system-prompt-skills
Reusable system prompt design patterns for AI products
All Skills in This Repository (15)
Pure Emerald Level Indicatorsmemory-system
Design persistent AI memory architectures with CRUL lifecycle workflows.
conversation-flow
Classify user intents and route conversations to specialized handlers.
voice-optimization
Optimizes voice assistant prompts for concise, safe spoken outputs.
agent-delegation
Coordinate multi-agent delegation with lifecycle gates and context isolation.
mobile-adaptation
Adapt system prompts for mobile environments with screen-aware formatting and native device integration.
output-formatting
Enforce platform-aware output length, style, and anti-slop rules.
search-integration
Define search triggers, source priorities, and re-search rules for AI prompts.
safety-guardrails
Design multi-layer safety guardrails with threat modeling and domain-specific rules.
context-management
Manage token budgets and context windows for long-running AI conversations.
personality-system
Layer switchable AI personas over a base identity with atomic switching.
citation-system
Design and enforce inline citations and provenance tagging for factual content.
tool-specification
Define tool interfaces, discovery, and orchestration patterns for AI agents.
Frequently Asked Questions
FAQPage SchemaHow to install system-prompt-skills?▼
Run `npx skills add kangarooking/system-prompt-skills --all -g -y` in your terminal to install all 15 skills globally.
What problems do these system prompt skills solve?▼
They help you design stable system prompts covering identity, tools, safety, memory, context, search, citations, and output formatting without starting from scratch.
Are these leaked prompts from AI companies?▼
No. The original prompts were only used as source material; this repository keeps the transferable design methodology, not the raw prompt text.
Which skills should I combine to build an AI agent?▼
Combine tool-specification, conversation-flow, agent-delegation, and injection-defense for agents; add search-integration and citation-system for search or RAG products.
Do I need prompt engineering experience to use these skills?▼
No. Each skill includes clear trigger signals, step-by-step execution guidance, and boundary rules that your AI agent can apply directly.
Related Repositories in Software Engineering
View All in Software Engineering→openclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core