🛡️ Llm Evaluation
This skill enables automated LLM evaluation, regression and security testing with Promptfoo, integrating into CI/CD to improve prompt quality and safety.
npx playbooks add skill phrazzld/claude-config --skill llm-evaluation
About Llm Evaluation
This skill enables automated LLM evaluation, regression and security testing with Promptfoo, integrating into CI/CD to improve prompt quality and safety.
At 21 words, this compact prompt gives your agent specialized security expertise with structured patterns and output formats. Install via CLI or copy the prompt below.
Use Cases
- Auditing code for OWASP Top 10 vulnerabilities
- Implementing authentication and authorization patterns
- Reviewing API security, rate limiting, and input validation
- Hardening infrastructure and dependency security
Example Prompts
System Prompt (21 words)
This skill enables automated LLM evaluation, regression and security testing with Promptfoo, integrating into CI/CD to improve prompt quality and safety.
Frequently Asked Questions
What is Llm Evaluation?
Llm Evaluation is a free security skill for AI coding agents. This skill enables automated LLM evaluation, regression and security testing with Promptfoo, integrating into CI/CD to improve prompt quality and safety.. It provides a specialized system prompt that configures your agent with security expertise.
How do I use Llm Evaluation with Claude Code?
Run npx playbooks add skill phrazzld/claude-config --skill llm-evaluation in your terminal to install Llm Evaluation into your Claude Code session. It works immediately after installation.
Which AI coding agents work with Llm Evaluation?
Llm Evaluation is compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any AI agent that supports custom system prompts or .cursorrules files.
Is Llm Evaluation free to use?
Yes, Llm Evaluation is completely free and open source. The full source is available on GitHub at https://github.com/phrazzld/claude-config/tree/main/skills/llm-evaluation. You only need a subscription to the AI agent you use it with.
