Install any skill in seconds. Free to start, no credit card required.
Get Started Free →huangwb8/research-topic-extractor
当用户明确要求"从文件/图片/网页/描述中提取综述主题"、"生成主题+关键词+核心问题结构化输出",或要求使用旧名 get-review-theme skill 时使用。支持文件(PDF/Word/Markdown/Tex)、文件夹、图片、自然语言描述、网页 URL 等多种输入源,自动识别输入类型并提取内容,生成可直接用于 research-literature-review 及其他文献综述技能的结构化输出。
Passed 11 of 19 test cases with the skill, and 2 of 19 without it.
and 9 more in the full report
10 fixed3 passed either way10 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Extract the review topic parameters in JSON format from my research summary at `./nonexistent_drafts/robot_learning.pdf`.
| Checked | Without skill | With skill |
|---|---|---|
| Response notifies user that the file at ./nonexistent_drafts/robot_learning.pdf was not found. | Missed | Passed |
| Response prompts user to paste text directly. | Passed | Passed |
The instructions your model reads when the skill loads.
research-literature-review 或其他文献综述工作流。get-review-theme 的 prompt 触发;系统级旧目录由安装器清理。必需:
{输入源}:文件路径、URL、文件夹路径、图片路径,或直接文本描述可选:
{输出格式}:text / yaml / json,默认 text按用户请求和配置文件提供必要输入;缺失信息应明确列出并停止依赖该输入的步骤。
bensz-collect-bugs 按规范记录到 ~/.bensz-skills/bugs/,严禁直接修改用户本地 Claude Code / Codex 中已安装的 skill 源码。gh 与 bensz-collect-bugs,仅上传新增 bug 到 huangwb8/bensz-bugs;不要 pull / clone 整个 bug 仓库。test cases passed, vs 2 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.