Browse skills

Official github skill covering AI, code review for building AI and machine learning applications.

Analyzes AI outputs for bias, fairness, safety, and adherence to guidelines; generates detailed audit reports.

This skill builds custom AI safety filters to proactively manage responses and mitigate potential risks, ensuring more reliable outputs.

Configure Claude's safety settings (e.g., refusal rates, content filters) to align with your organization’s risk tolerance.

This skill defends against prompt injection attacks by analyzing and neutralizing malicious instructions within user prompts, ensuring AI safety & reliability.

Assess LLM outputs based on provided criteria like accuracy, relevance, and safety, generating detailed feedback reports.

Analyzes AI outputs for potential harms like bias, toxicity, or misinformation, flagging risks for review.

The Guardrails Reviewer analyzes your AI model’s outputs against predefined guardrails, ensuring safety and compliance – crucial for responsible AI deployment.

The Guardrails Writer generates effective AI safety prompts and guidelines, ensuring your models produce helpful and harmless outputs.

Analyzes AI systems for potential safety risks, biases, and ethical concerns using jmsktm's proprietary methodology.

Verifies text aligns with Anthropic's safety guidelines, flagging potential policy violations for review and mitigation.

Evaluates if a language model’s responses stay within defined boundaries, ensuring safety and relevance for reliable outputs.

Ensures AI outputs align with Anthropic's safety principles and legal requirements, minimizing risk and promoting responsible use.

Together Evaluations assesses large language model outputs for quality, safety, and alignment, streamlining evaluation workflows & improving LLM performance.