Explorar skills

GAN thinking mode — when delivering X, also run an adversarial pipe asking "is X fundamentally flawed as a concept? achievable with existing means via refactor? do bugs/vulns exist in X?". Two timings — pre-ship (in-vacuum, no real-world signal yet) and post-ship (with feedback signal). DELIBERATE REFRAME of the chengyu: the literal Chinese is "two pipes simultaneously" (parallel-cooperative), but

Structure a product dashboard that supports consistent, fast decision-making. Use this skill when a team needs to design or improve a product metrics dashboard.

Write well-formed user stories with clear acceptance criteria ready for development. Use this skill when a team needs to break down a feature or initiative into development-ready stories.

Esta skill é ativada quando o usuário expressa o desejo de aprender, entender ou dominar um tópico. É aplicável a qualquer área, como linguagens de programação, conceitos matemáticos, design patterns, ferramentas, frameworks, conhecimento de domínio e soft skills.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads accounts. Generates health score per platform and aggregate score. Use when user says "audit", "full ad check", "analyze my ads", "account health check", or "PPC audit".

Review a Pull Request or code change with rigor calibrated to whether it's leaf-node or core code. Use this skill whenever the user asks to review, audit, or evaluate code — phrases like "review this PR", "audit this code", "is this PR ready", "look at this branch", "review my changes", "what do you think of this", "code review please". Also trigger when reviewing AI-authored code specifically. Th

Claude Code plugin marketplace + playbook. 9 QA skills (review, security, architecture, performance, WordPress, Terraform) and 8 production guides from an AI-first consultancy.

Monthly devlog — longer, more reflective recap. ~1200-2000 words. Stitches together the month's work, names the pattern, draws a non-obvious lesson. Goes deeper than a weekly recap.

扫描项目的环境变量使用情况，检查安全性、完整性和一致性。 当用户提到"环境变量"、".env"、"配置安全"、"secrets"、 "API key 泄露"时使用。即使用户只是说"帮我检查一下配置 有没有问题"也应该触发。

Design a customer feedback survey that generates reliable, actionable data. Use this skill when a team needs to collect structured feedback at scale without the bias and noise that comes from poorly designed surveys.

Transforma lógica, caminhos de código, arquitetura ou resultados de verificação em uma apresentação de slides horizontal com estilo PPT de tema escuro, diagramas Mermaid e painéis coloridos, entregue como um único arquivo HTML. Use-o para explicar visualmente como algo funciona, ou quando slides, uma apresentação, diagramas ou fluxogramas são solicitados.