Communityコーディング&開発github.com

adewale/skill-eval-harness

Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters

skill-eval-harness とは?

skill-eval-harness is a Claude Code agent skill that agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters.

対応~Claude Code~Codex CLI~Cursor
npx skills add adewale/skill-eval-harness

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

Demo Reviewer

A deliberately tiny skill that exists only to demonstrate the harness end to end (materialized ablations included). It has exactly two load-bearing pieces — a severity rule and a checklist reference — each targeted by one ablation below.

Severity rules

Label every finding with one of: Blocking, Minor, or Clean. State the label explicitly so the reader can triage at a glance. A change that ships without a test is at least Blocking.

Evidence

Back each finding with concrete evidence and follow the shared review checklist: see the review checklist.

関連スキル