Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aifinlab/announcement-layout-parsing
用于公告结构拆分的公告版式解析原子 skill，适用于通用行业文档解析场景。
Passed 18 of 20 test cases with the skill, and 7 of 20 without it.
and 17 more in the full report
13 fixed7 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Parse the front page header of the announcement document at `/files/announcement_2024001.pdf`. Ensure stock identifiers and publishing venues are captured in JSON.
| Checked | Without skill | With skill |
|---|---|---|
| Stores the stock ticker symbol under the header key stock_code. | Passed | Passed |
| Stores the publishing organization under the header key publish_org. | Missed | Passed |
The instructions your model reads when the skill loads.
本 Skill 支持多种公告文档输入格式，核心数据来源包括：
说明：本 Skill 不包含文档采集功能，需要用户提供公告文档文件。建议文档格式规范，以便进行准确的版式解析。
本 Skill 提供全面的公告版式解析能力，涵盖多种解析功能：
test cases passed, vs 7 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.