Skill Claude CodeCodex
Use when generating analysis reports for WB-Bench-Office, WB-Bench-Web, or WB-Bench-Code from a single Harbor evaluation run artifact directory; route to the matching reference workflow.
315 12d ago A 44 tokens
315Stars on the repository
2Mods indexed here, across every type
12d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
Skill Claude CodeCodex
Use when a user wants to configure and launch a WorkBuddy Bench evaluation run from scratch, or is unsure how to set one up. Walks them interactively through environment setup, model config, .env credentials, job config, and launching the run, then hands off to wbbench-report-skills for metrics and trajectory analysis.
315 12d ago A 72 tokens