trueskill-rank

Ranks text items by quality using TrueSkill-based scoring with swappable rubrics and JSON output.

15|1|Updated Feb 17, 2026

Search Tags:#scalability #llm #evaluation #rubric #ranking #trueskill

Ready to run

npx skills add https://github.com/buildoak/fieldwork-skills --skill trueskill-rank

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: trueskill-rank
Source: https://github.com/buildoak/fieldwork-skills/tree/main/skills/trueskill-rank
Command: npx skills add https://github.com/buildoak/fieldwork-skills --skill trueskill-rank

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires trueskill, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Domain-agnostic TrueSkill batch ranking via LLM-as-judge. Ranks any list of text items using overlapping subsets dispatched to Codex Spark workers. Swappable rubrics. Use when you need to rank, score, curate, or sort a collection by quality.

Core Features & Use Cases

TrueSkill-based ranking across batches and rubrics
LLM-as-judge for scalable, domain-agnostic evaluation
Supports batch and pairwise modes with deterministic prompts

Quick Start

Install the trueskill library, place your input items with id and text, then run the full pipeline to produce rankings.

Frequently Asked Questions about trueskill-rank

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I rank a large collection of text items by quality using LLM evaluation?▼

You can rank text items by quality using a TrueSkill-based scoring pipeline that dispatches overlapping subsets to LLM workers, outputting final rankings in JSON. It operates at scale by generating overlapping subsets for evaluation.

What is TrueSkill ranking and how does it work with an LLM-as-judge?▼

TrueSkill ranking is a scoring mechanism that uses LLM-as-judge to evaluate text items. It operates at scale by dispatching overlapping subsets to Codex Spark workers, supporting batch and pairwise modes with swappable rubrics.

Do I need Python and the trueskill library to run an LLM-based text ranking pipeline?▼

Yes, running an LLM-based text ranking pipeline requires Python 3.11+ and the trueskill library. You must install the dependency and prepare input items with id and text fields before executing the full pipeline.

Can I use custom rubrics for domain-agnostic text evaluation and sorting?▼

Yes, you can use custom rubrics for domain-agnostic text evaluation. The pipeline supports swappable rubrics, allowing you to define specific quality criteria for ranking your collection of text items.

What's the best way to scale LLM evaluation for ranking a large list of items?▼

The best way to scale LLM evaluation is using a TrueSkill pipeline that generates overlapping subsets and dispatches them to Codex Spark workers. This batch and pairwise approach supports scalable, deterministic quality ranking.

What format does the TrueSkill ranking pipeline output for downstream automation?▼

The TrueSkill ranking pipeline outputs rankings in JSON format. This structured output allows for seamless integration into downstream automation workflows after the LLM evaluates the text items.