blunder-backfill

Community

Backfill outdated blunder analyses in games.

AuthorGregorStocks
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Backfill outdated or missing blunder analyses for recent MageBench games to ensure complete playback insights and consistent evaluation records.

Core Features & Use Cases

  • Run the backfill script on the most recent N outdated games (default 10).
  • Identify games with blunderScriptVersion older than current or missing annotations.
  • Execute per-decision Sonnet 4.5 analysis on each identified game.
  • Produce a cost breakdown per game and highlight improvements.
  • Requires OPENROUTER_API_KEY in the environment.

Quick Start

Run the backfill script on the most recent outdated games using uv run python -m magebench.analysis.toolbox.backfill_annotations [N]

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: blunder-backfill
Download link: https://github.com/GregorStocks/mage-bench/archive/main.zip#blunder-backfill

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.