agency-meetup-publish

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AGENCY Meetup Publish

AGENCY 聚会录像发布

Publish AGENCY Community meetup recordings to YouTube with intro, thumbnail, description, and timecodes.

将AGENCY社区聚会录像发布到YouTube，包含片头、缩略图、描述和时间码。

Prerequisites

前置条件

```
~/ai_projects/youtube-uploader/
```
— YouTube upload scripts with OAuth credentials

~/ai_projects/my-video/out/agency-swarm-intro.mp4

— AGENCY intro animation (6s, 1920x1080)

Zoom OAuth configured at
```
~/.zoom_credentials/
```
```
ffmpeg
```
and
```
ffprobe
```
installed
Playwright or Chrome installed (for thumbnail rendering)

```
~/ai_projects/youtube-uploader/
```
— 带有OAuth凭证的YouTube上传脚本

~/ai_projects/my-video/out/agency-swarm-intro.mp4

— AGENCY片头动画（6秒，1920x1080）

Zoom OAuth已在
```
~/.zoom_credentials/
```
配置完成
已安装
```
ffmpeg
```
和
```
ffprobe
```
已安装Playwright或Chrome（用于缩略图渲染）

Pipeline Overview

流程概览

1. Identify meeting → 2. Download from Zoom → 3. Add intro/outro
→ 4. Generate timecodes → 5. Write description → 6. Create thumbnail
→ 7. Upload to YouTube → 8. Set thumbnail → 9. Add to playlist

1. Identify meeting → 2. Download from Zoom → 3. Add intro/outro
→ 4. Generate timecodes → 5. Write description → 6. Create thumbnail
→ 7. Upload to YouTube → 8. Set thumbnail → 9. Add to playlist

Step 1: Identify the Meeting

步骤1：确定会议

Ask the user for:

Meeting name or Zoom ID — if unknown, list recent recordings:

bash

python3 ~/.claude/skills/zoom/scripts/zoom_meetings.py recordings --start YYYY-MM-DD

Speaker name — for description and thumbnail
Topic summary — or derive from transcript

Get recording details:

bash

python3 ~/.claude/skills/zoom/scripts/zoom_meetings.py recording MEETING_ID

This returns MP4 download URL, duration, transcript URL, and other files.

向用户询问：

会议名称或Zoom ID — 若未知，列出近期录像：

bash

python3 ~/.claude/skills/zoom/scripts/zoom_meetings.py recordings --start YYYY-MM-DD

演讲者姓名 — 用于描述和缩略图
主题摘要 — 或从转录文本中提取

获取录像详情：

bash

python3 ~/.claude/skills/zoom/scripts/zoom_meetings.py recording MEETING_ID

此命令会返回MP4下载链接、时长、转录文本链接及其他文件。

Step 2: Download from Zoom

步骤2：从Zoom下载

Download MP4 and VTT transcript in parallel:

bash

undefined

并行下载MP4视频和VTT转录文本：

bash

undefined

Video (run in background — large file)

curl -L -o ~/Brains/brain/YYYYMMDD-meeting-slug.mp4 "DOWNLOAD_URL"

Transcript

curl -L -o ~/Brains/brain/YYYYMMDD-meeting-slug.vtt "TRANSCRIPT_URL"


**Naming convention:** `YYYYMMDD-meeting-slug.mp4` where slug is a kebab-case topic summary.

curl -L -o ~/Brains/brain/YYYYMMDD-meeting-slug.vtt "TRANSCRIPT_URL"


**命名规范：** `YYYYMMDD-meeting-slug.mp4`，其中slug是主题摘要的短横线分隔格式。

Step 3: Add Intro (and Outro if Available)

步骤3：添加片头（如有片尾也添加）

The intro and meeting likely have different specs. Check both:

bash

ffprobe -v quiet -print_format json -show_streams INTRO.mp4
ffprobe -v quiet -print_format json -show_streams MEETING.mp4

Key parameters to match: resolution, fps, audio sample rate, audio channels.

片头和会议录像的参数可能不同，需检查两者：

bash

ffprobe -v quiet -print_format json -show_streams INTRO.mp4
ffprobe -v quiet -print_format json -show_streams MEETING.mp4

需要匹配的关键参数：分辨率、帧率、音频采样率、音频声道数。

Re-encode intro to match meeting

重新编码片头以匹配会议录像

bash

ffmpeg -y -i ~/ai_projects/my-video/out/agency-swarm-intro.mp4 \
  -vf "scale=WIDTH:HEIGHT:force_original_aspect_ratio=decrease,pad=WIDTH:HEIGHT:(ow-iw)/2:(oh-ih)/2:black" \
  -r FPS -c:v libx264 -preset fast -crf 18 \
  -ar SAMPLE_RATE -ac CHANNELS -c:a aac \
  /tmp/intro-matched.mp4

bash

ffmpeg -y -i ~/ai_projects/my-video/out/agency-swarm-intro.mp4 \
  -vf "scale=WIDTH:HEIGHT:force_original_aspect_ratio=decrease,pad=WIDTH:HEIGHT:(ow-iw)/2:(oh-ih)/2:black" \
  -r FPS -c:v libx264 -preset fast -crf 18 \
  -ar SAMPLE_RATE -ac CHANNELS -c:a aac \
  /tmp/intro-matched.mp4

Trim meeting start

修剪会议录像开头

Review the VTT to find where real content begins. Typically trim 1-3 seconds of silence:

bash

ffmpeg -y -ss TRIM_SECONDS -i MEETING.mp4 \
  -c:v libx264 -preset fast -crf 18 \
  -ar SAMPLE_RATE -ac CHANNELS -c:a aac \
  -r FPS -vf "scale=WIDTH:HEIGHT" \
  /tmp/meeting-trimmed.mp4

This re-encode is necessary for concat compatibility. Run in background — it takes several minutes for long recordings.

查看VTT转录文本以找到实际内容开始的位置。通常修剪1-3秒的静音部分：

bash

ffmpeg -y -ss TRIM_SECONDS -i MEETING.mp4 \
  -c:v libx264 -preset fast -crf 18 \
  -ar SAMPLE_RATE -ac CHANNELS -c:a aac \
  -r FPS -vf "scale=WIDTH:HEIGHT" \
  /tmp/meeting-trimmed.mp4

为了兼容拼接操作，此重新编码步骤是必要的。后台运行此命令——长录像可能需要数分钟。

Concatenate

拼接视频

bash

echo "file '/tmp/intro-matched.mp4'" > /tmp/concat-list.txt
echo "file '/tmp/meeting-trimmed.mp4'" >> /tmp/concat-list.txt

bash

echo "file '/tmp/intro-matched.mp4'" > /tmp/concat-list.txt
echo "file '/tmp/meeting-trimmed.mp4'" >> /tmp/concat-list.txt

If outro exists:

echo "file '/tmp/outro-matched.mp4'" >> /tmp/concat-list.txt

ffmpeg -y -f concat -safe 0 -i /tmp/concat-list.txt -c copy
~/ai_projects/my-video/out/YYYYMMDD-meeting-slug-final.mp4

undefined

ffmpeg -y -f concat -safe 0 -i /tmp/concat-list.txt -c copy
~/ai_projects/my-video/out/YYYYMMDD-meeting-slug-final.mp4

undefined

Step 4: Generate Timecodes from Transcript

步骤4：从转录文本生成时间码

Read the VTT transcript and identify up to 20 topic transitions. Look for:

Speaker changes (especially when the main speaker starts)
Topic shifts signaled by phrases like "давайте", "следующий", "перейдем к"
Q&A segments
Demo/screen-share moments
Conclusion/wrap-up

Important: Timecodes must account for the intro offset. Add the intro duration (typically 6s) to all VTT timestamps.

Format:

MM:SS Topic description

H:MM:SS

for videos over 1 hour.

读取VTT转录文本，识别最多20个主题转换点。重点关注：

演讲者变更（尤其是主演讲者开始发言时）
表示主题切换的短语，如“давайте”“следующий”“перейдем к”
问答环节
演示/屏幕共享时刻
总结/收尾部分

重要提示： 时间码必须考虑片头的时长偏移。将所有VTT时间戳加上片头时长（通常为6秒）。

格式：

MM:SS 主题描述

，若视频超过1小时则使用

H:MM:SS

。

Step 5: Write Description

步骤5：撰写描述

Follow the template from previous AGENCY Community uploads. See

references/description-template.md

for the full template.

Key sections:

Title line —
```
AGENCY Community Meetup: [Topic]
```
Summary paragraph — 2-3 sentences about the speaker and topic
Bullet points — 5-7 key topics covered (use •)
Timecodes — prefixed with
```
⏱ Таймкоды:
```

Community line —

AGENCY Community — сообщество практиков AI-автоматизации.

Links — prefixed with 🔗, using → arrows
Hashtags — topic-relevant, always include
```
#AGENCY #Community
```

Save description to

/tmp/youtube-description.txt

遵循之前AGENCY社区上传的模板。完整模板请查看

references/description-template.md

。

关键部分：

标题行 —
```
AGENCY Community Meetup: [Topic]
```
摘要段落 — 2-3句话介绍演讲者和主题
项目符号 — 5-7个涵盖的关键主题（使用•）
时间码 — 前缀为
```
⏱ Таймкоды:
```

社区标语 —

AGENCY Community — сообщество практиков AI-автоматизации.

链接 — 前缀为🔗，使用→箭头
话题标签 — 与主题相关，务必包含
```
#AGENCY #Community
```

将描述保存到

/tmp/youtube-description.txt

。

Step 6: Create Thumbnail

步骤6：创建缩略图

Use the AGENCY thumbnail HTML template rendered to 1280x720 PNG.

使用AGENCY缩略图HTML模板渲染为1280x720的PNG图片。

Template approach

模板方法

Write an HTML file at

/tmp/thumbnail.html

based on

references/thumbnail-template.html

. Customize:

Title text — short, punchy (2-4 words max per line)
Subtitle — in EB Garamond italic
Speaker line —
```
Speaker Name × AGENCY
```
Speaker photo — if available, use with
```
mix-blend-mode: hard-light
```

基于

references/thumbnail-template.html

在

/tmp/thumbnail.html

生成HTML文件。自定义内容：

标题文本 — 简短有力（每行最多2-4个单词）
副标题 — 使用EB Garamond斜体
演讲者行 —
```
Speaker Name × AGENCY
```
演讲者照片 — 如有可用，使用
```
mix-blend-mode: hard-light
```
效果

Render to PNG

渲染为PNG

Preferred: headless Chrome (no install needed):

bash

"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
  --headless --screenshot=/tmp/thumbnail.png \
  --window-size=1280,720 --hide-scrollbars \
  "file:///tmp/thumbnail.html"

Fallback: Playwright:

python

from playwright.sync_api import sync_playwright
with sync_playwright() as p:
    browser = p.chromium.launch()
    page = browser.new_page(viewport={'width': 1280, 'height': 720})
    page.goto('file:///tmp/thumbnail.html')
    page.wait_for_timeout(2000)
    page.screenshot(path='/tmp/thumbnail.png')
    browser.close()

首选方式：无头Chrome（无需额外安装）：

bash

"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
  --headless --screenshot=/tmp/thumbnail.png \
  --window-size=1280,720 --hide-scrollbars \
  "file:///tmp/thumbnail.html"

备选方式：Playwright：

python

from playwright.sync_api import sync_playwright
with sync_playwright() as p:
    browser = p.chromium.launch()
    page = browser.new_page(viewport={'width': 1280, 'height': 720})
    page.goto('file:///tmp/thumbnail.html')
    page.wait_for_timeout(2000)
    page.screenshot(path='/tmp/thumbnail.png')
    browser.close()

Step 7: Upload to YouTube

步骤7：上传至YouTube

bash

cd ~/ai_projects/youtube-uploader && python3 youtube_upload.py \
  --video ~/ai_projects/my-video/out/FINAL.mp4 \
  --title "TITLE" \
  --description "$(cat /tmp/youtube-description.txt)" \
  --category education \
  --privacy public \
  --tags "TAG1,TAG2,..." \
  --yes

The upload script outputs the Video ID and Video URL on success. Capture these for the next steps.

Title guidelines: Keep under 100 chars. Format:

Topic — Speaker Name

. Include key terms for search.

bash

cd ~/ai_projects/youtube-uploader && python3 youtube_upload.py \
  --video ~/ai_projects/my-video/out/FINAL.mp4 \
  --title "TITLE" \
  --description "$(cat /tmp/youtube-description.txt)" \
  --category education \
  --privacy public \
  --tags "TAG1,TAG2,..." \
  --yes

上传成功后，脚本会输出视频ID和视频链接。记录这些信息用于后续步骤。

标题准则： 长度不超过100字符。格式：

Topic — Speaker Name

。包含便于搜索的关键词。

Step 8: Set Thumbnail

步骤8：设置缩略图

bash

cd ~/ai_projects/youtube-uploader && \
  python3 youtube_manage.py thumbnails set VIDEO_ID /tmp/thumbnail.png

bash

cd ~/ai_projects/youtube-uploader && \
  python3 youtube_manage.py thumbnails set VIDEO_ID /tmp/thumbnail.png

Step 9: Add to Playlist

步骤9：添加到播放列表

The AGENCY Community playlist ID is

PLZNP0SKU2SqjHOy01UjDxhSRtcluvuw0m

bash

cd ~/ai_projects/youtube-uploader && \
  python3 youtube_manage.py playlists add-item PLZNP0SKU2SqjHOy01UjDxhSRtcluvuw0m VIDEO_ID

AGENCY社区播放列表ID为

PLZNP0SKU2SqjHOy01UjDxhSRtcluvuw0m

。

bash

cd ~/ai_projects/youtube-uploader && \
  python3 youtube_manage.py playlists add-item PLZNP0SKU2SqjHOy01UjDxhSRtcluvuw0m VIDEO_ID

Parallelization Strategy

并行化策略

For speed, run these in parallel where possible:

Phase	Can parallelize with
Download MP4	Download VTT
Re-encode meeting (bg)	Read transcript, draft timecodes
Upload to YouTube (bg)	Generate thumbnail
Set thumbnail	Add to playlist

为提升速度，可在以下环节并行操作：

阶段	可并行操作的环节
下载MP4	下载VTT
重新编码会议录像（后台）	读取转录文本、草拟时间码
上传至YouTube（后台）	生成缩略图
设置缩略图	添加到播放列表

Output

输出

Report to the user:

Video URL:

https://www.youtube.com/watch?v=VIDEO_ID

Studio URL:

https://studio.youtube.com/video/VIDEO_ID/edit

Playlist: AGENCY Community

向用户汇报：

视频链接:

https://www.youtube.com/watch?v=VIDEO_ID

工作室链接:

https://studio.youtube.com/video/VIDEO_ID/edit

播放列表: AGENCY Community

Existing Skills Used

使用的现有技能

This pipeline builds on:

zoom —
```
~/.claude/skills/zoom/
```
for Zoom recording access
video-youtube-upload —
```
~/.claude/skills/video-youtube-upload/
```
for upload reference
youtube —
```
~/.claude/skills/youtube/
```
for post-upload management
agency-socials —
```
~/.claude/skills/agency-socials/
```
for cover design system reference

此流程基于以下技能构建：

zoom —
```
~/.claude/skills/zoom/
```
用于访问Zoom录像
video-youtube-upload —
```
~/.claude/skills/video-youtube-upload/
```
作为上传参考
youtube —
```
~/.claude/skills/youtube/
```
用于上传后管理
agency-socials —
```
~/.claude/skills/agency-socials/
```
用于封面设计系统参考