Use when the user wants to iterate on a viral-article scoring system itself, calibrate or improve a scoring prompt against labeled samples, or run batch scoring experiments on a fixed article set. Best for prompt-only scoring research where the evaluator scripts stay fixed and only the scoring rubric/prompt is meant to evolve.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-writing-skills:score-optimizerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
这个 skill 只负责一件事:优化文章评分系统本身。
这个 skill 只负责一件事:优化文章评分系统本身。
它适合做的是:
它不负责:
适用场景:
不适用场景:
后者应改用 article-optimizer。
开始前先读:
需要看实现时再读:
样本文集位置(用户自己提供,本 skill 不带样本):
assets/articles/samples/ —— 把你自己标注过的 .md 文章放进来,然后 cp labels.example.json labels.json 填上你的评分。详见 assets/articles/samples/README.mdreferences/score_program.md,按它的实验约束执行。references/score_prompt.md,不要动评估脚本。composite_score、mae、spearman、classification。在 skill 根目录执行:
python3 scripts/run_scoring.py > scoring.log 2>&1
python3 scripts/evaluate.py > eval.log 2>&1
grep "^composite_score:\|^mae:\|^spearman:\|^classification:" eval.log
如果需要图表:
python3 scripts/generate_score_chart.py
scripts/evaluate.pyscripts/run_scoring.pynpx claudepluginhub xiaomoboy/claude-writing-skills --plugin claude-writing-skillsCreates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.