advanced-evaluation

github:muratcankoylan/Agent-Skills-for-Context-Engineering · first committed 2025-12-24 · source · badge

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

9 commits to this file on GitHub (newest first).

2026-06-29 · commit 8fc51c7 · chore: polish repo-wide production readiness
2026-06-29 · commit 9749e5c · fix: certify production Agent Skills compatibility across Cursor, Claude Code, and Codex (#96)
2026-05-19 · commit cbc2c97 · Harden full skill corpus for v2.3.0 release
2026-05-15 · commit 0d7595d · Release v2.2.0: researcher operating system + continuous loop
2026-03-18 · commit 9cd3073 · Fix review issues from post-rewrite audit of all 13 skills
2026-03-17 · commit c847b20 · Rewrite all 13 skills from textbook to hybrid instructional voice
2025-12-31 · commit cfe1870 · fix: remove version field from SKILL.md frontmatter
2025-12-31 · commit 0b2be51 · fix: restructure plugin to match official Claude Code format
2025-12-24 · commit 0b9a3b8 · Add LLM-as-Judge example and advanced-evaluation skill

Archived snapshots