LLM Guardrails Spec

Specify the safety and reliability guardrails for an LLM feature before it ships. Use when asked to define LLM guardrails, add safety controls to an AI feature, prevent prompt injection or jailbreaks, or harden a chatbot/agent against misuse. Produces a guardrails spec — threats, input/output controls, refusal and escalation policy, logging, and a red-team test set — mapped to where each control runs.

Slipcast-dev Updated 1 repo stars
Claude Skills Collection banner

File contents

Slipcast-dev/claude-skills commit 50a7829747

Frequently asked questions

npx get-skill add slipcast-dev/llm-guardrails-spec