Advanced Evaluation
Sets up LLM-as-judge scoring, pairwise comparisons, and bias-aware eval rubrics.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 11, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · be8b44d
Verbatim install worked cleanly: single self-contained SKILL.md with valid frontmatter, no external deps or API keys. In the A/B output test (pairwise judging with position-swap bias mitigation) the skill arm followed the documented protocol correctly, but the base arm without the skill produced an equally rigorous, equally correct result — the skill's guidance is sound but added no measurable lift on this task. Trigger description is somewhat over-broad ('create evaluation rubrics', 'automated quality assessment' can false-fire on non-LLM contexts), and the doc cites unsourced reliability stats (e.g. '15-25% improvement').
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 3/5
- Output vs. baseline 5/10
- Docs & honesty 3/5
What Advanced Evaluation does
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.
How to install Advanced Evaluation
git clone https://github.com/sickn33/antigravity-awesome-skills
cd antigravity-awesome-skills
mkdir -p ~/.claude/skills
cp -r plugins/agentic-awesome-skills-claude/skills/advanced-evaluation ~/.claude/skills/advanced-evaluation
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Advanced Evaluation
-
/advanced-evaluationSets up LLM-as-judge scoring, pairwise comparisons, and bias-aware eval rubrics.
It also activates on plain-language prompts like these:
-
Implement LLM-as-judge to score these model outputs -
Create an evaluation rubric to compare model outputs -
Set up a pairwise comparison pipeline to reduce bias
Frequently asked questions
- Is the Advanced Evaluation skill free?
- Yes. The skill itself is free from sickn33/antigravity-awesome-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Advanced Evaluation work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 11, 2026. Verdict: Works with setup. Verbatim install worked cleanly: single self-contained SKILL.md with valid frontmatter, no external deps or API keys. In the A/B output test (pairwise judging with position-swap bias mitigation) the skill arm followed the documented protocol correctly, but the base arm without the skill produced an equally rigorous, equally correct result — the skill's guidance is sound but added no measurable lift on this task. Trigger description is somewhat over-broad ('create evaluation rubrics', 'automated quality assessment' can false-fire on non-LLM contexts), and the doc cites unsourced reliability stats (e.g. '15-25% improvement').
- What is the Advanced Evaluation SkillProof Score?
- 6.4/10 — installs cleanly 5/5, triggers reliably 3/5, output vs. baseline 5/10, docs & honesty 3/5.
- How do I install Advanced Evaluation?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Advanced Evaluation with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.