github-featured / juliusbrussee--caveman

发布

0 发布 46 Git 标签

RSS 订阅源
  • v1.1.0 6c3e2f6147
    比较

    Add benchmarks suite and update README

    frostbyte_neo 发布于 2026-04-05 17:25:25 +00:00 | 543 次提交 在此版本后已推送到 main

    Add a benchmarks directory with prompts.json, requirements.txt, results/.gitkeep, and run.py to measure Claude output token counts (normal vs caveman) using the Anthropic client. run.py supports dry-run, multiple trials, saving JSON results, computing stats, and optionally updating the README benchmark table; it reads the caveman SKILL.md for the system prompt. Also add .gitignore entries and expand README.md with badges, a Benchmarks section, sample table, and usage instructions.

    下载附件