Back to skills
SkillHub ClubAnalyze Data & AIFull StackData / AITesting

evaluation

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.

Packaged view

This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.

Stars
22
Hot score
88
Updated
March 20, 2026
Overall rating
C2.3
Composite score
2.3
Best-practice grade
A85.2

Install command

npx @skill-hub/cli install mjunaidca-mjs-agent-skills-evaluation

Repository

mjunaidca/mjs-agent-skills

Skill path: .claude/skills/evaluation

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.

Open repository

Best for

Primary workflow: Analyze Data & AI.

Technical facets: Full Stack, Data / AI, Testing.

Target audience: Development teams looking for install-ready agent workflows..

License: Unknown.

Original source

Catalog source: SkillHub Club.

Repository owner: mjunaidca.

This is still a mirrored public skill entry. Review the repository before installing into production workflows.

What it helps with

  • Install evaluation into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
  • Review https://github.com/mjunaidca/mjs-agent-skills before adding evaluation to shared team environments
  • Use evaluation for development workflows

Works across

Claude CodeCodex CLIGemini CLIOpenCode

Favorites: 0.

Sub-skills: 0.

Aggregator: No.

evaluation | SkillHub