Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →cnfjlhj/timestamped-video-summary
Generate a detailed, professional video content summary from timestamped subtitles/transcripts (e.g., lines starting with 00:00 / 1:23:45). Enforce strict per-segment structure (timestamp range + bold segment title + 2-paragraph body: first-person creator summary + expert 【导师评注】 critique with uncertainty handling).
Passed 18 of 23 test cases with the skill, and 6 of 23 without it.
and 17 more in the full report
13 fixed5 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
请帮我整理这份带时间戳的视频转录文本。要求按逻辑划分为不同的时间段，每个段落包含时间范围、加粗的主题标题，正文第一段以讲者第一人称复述核心观点并突出重点，第二段以专家视角进行评价并指出需要进一步验证的地方。只需生成 Markdown 文字版本，不需要导出文件。
| Checked | Without skill | With skill |
|---|---|---|
| Uses the timestamp header prefix format 时间戳范围: [ | Missed | Passed |
| Places the bolded title on the line immediately following the timestamp range line | Missed | Passed |
| Starts the second paragraph strictly with the prefix 【导师评注】 without adding extra subheadings like 讲者观点 or 专家点评 | Missed | Passed |
The instructions your model reads when the skill loads.
将“带时间戳的字幕/转录”整理为严格结构的视频内容纪要，并在用户要求“落盘/导出/PDF”时，把纪要渲染成排版清晰的中文 PDF（默认不附带原始逐行字幕材料）。
*.md → 运行 scripts/validate_summary_md.py 校验 → 运行 scripts/render_pdf.py 生成 *.pdf。00:00 / 00:02 / 01:23 / 1:23:45 这样的时间戳行对字幕的每个逻辑段落，输出必须包含且仅包含以下三部分（按顺序）：
时间戳范围: [开始时间 - 结束时间]**标题**【导师评注】 开头；以顶尖专家口吻补充概念、指出漏洞/争议；若无法判断真伪，必须明确写出该点**“需要进一步验证”**，并给出具体验证思路/方法。禁止项（默认规则）：
【导师评注】。test cases passed, vs 6 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.