kangarooking/system-prompt-skills

Agent Delegation describes how to split work across specialized sub-agents with isolated context, briefing-based handoffs, and validation gates. Use it when designing multi-agent systems, task lifecycles, or cross-tool coordination; not for single-agent routing.

Citation System defines inline citation formats and source-tracking rules for answers that need traceable evidence. Use it for document Q&A, RAG, code references, and other outputs where users must verify where information came from.

Code Engineering defines system-prompt rules for coding agents that edit files, manage Git workflows, and verify changes. Use it for autonomous or guided code modification tasks, not for pure code Q&A or infrastructure setup.

Context Management helps design token budgets, compression strategies, lazy loading, and persistent memory for long-running AI assistants and multi-session systems. Use it when conversation history, large files, or user preferences need to stay usable without overflowing the context window.

Conversation Flow defines how an AI classifies user intent, routes requests into task-specific paths, and chooses when to ask clarifying questions versus proceed autonomously. Use it for multi-step assistants and agents that need structured dialogue management.

Injection Defense helps design system prompts that resist prompt injection, jailbreaks, social engineering, and trust-boundary breaks. Use it for agents or chatbots that process external content like documents, web pages, email, or memory.

Memory System designs how an AI stores, retrieves, applies, and updates user and project memories across sessions. Use it when building personalization, handling sensitive memories, or deciding when memory should be applied silently.

Mobile Adaptation shapes system prompts for phone and tablet screens. It sets length limits, scan-friendly formatting, and answer-first structure, and it can account for mobile-native tools like calendar, reminders, and location.

Output Formatting defines response length, structure, and style rules for AI outputs. Use it when a prompt needs to adapt to a platform, avoid canned phrasing, or control density and tone.

Persona Design defines an AI product’s identity, role statement, capability boundaries, and relationship framing. Use it when writing a system prompt, splitting one model into different roles, or clarifying how the AI should introduce itself.

Personality System designs a base persona with switchable personality overlays and shared meta-rules. Use it when a product needs selectable tones, consistent personality switching, or protection against personality leaking into user-written text.

Safety Guardrails helps design layered safety boundaries for AI systems, including refusal policies, prompt injection defenses, and domain-specific rules. Use it when an AI handles sensitive topics or needs clear ethical limits.

Search Integration defines when an AI should search, what sources to search, and how to handle results. Use it for real-time knowledge retrieval in chatbots, research assistants, and enterprise Q&A; it is not for offline or purely internal knowledge tasks.

Tool Specification defines how to design AI tool interfaces, discovery, permissions, and parallel execution. Use it when an agent needs to call external APIs, manage many tools, or delegate work to sub-agents.

Voice Optimization helps adapt system prompts for spoken interactions like voice assistants, voice search, and phone agents. It keeps answers concise, conversational, and safe for audio use, with rules for supported languages and no preambles.