fast-analysis

Analyze exported game files to assess gameplay, model decisions, and likely bugs.

64|8|Updated Oct 24, 2025

Search Tags:#triage #llm-evaluation #magebench #fast-analysis #game-analysis #export-analysis

Ready to run

npx skills add https://github.com/GregorStocks/mage-bench --skill fast-analysis

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: fast-analysis
Source: https://github.com/GregorStocks/mage-bench/tree/main/.claude/skills/fast-analysis
Command: npx skills add https://github.com/GregorStocks/mage-bench --skill fast-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyze exported game files to assess gameplay, model decisions, and likely bugs without raw logs, enabling fast triage.

Core Features & Use Cases

Parallelized, script-driven analysis across multiple exported games.
Generates structured outputs (game_overview, game_narrative, llm_events, llm_reasoning) to surface decision quality, errors, and tool usage.
Unified workflow for triaging bugs and model behavior issues without digging through logs.

Quick Start

Run the fast-analysis workflow on an exported game file to generate a concise triage report.

Frequently Asked Questions about fast-analysis

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

FAQPage Schema

How do I triage game export files to find model decision bugs without raw logs?▼

Analyze game export files to assess gameplay and model decisions without raw logs. This workflow generates structured summaries covering llm_events and llm_reasoning, enabling fast triage and quick identification of bugs across exported games.

Can I batch analyze multiple exported games in parallel to speed up triage?▼

Batch analyze exported games using a parallelized, script-driven workflow to process multiple files simultaneously. This generates per-game json outputs containing game_overview and llm_events, enabling quick identification of issues across multiple game exports.

What structured outputs are generated when analyzing exported game files?▼

Analyzing exported game files produces structured outputs: game_overview, game_narrative, llm_events, and llm_reasoning. These compact summaries surface decision quality, errors, and tool usage, exported to per-game json files for quick triage.

What is the best way to evaluate LLM reasoning and events from game exports?▼

Evaluate LLM reasoning by running script-driven analysis on game exports to extract llm_reasoning and llm_events. This workflow surfaces decision quality, errors, and tool usage patterns without requiring access to the original raw logs.

Do I need raw server logs to assess gameplay and identify likely bugs?▼

No, raw server logs are not needed to assess gameplay and identify likely bugs. The fast-analysis workflow operates directly on exported game files to evaluate model decisions and surface errors using reusable analysis scripts.