with one click
srt-to-markdown
将 SRT 字幕文件整理为结构完整、行文通顺的 Markdown 文档。适用于讲座、直播、访谈等口语转录的结构化整理。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
将 SRT 字幕文件整理为结构完整、行文通顺的 Markdown 文档。适用于讲座、直播、访谈等口语转录的结构化整理。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Evaluate agent-generated code against ground truth diff and handwritten file list. Prefer reading GT inputs directly from base_repo via experiment metadata. Trigger on "/diff-eval-local", "evaluate diff", "eval experiment".
Full dev workflow - worktree setup, commit, push, PR, and post-merge cleanup. Use when starting feature work, committing, opening PRs, or cleaning up after merge.
Use when downloading models from Hugging Face, especially large models (LLM, diffusion, VLM) that fail with timeouts or connection drops. Trigger on "download model", "hf download", "pull model from Hugging Face", or when hf download crashes with httpx.ReadTimeout / RemoteProtocolError.
Evaluate agent-generated code changes against a human-approved PR with deterministic file coverage and function-level coverage analysis. Extracts function/symbol changes from diff hunk headers and compares at granular level. Use when evaluating agent code generation quality, benchmarking AI coding tools, or comparing generated patches against human-approved pull requests. Trigger on "/diff-eval-func", "evaluate diff with function coverage", "function-level diff eval".
从论文中提取图片,优先从arXiv源码包获取真正的论文图
深度分析单篇论文,生成详细笔记和评估,图文并茂
| name | srt-to-markdown |
| description | 将 SRT 字幕文件整理为结构完整、行文通顺的 Markdown 文档。适用于讲座、直播、访谈等口语转录的结构化整理。 |
将一个或多个 SRT(SubRip)字幕文件转化为结构完整、逻辑通顺、适合阅读或出版的 Markdown 文档。
用户提供:
.srt 文件的路径读取 SRT 文件,跳过:
HH:MM:SS,mmm --> HH:MM:SS,mmm)清洗零宽字符:移除 ASR 平台嵌入的隐形水印
[\u200b\u200c\u200d\ufeff\u2060]合并连续文本行为段落:
这是最关键的一步。ASR 转录的原始文本通常:
逐段阅读,根据语义和语气补充完整标点:
ASR 对专业术语的识别错误率极高。常见模式:
| 错误类型 | 示例 |
|---|---|
| 同音替换 | "康复周期" → "康波周期"、"美丽时钟" → "美林时钟" |
| 人名误识 | "包贝尔" → "鲍威尔"、"吴京" → "吴清" |
| 机构名 | "道具部门" → "政府效率部(DOGE)" |
| 术语误读 | "心智生产力" → "新质生产力" |
| 音译名 | "布伦森森林" → "布雷顿森林" |
修正策略:
[?] 供人工复查| 口语特征 | 处理方式 |
|---|---|
| 语气词("嗯"、"啊"、"对吧") | 删除 |
| 重复表述 | 保留表意最清晰的一次 |
| 口头禅("就是说"、"然后呢") | 删除或替换为书面连接词 |
| 散乱长句 | 拆分为短句,调整语序 |
| 口语化词汇 | 替换("搞" → "推行"、"弄" → "实施") |
注意:保留讲者的分析风格和个人特色,不要过度书面化。比喻、类比、生动表达应当保留。
阅读清洗后的全文,识别:
# 章标题(对应整个视频/讲座的主题)
> 章首引言(提炼全章最核心的一句话)
## 节标题(对应一个完整话题)
### 小节标题(对应话题下的子论点)
正文段落...
---
*来源:视频标题或原始文件名*
命名规范:
每章开头添加一段 blockquote 引言:
根据用户需求选择输出格式:
Markdown(默认):直接输出结构化 .md 文件
LaTeX:转换为 LaTeX 格式
# → \chapter{}## → \section{}### → \subsection{}\begin{quote}...\end{quote}\source{}(自定义命令)多文件合并:当多个 SRT 文件属于同一主题时
**主持人**:、**嘉宾A**:输入(SRT 原文,无标点):
1
00:00:01,000 --> 00:00:03,500
今天我们来聊一聊经济周期
2
00:00:03,500 --> 00:00:07,000
很多朋友问经济到底什么时候能变好
3
00:00:07,000 --> 00:00:11,500
要回答这个问题绕不开经济周期理论
输出(结构化 Markdown):
## 经济周期理论:分析的钥匙
很多朋友问:经济到底什么时候能变好?要回答这个问题,绕不开经济周期理论。