Communityコーディング&開発github.com

jeremylongshore/j-rig-skill-binary-eval

Binary-criteria evaluation harness for Claude skills with planned extension to plugins, agents, and MCP servers. Score every change yes/no across 7 layers — package integrity, trigger quality, functional quality, regression protection, baseline value, model variance, rollout safety. Never gradients.

j-rig-skill-binary-eval とは?

j-rig-skill-binary-eval is a Claude Code agent skill that binary-criteria evaluation harness for Claude skills with planned extension to plugins, agents, and MCP servers. Score every change yes/no across 7 layers — package integrity, trigger quality, functional quality, regression protection, baseline value, model variance, rollout safety. Never gradients.

対応Claude Code~Codex CLI~Cursor
npx skills add jeremylongshore/j-rig-skill-binary-eval

Installed? Explore more コーディング&開発 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

お気に入りのAIに質問する

このエージェントスキルを事前に読み込んだ状態で新しいチャットを開きます。

ドキュメント

j-rig-skill-binary-eval は何をしますか?

Binary-criteria evaluation harness for Claude skills with planned extension to plugins, agents, and MCP servers. Score every change yes/no across 7 layers — package integrity, trigger quality, functional quality, regression protection, baseline value, model variance, rollout safety. Never gradients.

関連スキル