← Browse
evalup
its-magdy ★ 2
evalup is a Claude Code plugin that evaluates LLM chat and agent applications by analyzing their architecture, generating test datasets, and running layered scoring across routing, tool use, trajectory, and answer quality to pinpoint which prompts and tool descriptions need fixes. It uses Claude Code for judgment and profiling while keeping all scoring reproducible through stdlib-only Python scripts that can run in CI with statistical gates.
Install
> /plugin marketplace add its-magdy/evalup/tree/HEAD/evalup
> /plugin install evalup
Source: https://github.com/its-magdy/evalup/tree/HEAD/evalup
What it's made of
3 agents · 7 skills
- Commands
- 0
- Agents
- 3
- Skills
- 7
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (its-magdy).