How do I install the Rank LLM Eval skill?

Run npx skillmds@latest add castorini/rank-llm-eval in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Rank LLM Eval safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Rank LLM Eval?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Rank LLM Eval free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Rank LLM Eval?

castorini (@castorini) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Rank LLM Eval by castorini — Agent Skill

Name: Rank LLM Eval
Author: castorini

Rank LLM Eval

Use when analyzing rank_llm evaluation outputs across runs or models. Covers aggregated trec_eval JSONL files, response-analysis metrics, retrieval-cache handoff files, and side-by-side comparison of stored evaluation artifacts.

castorini 239d9f8 3 files · 6.4 KB Updated Sep 17, 2026

File contents

rank_llm Eval

Analyze and compare RankLLM evaluation outputs across models, prompt templates, or retrieval settings.

When to Use

After rank-llm evaluate
After rank-llm analyze
When comparing two rerank runs or model variants
When checking whether a retrieval-cache or rerank artifact is ready for downstream evaluation

What It Does

Aggregated Metric Comparison

Load two trec_eval_aggregated_results_<model>.jsonl files
Compare per-file metric values side by side
Report deltas for metrics such as ndcg_cut_10, map_cut_100, or recall-style scores

Response Analysis Interpretation

Read analyze summaries and error counts
Flag mixed valid and malformed outputs when partial_success appears
Separate response-format problems from ranking-quality problems

Retrieval Handoff Checks

Confirm that a run has the expected rerank JSONL or TREC artifacts before aggregation
Confirm that cached retrieval JSON exists when evaluation depends on precomputed retrieval results

Usage

Compare two evaluation outputs:

python3 .claude/skills/rank-llm-eval/scripts/compare.py \
  --run-a trec_eval_aggregated_results_a.jsonl \
  --run-b trec_eval_aggregated_results_b.jsonl

Or use the CLI directly:

rank-llm evaluate --model-name castorini/rank_zephyr_7b_v1_full
rank-llm analyze --files invocations.json --verbose
rank-llm view rerank_results.jsonl

Reference Files

references/metrics.md - Metric names, output files, and interpretation guidance

Comparison Script

See scripts/compare.py for the side-by-side comparison tool.

Gotchas

evaluate aggregates stored rerank outputs. It does not execute reranking by itself.
Comparing two aggregated evaluation files only makes sense when both runs cover the same datasets or TREC output files.
analyze focuses on response and parsing quality, not ranking quality. A clean analyze result does not imply good ndcg_cut_10.
partial_success means some responses were usable and some were malformed. Treat that as a data-quality issue before reading too much into the metric deltas.

---name: rank-llm-evaldescription: Use when analyzing rank_llm evaluation outputs across runs or models. Covers aggregated trec_eval JSONL files, response-analysis metrics, retrieval-cache handoff files, and side-by-side comparison of stored evaluation artifacts.---# rank_llm EvalAnalyze and compare RankLLM evaluation outputs across models, prompt templates, or retrieval settings.## When to Use- After `rank-llm evaluate`- After `rank-llm analyze`- When comparing two rerank runs or model variants- When checking whether a retrieval-cache or rerank artifact is ready for downstream evaluation## What It Does### Aggregated Metric Comparison- Load two `trec_eval_aggregated_results_<model>.jsonl` files- Compare per-file metric values side by side- Report deltas for metrics such as `ndcg_cut_10`, `map_cut_100`, or recall-style scores### Response Analysis Interpretation- Read `analyze` summaries and error counts- Flag mixed valid and malformed outputs when `partial_success` appears- Separate response-format problems from ranking-quality problems### Retrieval Handoff Checks- Confirm that a run has the expected rerank JSONL or TREC artifacts before aggregation- Confirm that cached retrieval JSON exists when evaluation depends on precomputed retrieval results## UsageCompare two evaluation outputs:```bashpython3 .claude/skills/rank-llm-eval/scripts/compare.py \ --run-a trec_eval_aggregated_results_a.jsonl \ --run-b trec_eval_aggregated_results_b.jsonl```Or use the CLI directly:```bashrank-llm evaluate --model-name castorini/rank_zephyr_7b_v1_fullrank-llm analyze --files invocations.json --verboserank-llm view rerank_results.jsonl```## Reference Files- `references/metrics.md` - Metric names, output files, and interpretation guidance## Comparison ScriptSee `scripts/compare.py` for the side-by-side comparison tool.## Gotchas- `evaluate` aggregates stored rerank outputs. It does not execute reranking by itself.- Comparing two aggregated evaluation files only makes sense when both runs cover the same datasets or TREC output files.- `analyze` focuses on response and parsing quality, not ranking quality. A clean `analyze` result does not imply good `ndcg_cut_10`.- `partial_success` means some responses were usable and some were malformed. Treat that as a data-quality issue before reading too much into the metric deltas.

Frequently asked questions