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). Use when the user provides time-coded subtitles and asks for a规范化纪要/内容纪要/逐段总结, and optionally wants a clean PDF export (do NOT include the full raw transcript in the PDF unless explicitly requested).
Best use case
timestamped-video-summary is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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). Use when the user provides time-coded subtitles and asks for a规范化纪要/内容纪要/逐段总结, and optionally wants a clean PDF export (do NOT include the full raw transcript in the PDF unless explicitly requested).
Teams using timestamped-video-summary should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/timestamped-video-summary/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How timestamped-video-summary Compares
| Feature / Agent | timestamped-video-summary | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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). Use when the user provides time-coded subtitles and asks for a规范化纪要/内容纪要/逐段总结, and optionally wants a clean PDF export (do NOT include the full raw transcript in the PDF unless explicitly requested).
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
Best AI Skills for ChatGPT
Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.
SKILL.md Source
# Timestamped Video Summary ## Overview 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）。 ## Workflow Decision Tree 1) 只要文字纪要 - 直接按“输出规范”生成 Markdown 纪要即可（无需落盘）。 2) 需要落盘为 PDF（排版清楚） - 先生成符合规范的 Markdown 纪要 → 写入 `*.md` → 运行 `scripts/validate_summary_md.py` 校验 → 运行 `scripts/render_pdf.py` 生成 `*.pdf`。 ## Input Assumptions - 输入是**带时间戳**的字幕/转录文本，典型形态为： - `00:00` / `00:02` / `01:23` / `1:23:45` 这样的时间戳行 - 其下一行/多行是字幕内容 - 允许字幕存在口误、ASR 错别字、英文大小写/空格 token 等噪声；纪要要“忠实还原 + 专业归纳”，不要凭空补剧情。 ## Output Spec (Strict) 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）： 1) 时间戳范围 - 格式：`时间戳范围: [开始时间 - 结束时间]` 2) 段落核心标题 - 紧跟时间戳范围下一行 - 必须用 Markdown 加粗：`**标题**` - 标题要“精准概括该段落内容”，避免空泛（如“介绍一下”“继续讲”）。 3) 内容主体（两层，但不加额外小标题/前缀） - 第一段：核心内容总结（**必须**用博主第一人称：“我/我们”），忠实复述观点、论证、操作；用 **加粗**突出关键术语/核心结论/数据。 - 第二段：另起一段，必须以 `【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）： - 不要把“原始逐行字幕（每行时间戳+原文）”附在纪要或 PDF 后面（除非用户明确要求“把原字幕也附录进去”）。 - 不要在内容主体里加“核心内容总结：/导师评注：”这类额外标题；导师段只允许前缀 `【导师评注】`。 ## Segmentation Heuristics (Practical) 将字幕分成“逻辑段落”时： - 以话题切换、板书/投影片章节、例子切换、从原理→实作等自然边界为主 - 段落不要过碎（否则标题会变得重复、信息密度下降）；也不要过大（否则难以检索） - 段落时间跨度建议落在 1–5 分钟量级；必要时可更长，但标题必须能覆盖主要内容 ## Quality Checklist (Before Final) - 每段都满足：时间戳范围 + **标题** + 两段正文（第二段以 `【导师评注】` 开头） - 第一段是否全程第一人称（我/我们），且没有混入“导师视角” - 关键术语/结论/数据是否用 **加粗**标出（不过度加粗） - 导师评注是否包含：概念补充 + 批判性审视 + 不确定性处理（需要进一步验证 + 验证方法） - 未出现“原始逐行字幕全文” ## PDF Export (No Raw Transcript Appendix by Default) 落盘流程建议： 1) 先把最终纪要写入 `output.md` 2) 运行校验：`python3 scripts/validate_summary_md.py output.md` 3) 生成 PDF：`python3 scripts/render_pdf.py --input output.md --outdir .` 命名规则（默认不覆盖）： - 输出文件名默认形如：`视频纪要_<主题短名>_<YYYYMMDD_HHMMSS>.pdf` - 若同名已存在：自动追加 `-v2/-v3` ## Resources - `scripts/validate_summary_md.py`：格式与硬性规范校验 - `scripts/render_pdf.py`：把纪要 Markdown 渲染为 PDF（封面+目录+模块化段落；默认不附原字幕）
Related Skills
writing-anti-ai
This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural", "remove AI-generated traces", "fix robotic writing", or needs to eliminate AI writing patterns from prose. Supports both English and Chinese text. Based on Wikipedia's "Signs of AI writing" guide, detects and fixes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, AI vocabulary, negative parallelisms, and excessive conjunctive phrases.
xhs-note-creator
小红书笔记素材创作技能。当用户需要创建小红书笔记素材时使用这个技能。技能包含：根据用户的需求和提供的资料，撰写小红书笔记内容（标题+正文），生成图片卡片（封面+正文卡片），以及发布小红书笔记。
xhs-longform-private-publisher
This skill should be used when the user wants to publish an existing Markdown article to Xiaohongshu as a private longform post, keep the original wording and structure, insert inline images in order, use one-click layout, and verify the result in note manager.
skills-governance
Use when auditing a large local skill collection, identifying duplicate or imported skills, comparing skill roots, or deciding what to keep, disable, or archive across Codex and adjacent agent skill directories.
skill-governance-loop
Use when the user asks to review a skill, analyze skill quality, update a skill version, or run a repeatable keep/disable/archive decision loop from real failures instead of abstract best practices.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
session-recovery-codex
Use when recovering a Codex session, especially if the user provides a Codex session id or wants recent Codex sessions listed before resuming work.
research-lead-sidecar
Use when the user wants multi-agent division of labor for research-led work and the lead should stay on the critical path while 1-2 bounded sidecars handle low-coupling tasks. Do not use this for tiny tasks, fully sequential debugging, or overlapping refactors.
question-refiner
Use when a research question is still vague and must be clarified into a structured deep-research brief before actual literature research or execution. Skip this if the user already has a concrete paper draft or a ready-to-run research specification.
prompt-polisher
Use when receiving messy, unstructured input like voice transcriptions, stream-of-consciousness notes, or rough document content that needs to be transformed into a polished, optimized prompt. Cleans up filler words, extracts intent, asks clarifying questions, applies Claude 4.x/Opus 4.5/Sonnet 4.5 best practices, and previews the polished prompt for approval before execution. Trigger phrases include "polish this", "clean this up", "turn this into a prompt", or when input is clearly rough/unstructured.
proactive-explorer
落实 CLAUDE.md / AGENTS.md 中的“主动探索”原则，在向用户提问前自动使用 Grep、Read、Bash、WebSearch 等工具获取信息
paperreview
Use when the user explicitly wants to upload a final or near-final PDF to paperreview.ai for an external second opinion. Skip this for local paper critique, which should go through `paper-review-pipeline` first.