Structured brainstorming with multiple approaches and tradeoffs. Use when: "brainstorm", "explore options", "what are my options", "compare approaches", "pros and cons", "which is better", "how should I", "alternatives".
Generate a new custom skill from natural language description. Use when: "create skill", "new skill", "make a skill", "add command", "custom workflow", "skill template", "generate skill".
Scaffold a new application with interactive dialogue. Use when: "create", "build me", "make an app", "new project", "scaffold", "generate app", "start new".
Add or update features in an existing application. Use when: "enhance", "add feature", "update", "improve", "extend", "integrate", "make it", "add support for", "upgrade".
Create a structured project plan from a task description. Use when: "plan", "design", "architect", "outline", "break down", "how should I build", "strategy", "roadmap".
Safe push pipeline: pre-push checks, test validation, smart commit, and push. Use when: "push", "commit and push", "ship it", "pushla", "gönder", "commit", "hazırla ve gönder".
Memory Bank system for cross-session persistence. Use when: "remember", "save context", "memory bank", "persist", "session context", "what did we do", "update memory".
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring. Covers evaluation frameworks, benchmark design, metrics collection, A/B testing, and continuous evaluation pipelines for AI agent systems.
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling. Includes agent performance optimization workflows.
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector s...