The reputation layer for AI skills, tools & agents

EvalView by hidai25

#2730 of 3124 by hidai25
23 score

MCP server that lets coding agents test AI agents. Create YAML test cases, snapshot golden baselines, check for regressions, and generate visual reports all from inside Claude Code or any MCP-compatible tool. Works with LangGraph, CrewAI, OpenAI, Claude, Mistral, and any HTTP API.

Ranked #2730 out of 3124 indexed skills.

Signal Breakdown

Installs 0
Freshness GitHub not linked
Issue Health GitHub not linked
Stars GitHub not linked
Platform Breadth 1 platform
Contributors GitHub not linked
Description Detailed

How to Improve

Platforms medium impact

Only 1 platform listed — publishing to more platforms improves your score

Badge

AgentRank score for EvalView by hidai25
[![AgentRank](https://agentrank-ai.com/api/badge/skill/glama-hidai25--eval-view)](https://agentrank-ai.com/skill/glama-hidai25--eval-view)
<a href="https://agentrank-ai.com/skill/glama-hidai25--eval-view"><img src="https://agentrank-ai.com/api/badge/skill/glama-hidai25--eval-view" alt="AgentRank"></a>

Supported Platforms

MCP