Not on Product Hunt
Claude Skills
AI Agentssoon
Workflowssoon
Creators

Not on Product Hunt

1,496 curated Claude Skills. We rejected 2,904 so you don't have to.

Categories

DevelopmentMarketingSecurityIntegrationsOperationsLegal

Resources

Submit a SkillSearch SkillsCreatorsSitemapllms.txt

Legal

Privacy PolicyTerms of Service

© 2025 Not on Product Hunt. Not affiliated with Product Hunt.

Built for the Claude community

ai-agentsintermediate

Evaluation Harness Framework

Implements evaluation-driven development principles for Claude Code sessions with automated testing frameworks.

Install

/plugin install evaluation-harness-framework@affaan-m

Requires Claude Code CLI.

Use cases

AI engineers and developers use this to define pass/fail criteria before implementation, measure agent reliability via pass@k metrics, and catch regressions across model versions.

Reviews

No reviews yet. Be the first to review this skill.

Stats

Installs0
GitHub Stars112.0k
Forks14594
LicenseMIT
UpdatedMar 27, 2026

Creator

A

Affaan M

@affaan-m

View on GitHub