kangarookingkangarookingCommunity·15 Agent Skills Included

system-prompt-skills

Reusable system prompt design patterns for AI products

Distills 15 reusable system prompt design patterns from 165 top AI products like Claude, ChatGPT, Gemini, and Perplexity. Covers persona design, tool permissions, safety guardrails, memory, context management, search, citations, and injection defense. Eliminates guesswork when building chat assistants, coding agents, voice apps, or mobile AI features. Provides trigger conditions, execution steps, and boundary rules ready to plug into any agent framework.
npx skills add kangarooking/system-prompt-skills --all -g -y

All Skills in This Repository (15)

Pure Emerald Level Indicators
📦 In Repo
kangarookingkangarooking

memory-system

Design persistent AI memory architectures with CRUL lifecycle workflows.

Community
Advanced
📦 In Repo
kangarookingkangarooking

conversation-flow

Classify user intents and route conversations to specialized handlers.

Community
Advanced
📦 In Repo
kangarookingkangarooking

voice-optimization

Optimizes voice assistant prompts for concise, safe spoken outputs.

Community
Intermediate
📦 In Repo
kangarookingkangarooking

agent-delegation

Coordinate multi-agent delegation with lifecycle gates and context isolation.

Community
Advanced
📦 In Repo
kangarookingkangarooking

mobile-adaptation

Adapt system prompts for mobile environments with screen-aware formatting and native device integration.

Community
Intermediate
📦 In Repo
kangarookingkangarooking

output-formatting

Enforce platform-aware output length, style, and anti-slop rules.

Community
Advanced
📦 In Repo
kangarookingkangarooking

search-integration

Define search triggers, source priorities, and re-search rules for AI prompts.

Community
Advanced
📦 In Repo
kangarookingkangarooking

safety-guardrails

Design multi-layer safety guardrails with threat modeling and domain-specific rules.

Community
Advanced
📦 In Repo
kangarookingkangarooking

context-management

Manage token budgets and context windows for long-running AI conversations.

Community
Advanced
📦 In Repo
kangarookingkangarooking

personality-system

Layer switchable AI personas over a base identity with atomic switching.

Community
Advanced
📦 In Repo
kangarookingkangarooking

citation-system

Design and enforce inline citations and provenance tagging for factual content.

Community
Advanced
📦 In Repo
kangarookingkangarooking

tool-specification

Define tool interfaces, discovery, and orchestration patterns for AI agents.

Community
Advanced

Frequently Asked Questions

FAQPage Schema
How 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