How do I install the Rank LLM Verify skill?

Run npx skillmds@latest add castorini/rank-llm-verify 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 Verify 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 Verify?

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 Verify free to use?

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

Who published Rank LLM Verify?

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

Rank LLM Verify by castorini — Agent Skill

Name: Rank LLM Verify
Author: castorini

Rank LLM Verify

Use when validating rank_llm artifacts after rerank, retrieve-cache, or related CLI workflows. Checks JSONL integrity, TREC formatting, candidate shape, invocation-history structure, and duplicate query identifiers. Wraps rank-llm view plus custom assertions.

castorini Updated Sep 17, 2026

File contents

rank_llm Verify

Validates stored RankLLM artifacts for correctness and structural consistency.

When to Use

After rank-llm rerank
After rank-llm retrieve-cache
Before using rerank outputs for evaluate or analyze
When comparing artifacts across models or prompt templates

What It Checks

JSONL Integrity

Every line is valid JSON
No empty files
No truncated or malformed records

Request Input

Every record has query and candidates
Every record has at least one candidate
Candidate entries expose either doc or text

Rerank Output

Every record has query and candidates
Every candidate has docid, score, and doc
No duplicate query identifiers when qid values are present

Invocation History

Top-level file is a JSON list
Each record has an invocations_history list
Every invocation entry is object-shaped

TREC Output

Every non-empty line has 6 columns
Rank field is an integer
Score field is numeric

Usage

Run the verification script:

bash .claude/skills/rank-llm-verify/scripts/verify.sh <artifact-path> [artifact-type]

Supported artifact types:

request-input
rerank-output
invocations-history
trec-output

If no artifact type is provided, the script attempts to auto-detect it with rank-llm view.

Verification Script

See scripts/verify.sh for the runnable verification wrapper.

Gotchas

rank-llm validate rerank checks input contracts before execution. The verify script checks stored output artifacts after execution.
rank-llm view only detects supported artifact families. If a file is not one of those shapes, pass the artifact type manually or inspect the file directly.
A rerank JSONL file can be structurally valid and still be low quality. Use evaluate and analyze for score and response diagnostics.

---name: rank-llm-verifydescription: Use when validating rank_llm artifacts after rerank, retrieve-cache, or related CLI workflows. Checks JSONL integrity, TREC formatting, candidate shape, invocation-history structure, and duplicate query identifiers. Wraps rank-llm view plus custom assertions.---# rank_llm VerifyValidates stored RankLLM artifacts for correctness and structural consistency.## When to Use- After `rank-llm rerank`- After `rank-llm retrieve-cache`- Before using rerank outputs for `evaluate` or `analyze`- When comparing artifacts across models or prompt templates## What It Checks### JSONL Integrity- Every line is valid JSON- No empty files- No truncated or malformed records### Request Input- Every record has `query` and `candidates`- Every record has at least one candidate- Candidate entries expose either `doc` or `text`### Rerank Output- Every record has `query` and `candidates`- Every candidate has `docid`, `score`, and `doc`- No duplicate query identifiers when `qid` values are present### Invocation History- Top-level file is a JSON list- Each record has an `invocations_history` list- Every invocation entry is object-shaped### TREC Output- Every non-empty line has 6 columns- Rank field is an integer- Score field is numeric## UsageRun the verification script:```bashbash .claude/skills/rank-llm-verify/scripts/verify.sh <artifact-path> [artifact-type]```Supported artifact types:- `request-input`- `rerank-output`- `invocations-history`- `trec-output`If no artifact type is provided, the script attempts to auto-detect it with `rank-llm view`.## Verification ScriptSee `scripts/verify.sh` for the runnable verification wrapper.## Gotchas- `rank-llm validate rerank` checks input contracts before execution. The verify script checks stored output artifacts after execution.- `rank-llm view` only detects supported artifact families. If a file is not one of those shapes, pass the artifact type manually or inspect the file directly.- A rerank JSONL file can be structurally valid and still be low quality. Use `evaluate` and `analyze` for score and response diagnostics.

Frequently asked questions