Explorar skills

全自动 Bug 修复（定位→复现→修复→测试→文档）

Esta skill auxilia usuários que trabalham com a codebase OpenMythos, uma implementação PyTorch da arquitetura Recurrent-Depth Transformer (RDT) hipotetizada por Kye Gomez. Ela é ativada por sinais como `main.py` em `open_mythos/`, imports específicos ou helpers de variantes.

Auto-activate for Controller classes, Router, route decorators, @get/@post/@put/@patch/@delete, route_handler, path params, app/domain modules, or DomainPlugin layout. Use when designing Litestar routes, handlers, Controller grouping, Router composition, or domain folders. Not for non-Litestar routing or frontend routers.

Release preparation for Stages I-L of the VibeFlow docs-first workflow

Run a comprehensive Go-to-Market and launch readiness review for a project phase. Combines marketing content audit, code quality review, performance audit, accessibility audit, infrastructure readiness, and business review with council evaluation. Use before phase launches or when GTM review issues are ready.

This skill provides the Gen Alpha/brainrot output style transformation rules and vocabulary. It is automatically loaded by the SessionStart hook to transform all Claude responses into Gen Alpha internet slang. Contains comprehensive glossary, transformation patterns, and examples.

Creates and manages persistent markdown planning files (task_plan.md, findings.md, progress.md) for complex task execution. Use when starting multi-step tasks, research projects, or any task requiring >5 tool calls. Solves the EXECUTION problem - staying focused during long-running tasks.

Framework for navigating AI safety, ethics, and capability trade-off discussions. Covers responsible scaling, content policy, bias, privacy, dual-use, and alignment.

Initialize the design system or create new UI components with accessibility, Tailwind/shadcn integration, and documentation. Use when setting up the initial design system, adding component categories, or creating complex UI components that need design review.

发布工作流（跑测试 → bump VERSION → 更 CHANGELOG → tag → 触发 CI/CD）

Esta skill avalia um esboço de artigo de pesquisa (arquivo .qmd) com base em critérios estruturados do guia de pesquisa empírica de Kosuke Imai. Ela analisa o resumo e o contorno das seções quanto à clareza da questão de pesquisa, contribuições, hipóteses, dados, resultados planejados, abordagem inferencial e verificações de robustez, detectando também artigos causais a partir do resumo.

Real-time competitive analysis of the AI market. Covers foundation models, products, pricing, moats, and strategic positioning across major AI labs and emerging players.