Explorar skills

DEVE SER USADO para qualquer tarefa envolvendo Ionic Framework ou Capacitor. OBRIGATÓRIO sempre que o código ou projeto do usuário envolver: componentes ion-* (ion-button, ion-content, ion-tabs, ion-modal, ion-grid, ion-page), @ionic/react, @ionic/angular, @ionic/vue, @capacitor/core, plugins do Capacitor (Camera, Preferences, Geolocation, Push Notifications, Filesystem, Haptics, StatusBar, SplashScreen), capacitor.config.ts

Plan and execute Git Trunk-Based Development workflows on a repository with main as trunk. Use whenever the user asks about branch strategy, branch naming, rebasing on main, merge conflicts during rebase, PR flow, merge strategy, safe history rewrite, or branch cleanup, even if they do not mention "trunk-based" explicitly. For commit message formatting and Conventional Commits wording, delegate to

10 product agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. PM toolkit (RICE), agile PO, product strategist (OKR), UX researcher, UI design system, competitive teardown, landing page generator, SaaS scaffolder, research summarizer. Python tools (stdlib-only).

Implement exactly ONE vertical slice of the active feature, then stop with evidence — TDD, doubt loop, frontend craft, Spec Drift Guard. Use when the user says "build the next slice", "implement slice N", "continue", "code this slice". Not for bug fixes, prototypes, refactors outside scope, or two slices in a row.

Execute a task with automated verification. Classifies the goal, builds the cheapest possible verifier (deterministic test, regex/command check, LLM judge, or a hybrid of these), runs the work, and iterates until the verifier passes or a hard cap is hit. Use when a task has a checkable success criterion and you want confidence the output actually meets it — e.g. "write a function that does X", "dr

When the user wants to design, launch, or optimize a referral or affiliate program. Use when they mention 'referral program,' 'affiliate program,' 'word of mouth,' 'refer a friend,' 'incentive program,' 'customer referrals,' 'brand ambassador,' 'partner program,' 'referral link,' or 'growth through referrals.' Covers program mechanics, incentive design, and optimization — not just the idea of refe

Analisa projetos identificando as 5 principais personas de usuários (técnicas a não-técnicas), revela lacunas e sintetiza o que construir a seguir, incluindo inovações que elevam o projeto a um novo nível. Use para determinar o que construir, entender as necessidades dos usuários ou identificar lacunas no projeto.

Scaffold, polish, and publish open-source projects with AI-first documentation, governance, and CI. Use when: Starting a new OSS package, polishing/publishing an existing repo, setting up AGENTS.md / CONTEXT.md / DECISIONS.md / ROADMAP.md, onboarding AI agents to a codebase, or creating standard community files (README, LICENSE, CONTRIBUTING, CHANGELOG, CI pipelines, issue templates). Outputs repo

Use para verificar se o conteúdo social de um usuário corresponde à voz do seu site. Avalia o desvio de voz entre o site e as publicações sociais, considerando autoridade, formalidade, temperatura, vocabulário e posicionamento.

Batch-compile every .tex file in a directory tree into .pdf, with caching. Use when the user wants to compile LaTeX files — for example "compile all slides in exp/ml/", "build the PDFs for this chapter", or after editing multiple .tex files.

Arquiteto de Bens Comuns da Informação para 0xagentprivacy V5, ativado para desafios de pluralidade de mídia, problemas de sinal vs ruído, jornalismo comunitário, arquitetura de mídias sociais federadas, estratégias de inoculação e sistemas de verificação de IA. Projeta uma verdade compartilhada através de canais que preservam a privacidade, alcançando a todos de forma diferente enquanto fala a mesma verdade.

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom mode