Agent skill

Video Transcript Doc Writer

by dragon-hh in dragon-hh/ai-boshu-crawler

为 AI博主爬取 项目生成智能体辅助整理的可读口播稿章节。用于创建 publishtranscriptdocstofeishu.py 所需的 curation JSON,或在需要读取本地视频转写稿并在保持原意的前提下,重写成中文标题、段落和保守 ASR 修正的结构化可读稿时使用。

No licenceAuto-check passedKnowledge Management

Install Video Transcript Doc Writer

skills CLI
$ npx skills add dragon-hh/ai-boshu-crawler --skill video-transcript-doc-writer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dragon-hh/ai-boshu-crawler video-transcript-doc-writer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dragon-hh/ai-boshu-crawler.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/video-transcript-doc-writer .claude/skills/video-transcript-doc-writer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
video-transcript-doc-writer
GitHub stars
106
Token cost
~695 tokens
SKILL.md length
159 words
Files
3 (incl. references)
Skills in repo
21
Repo updated
First seen
Licence
None found

At a glance

为 AI博主爬取 项目生成智能体辅助整理的可读口播稿章节。用于创建 publishtranscriptdocstofeishu.py 所需的 curation JSON,或在需要读取本地视频转写稿并在保持原意的前提下,重写成中文标题、段落和保守 ASR 修正的结构化可读稿时使用。

  • Works in 8 steps: 从磁盘读取转写稿,并检查足够的上下文,确保理解整条视频。 → 将 内容摘要 和 关键要点 作为理解方向,但不要把它们复制成可读口播稿。 → 创建以 record_id 为键的 curation 对象;schema 见… → …
  • Tasks that involve Video and podcast notes
  • SKILL.md covers 目标, 必要输入, 工作流程 and 写作标准, plus 3 more sections
  • Calls python

What it does

Video Transcript Doc Writer is an agent skill from dragon-hh/ai-boshu-crawler. 为 AI博主爬取 项目生成智能体辅助整理的可读口播稿章节。用于创建 publishtranscriptdocstofeishu.py 所需的 curation JSON,或在需要读取本地视频转写稿并在保持原意的前提下,重写成中文标题、段落和保守 ASR 修正的结构化可读稿时使用。

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/curation-json.md`).

It sits in Knowledge Management, covering Video and podcast notes, Speech recognition and synthesis and Messaging and chat bots. It works with Feishu (Lark). The repository describes itself as: AI creator ingestion workflows for Bilibili, Douyin, and Feishu Base.

When your agent uses it

  • Tasks that involve Video and podcast notes
  • Tasks that involve Speech recognition and synthesis
  • Tasks that involve Messaging and chat bots

Example prompts

  • “/video-transcript-doc-writer”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. 从磁盘读取转写稿,并检查足够的上下文,确保理解整条视频。
  2. 将 内容摘要 和 关键要点 作为理解方向,但不要把它们复制成可读口播稿。
  3. 创建以 record_id 为键的 curation 对象;schema 见 references/curation-json.md。
  4. 将 readable_sections 写成面向读者的文章式口播稿
  5. 保守处理 ASR 错误
  6. 将 curation JSON 保存到 downloads/manifests/,文件名要有描述性。
  7. 使用以下命令刷新已有文档
  8. 通过读取飞书文档并对比结果来验证

What it can do on your machine

Read from SKILL.md and the folder at commit 57ad263. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Video Transcript Doc Writer loads about 695 tokens when it runs, and up to ~1.2k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 159 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~695
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 159 words (~695 tokens).

“为 publish_transcript_docs_to_feishu.py 产出 curation JSON。本 skill 负责语言整理工作:读取本地转写稿,理解视频内容,并写出润色后的 口播稿(可读版)。它不直接创建飞书文档,也不直接写入 Base 记录。”

— opening of SKILL.md by dragon-hh
name
video-transcript-doc-writer

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files (references) in .agents/skills/video-transcript-doc-writer of dragon-hh/ai-boshu-crawler.

  • SKILL.md
  • agents/openai.yaml
  • references/curation-json.md

Open the folder on GitHubat commit 57ad263

Compare with similar skills

Video Transcript Doc Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Video Transcript Doc Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Video Transcript Doc Writer this skilldragon-hh/ai-boshu-crawler106—~695Automated safety check: PassNone
Feishu Wikiraucvr/Group-Goki1123 repos~549Automated safety check: PassMIT
Feishu Wikiopenclaw/openclaw392k—~344Automated safety check: PassMIT
Ding SkillsLeoYeAI/openclaw-master-skills2.2k—~3.6kAutomated safety check: PassMIT
Multi-Source to NotebookLM Processorjoeseesun/qiaomu-anything-to-notebooklm6.2k—~3.6kAutomated safety check: PassMIT
Content CollectorLeoYeAI/openclaw-master-skills2.2k—~4.8kAutomated safety check: PassMIT

Similar skills

  • Feishu Wiki

    raucvr/Group-Goki

    Feishu knowledge base navigation. An agent skill from raucvr/Group-Goki.

    112 GitHub starsUsed in 3 repos~549 tokens
    Knowledge ManagementAuto-check passed
  • Feishu Wiki

    openclaw/openclaw

    Feishu knowledge-base navigation workflows. An agent skill from openclaw/openclaw.

    392k GitHub stars~344 tokensUpdated yesterday
    Knowledge ManagementAuto-check passed
  • Ding Skills

    LeoYeAI/openclaw-master-skills

    钉钉操作助手(DingTalk)。当用户通过钉钉对话、或提到以下任何场景时必须使用此技能:查人(查下某某、搜一下某人、找一下谁谁)、查部门、查手机号、查工号、约会议(预约会议、创建会议、安排会议、开个会)、发消息(给某人发消息、群里发个通知)、查审批(我的审批、待审批、审批状态)、发起审批、同意/拒绝审批、查日程、创建日程、查员工数、查离职、开视频会议、钉钉知识库(查钉钉知识库、在钉钉创建文档、…

    2.2k GitHub stars~3.6k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed
  • Multi-Source to NotebookLM Processor

    joeseesun/qiaomu-anything-to-notebooklm

    Collects content from WeChat articles, web pages, YouTube, podcasts, documents and more, uploads it to NotebookLM and generates podcasts, slides or mind maps.

    6.2k GitHub stars~3.6k tokensUpdated 4 days ago
    Knowledge ManagementAuto-check passed
  • Content Collector

    LeoYeAI/openclaw-master-skills

    Automatically collect and archive content from shared links in group chats.

    2.2k GitHub stars~4.8k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed
  • Larksnap Fetch

    AmbroseX/larksnap

    把飞书/Lark 文档或普通网页抓取并保存到本地,也能编辑用户有权限的飞书文档,并用已登录浏览器执行一次网页搜索。用户要求下载、导出、抓取、写入飞书文档,或联网搜索资料/参考链接时使用本技能,即使没有提到 larksnap。底层通过技能自带 daemon 桥接已登录的 larksnap 浏览器扩展;arXiv 使用独立脚本。

    300 GitHub stars~923 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from dragon-hh/ai-boshu-crawler

All 21 skills in this repo
  • Bili Daily Update Check

    dragon-hh/ai-boshu-crawler

    Check whether Feishu Base creators marked 是否持续跟踪=true published Bilibili videos in the recent 7-day window, download new videos in that window, write successful rows to the Feishu 视频 table, and…

    106 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Douyin Chrome Browser Manifest

    dragon-hh/ai-boshu-crawler

    Use this in the AI blogger crawler project when Douyin daily creator updates should use the Codex Chrome plugin instead of the local web-access CDP proxy to collect creator-page cards, selected…

    106 GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed
  • Bilibili Comments

    dragon-hh/ai-boshu-crawler

    Fetch and export all comments from a Bilibili video, including first-level comments and second-level replies, through the user's already logged-in Chrome browser.

    106 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Bilibili Favorite Links

    dragon-hh/ai-boshu-crawler

    Extract Bilibili favorite-folder or visible collection-page video URLs into a local manifest.

    106 GitHub stars~494 tokensUpdated 1 mo ago
    Auto-check passed
  • Douyin Download

    dragon-hh/ai-boshu-crawler

    Download Douyin (抖音) videos using yt-dlp with browser-assisted URL extraction.

    106 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check: warnings
  • Douyin Comments

    dragon-hh/ai-boshu-crawler

    Fetch and export structured comments from a Douyin video only through the user's already logged-in Chrome/CDP browser session.

    106 GitHub stars~3.1k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Video Transcript Doc Writer

What does Video Transcript Doc Writer do?

为 AI博主爬取 项目生成智能体辅助整理的可读口播稿章节。用于创建 publishtranscriptdocstofeishu.py 所需的 curation JSON,或在需要读取本地视频转写稿并在保持原意的前提下,重写成中文标题、段落和保守 ASR 修正的结构化可读稿时使用。. Video Transcript Doc Writer is an agent skill from dragon-hh/ai-boshu-crawler.

When should I use Video Transcript Doc Writer?

Video Transcript Doc Writer fits situations like: tasks that involve Video and podcast notes; tasks that involve Speech recognition and synthesis; tasks that involve Messaging and chat bots.

How do I install Video Transcript Doc Writer in Claude Code?

Run `npx skills add dragon-hh/ai-boshu-crawler --skill video-transcript-doc-writer -a claude-code`. Or copy the skill folder (.agents/skills/video-transcript-doc-writer in dragon-hh/ai-boshu-crawler) into .claude/skills/video-transcript-doc-writer in your project. Claude Code loads it when a task matches its description.

How do I install Video Transcript Doc Writer in Codex?

Run `npx skills add dragon-hh/ai-boshu-crawler --skill video-transcript-doc-writer -a codex`. Or copy the skill folder (.agents/skills/video-transcript-doc-writer in dragon-hh/ai-boshu-crawler) into .agents/skills/video-transcript-doc-writer in your project. Codex loads it when a task matches its description.

Can I use Video Transcript Doc Writer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dragon-hh/ai-boshu-crawler --skill video-transcript-doc-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-transcript-doc-writer, .gemini/skills/video-transcript-doc-writer, .github/skills/video-transcript-doc-writer and .opencode/skills/video-transcript-doc-writer in your project.

What does Video Transcript Doc Writer need to run?

Going by SKILL.md and its folder, Video Transcript Doc Writer needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Video Transcript Doc Writer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Video Transcript Doc Writer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Video Transcript Doc Writer use?

No licence was found for Video Transcript Doc Writer or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Video Transcript Doc Writer use?

About 695 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 522 tokens, read only when the agent opens those files.

What are the alternatives to Video Transcript Doc Writer?

Skills that share tags, products or a category with Video Transcript Doc Writer: Feishu Wiki (raucvr/Group-Goki, 112 stars), Feishu Wiki (openclaw/openclaw, 392k stars), Ding Skills (LeoYeAI/openclaw-master-skills, 2.2k stars) and Multi-Source to NotebookLM Processor (joeseesun/qiaomu-anything-to-notebooklm, 6.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Video Transcript Doc Writer?

dragon-hh (a GitHub user) maintains it in dragon-hh/ai-boshu-crawler, which has 106 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on August 11, 2026.

Source: dragon-hh/ai-boshu-crawler on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.