deepeval

Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.

Install

If the official marketplace isn’t added yet, run

Add DeepEval evaluations to an AI app, with metrics like task completion, answer relevancy and hallucination
Evaluate full agent trajectories or single steps such as LLM calls, tool use and retrieval
Add tracing and build evaluation datasets
Produce Confident AI reports and run improvement loops

Run /plugin install deepeval@claude-plugins-official
Ask Claude to add DeepEval evals or tracing to your AI application
Use the results to have Claude adjust models, prompts or architecture, then evaluate again

DeepEval is open source; its metrics can use any LLM or NLP models that run locally on your machine.

Summarized by AI from the project docs; check the official docs before relying on it.

agent-sdk-devOfficial plugin · Development
Development kit for working with the Claude Agent SDK
clangd-lspOfficial plugin · Development
C/C++ language server (clangd) for code intelligence
code-modernizationOfficial plugin · Development
Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).
csharp-lspOfficial plugin · Development
C# language server for code intelligence
feature-devOfficial plugin · Development
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review