plan-mode-arc-gsm8k-improvement

AEGISモデルのARC-Challenge評価改善とGSM8K健全性チェックのためのPlanモード。タイムアウト率・抽出失敗率分析、頑健な回答抽出、データ汚染検査、複数seed評価を実行。

by zapabob· Repository·data
Run in AgentAreaBrowse All Skills
Also installable via skills CLI
npx skills add zapabob/SO8T/data/plan-mode-arc-gsm8k-improvement

Source

Repo:github.com/zapabob/SO8T
Path:data/plan-mode-arc-gsm8k-improvement(main)

Related in data

electron-chromium-upgrade-electron-electron

Guide for performing Chromium version upgrades in the Electron project. Use when working on the roller/chromium/main branch to fix...

by electron
119,879

qiuzhi

指导Claude按照二哥的风格撰写求职类文章，包括公司薪资爆料、年终奖盘点、求职攻略、offer选择建议等内容。

by itwanger
16,619

awesome-ai-agents-illacloud-illa-builder

The chat will provide safety guides, equipment suggestions, reviews, and techniques, with context-driven summary and multimedia to...

by illacloud
12,356
plan-mode-arc-gsm8k-improvement | AgentArea Skills