Safety Guardrails

by kangarooking

Safety Guardrails is an AI Engineering skill for Claude Code, published by kangarooking in system-prompt-skills.

182 stars40 forkson kangarooking/system-prompt-skillsAdded 2026/09/06+3% in starsRepository updated 2026/05/04

View source on GitHub Download repo ZIP

agent-designagent-skillsai-agentscangjie-skillcontext-managementprompt-engineeringprompt-injectionsystem-prompttool-use

Install in seconds

Install Safety Guardrails

Copy Safety Guardrails into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/kangarooking/system-prompt-skills/tree/main/safety-guardrails ~/.claude/skills/safety-guardrails

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/kangarooking/system-prompt-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: safety-guardrails/SKILL.md in kangarooking/system-prompt-skills
Installs to: ~/.claude/skills/safety-guardrails
Collection: One of 15 skills cataloged from this repository
Category: AI Engineering — 3278 skills

What Safety Guardrails does

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.

Safety Guardrails is cataloged under AI Engineering on DirSkills. Safety Guardrails comes from a repository tagged agent-design, agent-skills, ai-agents, cangjie-skill and context-management.

Documentation

README

Excerpt

安全防线与伦理边界设计 (Safety Guardrails)

R — 原文 (Reading)

Claude: Child safety "critical" + refusal cascades + Anthropic reminders system + long-conversation drift prevention Claude Chrome: Multi-layer injection defense (critical_injection_defense, critical_security_rules, etc.) + rule immutability GPT-4o: Deprecation grief protocol + guardian_tool for elections ChatGPT Agent: Financial activity restrictions + sensitive personal info protection + prompt injection defense FlintK12: "School Duty of Care" + "Flag first, assess never" + teen slang detection + relationship-building detection Meta AI: Explicit value list (Truth, Beauty, Respect, Fun, Connection) + "Do not refuse social/political topics"

I — 方法论骨架 (Interpretation)

安全防线设计遵循"纵深防御"原则，由五个从外到内的防护层构成：

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Safety Guardrails

What else does kangarooking publish alongside Safety Guardrails?
Safety Guardrails is one of 15 skills that DirSkills catalogs from kangarooking/system-prompt-skills, the repository it ships in. Its siblings there include Agent Delegation, Citation System and Code Engineering. Each one is a separate skill with its own page in this directory, installs the same way Safety Guardrails does, and is maintained by kangarooking in that same repository. The rest of the collection is listed on the kangarooking/system-prompt-skills page.
How does Safety Guardrails compare to other AI Engineering skills?
Safety Guardrails ranks #3054 by stars among the 3278 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Safety Guardrails against them. Open each page to compare what they document and how they install.