/ai--llm-eval

/ai--llm-eval is a Claude Code skill in the AI & Agents section. Sets up an evaluation suite for an AI feature: test cases, rubrics, code-based checks, LLM-as-judge with bias controls and a CI gate.

Author's description

LLM output evals - rubrics, LLM-as-judge with bias controls, CI integration

How to ask for it

/ai--llm-eval create a rubric to score my assistant's answers
/ai--llm-eval set up an LLM-as-judge with bias controls
/ai--llm-eval wire model evals into our CI pipeline

Install

curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash

After installing with the script, type /ai--llm-eval. Using Cursor, Windsurf or Codex? Platform guides

Demo coming soon

/ai--llm-observabilityLLM call monitoring
Instruments your AI app with traces, token and cost tracking, quality signals, dashboards and alerts for every model call.
Built here
/ai--mcp-serverBuilding an MCP server
Builds a Model Context Protocol server that exposes your project's functions, APIs or data to clients like Claude Code, with transport, auth and tests.
Built here
/ai--multi-agentMulti-agent system design
Designs a system of several AI agents with an orchestration pattern, contracts between agents and failure handling, or advises a single agent instead.
Built here
/ai--prompt-engineerBetter AI prompts
Reviews and rewrites your system prompts, user prompts and tool definitions, then gives an A/B comparison of the original and improved versions.
Built here
/ai--rag-evalRAG pipeline evaluation
Builds a test harness that measures a RAG pipeline: a golden question set, retrieval metrics, groundedness checks and a regression gate.
Built here
/ai--semantic-cacheSemantic cache for LLM calls
Adds a cache in front of LLM calls so repeated or near-duplicate requests get a stored answer, and measures whether it helps without serving wrong ones.
Built here

How to ask for it

Install

More from this section