and conversion rate potential. Use when user says "landing page", "post-click experience", "landing page audit", "conversion rate", or "landing page optimization".

好吃好玩在苏州 - 苏州出行与美食规划Agent。优先推荐公交线路（旅游专线、好行观光巴士）， 辅以地铁换乘方案，结合苏州地铁食堂等特色餐饮，为用户规划吃喝玩乐一体化行程。 输出包含可视化HTML行程页面（含高德地图导航链接）。 使用场景：用户说"苏州怎么玩"、"从XX到YY怎么走"、"苏州一日游攻略"、"苏州美食推荐"等。

Use when about to claim work is done / verified / working — empirical verification is required, not model-based confidence. Run the code, observe the output, check the file exists, verify the page renders, read the actual stack trace. Don't trust your model of the system; trust the system. Pairs with the verification-before-completion superpower by giving it a cultural handle that operator-side ha

Deep-dive research and analysis of external reference materials (YouTube videos, articles, GitHub repos, documentation, code sources) against the current project. Reads pulse-config.yaml for config. Reports save to {research_dir}/deep-dives/. ONLY trigger when the user explicitly asks to research, analyze, or compare a resource against their project — not just because they share a link. Trigger: "