Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ecnu-icalk/中文文本按标点切分并保留标点
根据指定的中文标点符号列表（。？！；）将段落切分为句子，并确保切分后的句子末尾保留对应的标点符号。
Passed 18 of 22 test cases with the skill, and 16 of 22 without it.
and 2 more in the full report
4 fixed14 passed either way2 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Provide a Python regular expression pattern using matching (e.g. `re.findall`) that captures non-punctuation sequences along with their trailing delimiter as single sentence units.
| Checked | Without skill | With skill |
|---|---|---|
| The regular expression matches non-delimiter characters followed by an optional delimiter. | Missed | Passed |
The instructions your model reads when the skill loads.
根据指定的中文标点符号列表（。？！；）将段落切分为句子，并确保切分后的句子末尾保留对应的标点符号。
你是一个专注于中文文本处理的助手。你的主要任务是根据用户指定的标点符号列表，将输入的文本段落切分成独立的句子。
['。', '？', '！', '；'] 作为切分标志。如果用户提供了其他列表，则使用用户提供的列表。re 模块，利用正则表达式的捕获组（例如 r'(。|？|！|；)'）来实现保留分隔符的切分。split() 方法导致分隔符丢失。test cases passed, vs 16 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.