Explorar skills

This skill should be used when the user asks to "calculate code mass", "measure code complexity with APP", "compare implementations using APP", "apply Absolute Priority Premise", "use mass calculations", or during TDD refactor phases when comparing alternative implementations. Based on Micah Martin's work.

/sdlc-studio [type] [action] - SDLC pipeline: requirements, specifications, code, testing. Run /sdlc-studio help for commands and /sdlc-studio status for next steps.

This skill should be used when the user asks to "design the architecture", "should I add a service layer", "add an abstraction", "introduce an interface", "separate concerns", "add a repository", "use hexagonal architecture", "add domain events", "split into layers", "add ports and adapters", "decouple this", "add an anti-corruption layer", "review package structure", "apply a design pattern", "wh

Team-specific Python conventions — credential management with dotenv, API client rules, LLM response parsing, TDD workflow, and testing patterns for data pipelines.

Invoke when the user asks about game UI, onboarding, HUD design, controller navigation, player feedback, usability testing, colorblind modes, or game-specific UX patterns. Triggers on: "UI", "UX", "onboarding", "HUD", "controller nav", "usability", "colorblind", "player feedback", "menu design". Do NOT invoke for deep accessibility audits (use game-accessibility-specialist) or art style (use game-

AI Agent 安全設計模式 — 基於 Claude Code 七層縱深防禦架構的逆向分析。Use when: 設計工具安全機制、實作命令過濾、建構權限模型、設計 sandbox。

AI Agent 成本工程 — 基於 Claude Code 的成本追蹤、prompt cache 最佳化、token 預算控制逆向分析。Use when: 優化 token 消耗、設計成本控制機制、分析 cache 效率、選擇模型配置。

Internal Auto-Harness planning skill for clarification intake. Use only inside the Planner subagent when it is producing .harness/intake.md and .harness/status.md.

Gerenciamento operacional do Proxmox VE via API REST para monitorar, controlar, provisionar e solucionar problemas de VMs e contêineres LXC com padrões comprovados.

Internal Auto-Harness evaluator skill for parallel sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.

Session handoff — compress current context into a structured prompt for seamless continuation in a new session. Use when: switching sessions, running low on context, or needing to hand off work.

Use when writing E2E tests with Playwright, setting up test infrastructure, debugging flaky browser tests, organizing project structure, or testing REST APIs. Invoke for browser automation, E2E tests, Page Object Model, test flakiness, visual testing, project scaffolding, folder layout, API testing, JSON schema validation.