Explorar skills

Analisa as mudanças de sessão para detectar habilidades de validação ausentes. Explora dinamicamente as habilidades existentes, cria novas ou atualiza as existentes, e então gerencia o CLAUDE.md do projeto.

Automate Modelry tasks via Rube MCP (Composio). Always search tools first for current schemas.

This skill should be used when designing CrewAI crews with YAML-first architecture. Use it to create crews, configure agents and tasks, select processes, and generate validation-ready outputs.

Purple-team operations — structured detection validation against MITRE ATT&CK through planned emulation, measured coverage gaps, joint red+blue debrief, and tracked closure via D3FEND mapping. Bridge between the pentest bundle and the blue bundle.

Automate API Labz tasks via Rube MCP (Composio). Always search tools first for current schemas.

Use at the start of an orchestrator session to understand project state and find available work

Automate Moxie tasks via Rube MCP (Composio). Always search tools first for current schemas.

TDD-first spec management for AI coding workflows. Use this skill when the user explicitly mentions specs, forging, or structured planning: says "forge", "forge a spec", "write a spec for X", "create a spec", "plan X as a spec", "resume", "what was I working on", "spec list/status/pause/switch/activate", "implement the spec", "implement phase N", "implement all phases", "red green refactor", "run

分析职位描述并生成定制简历，突出相关经验、技能和成就，最大化面试机会

Step-by-step orchestrator for migrating a PrestaShop Legacy admin page to Symfony/CQRS. Covers the full lifecycle from audit to GA. Trigger: "migrate the Xxx admin page", "create CQRS for Xxx", "add a Symfony form for Xxx", "migrate AdminXxxController".

Automate Ipdata co tasks via Rube MCP (Composio). Always search tools first for current schemas.

Resolução competitiva de problemas multiagente: Esta skill gera múltiplos subagentes Claude Code em worktrees git paralelos para resolver independentemente a mesma tarefa de programação. As soluções são polinizadas cruzadamente através de rodadas de melhoria onde cada agente vê e aprende com os diffs dos outros, e a melhor solução é selecionada por votação de consenso Borda com juízes independentes.