一键在 Manus 中运行任何 Skill

$pwd:

agency-meetup-publish

Name: Agency Meetup Publish
Author: glebis

// End-to-end pipeline for publishing AGENCY Community meetup recordings to YouTube. Downloads Zoom recording, adds intro/outro, generates thumbnail, creates description with timecodes, uploads to YouTube, sets thumbnail, and adds to the AGENCY Community playlist. Use this skill when the user wants to publish a meetup, says "upload the meetup", "publish the recording", "process the Zoom recording for YouTube", or mentions uploading an AGENCY Community session. Also triggers on requests to add intro/outro to a meeting recording and upload it.

在 Manus 中运行

$ git log --oneline --stat

stars:233

forks:32

updated:2026年5月29日 09:13

文件资源管理器

3 个文件

SKILL.md

readonly

related-skills.json

同仓库

meeting-prep.md

from "glebis/claude-skills"

Prepare for upcoming meetings — pulls Cal.com bookings, researches participants, audits previous sessions from Obsidian vault, and creates prep notes. Also links prep notes to post-meeting session notes.

2026-05-30233

meeting-processor.md

from "glebis/claude-skills"

This skill should be used when processing meeting transcripts to auto-detect meeting type (leadgen, partnership, coaching, internal) and extract type-specific structured analysis. Triggers on "process meeting", "analyze meeting", "meeting summary", or after syncing new Fathom/Granola transcripts.

2026-05-30233

coaching-session-summarizer.md

from "glebis/claude-skills"

This skill should be used to summarize coaching or therapy session transcripts after a Fathom/Granola sync. The agent analyzes the transcript itself (no API key, runs on the subscription) and appends key insights, decisions, action items, and trail connections. Supports quick extraction or deep analysis with cross-session pattern detection.

2026-05-30233

synthetic-session-generator.md

from "glebis/claude-skills"

This skill should be used to generate realistic, persona-consistent synthetic coaching and therapy session transcripts for evals, demos, and training data. It produces fictional but believable coach/client (or therapist/client) dialogue grounded in a chosen modality (ICF/GROW coaching, CBT, IFS parts work, ACT/motivational interviewing) and exports to Fathom/Granola transcript style, plain dialogue, structured JSON, or Obsidian markdown. Triggers on requests like "generate a synthetic coaching session", "make fake therapy transcripts for evals", "create demo session transcripts", "synthetic CBT dialogue", "persona-consistent coaching transcript", "test data for my session summarizer", or "mock coaching call".

2026-05-30233

gpt-image-2.md

from "glebis/claude-skills"

Generate and edit images using OpenAI's GPT Image 2 API. Interactive skill that guides users through image creation with style presets, cost-aware draft/final workflow, thinking mode, carousels, and photo editing. This skill should be used when the user requests image generation via OpenAI/GPT Image 2, wants to create social media carousels, edit photos into artistic styles, or needs images with readable text (infographics, diagrams, posters).

2026-05-29233

agency-socials.md

from "glebis/claude-skills"

Generate social media covers and assets for AGENCY Community events, meetups, and YouTube recordings. Use when creating event covers, YouTube thumbnails, or social posts for the AGENCY Community.

2026-05-29233

package.json

"author": "glebis"

"repository": "glebis/claude-skills"

打开 GitHub 仓库查看创作者相关仓库

$ install --global

$ download --local

在 Manus 中运行

$ useful --forSOC

软件开发工程师计算机与数学类职业15-1252L4

name

agency-meetup-publish

description

End-to-end pipeline for publishing AGENCY Community meetup recordings to YouTube. Downloads Zoom recording, adds intro/outro, generates thumbnail, creates description with timecodes, uploads to YouTube, sets thumbnail, and adds to the AGENCY Community playlist. Use this skill when the user wants to publish a meetup, says "upload the meetup", "publish the recording", "process the Zoom recording for YouTube", or mentions uploading an AGENCY Community session. Also triggers on requests to add intro/outro to a meeting recording and upload it.

AGENCY Meetup Publish

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

Prerequisites

~/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)

Pipeline Overview

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

Ask the user for:

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

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:

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

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

Step 2: Download from Zoom

Download MP4 and VTT transcript in parallel:

# 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.

Step 3: Add Intro (and Outro if Available)

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

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.

Re-encode intro to match meeting

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

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

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.

Concatenate

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

Step 4: Generate Timecodes from Transcript

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 or H:MM:SS for videos over 1 hour.

Step 5: Write Description

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.

Step 6: Create Thumbnail

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

Template approach

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

Render to PNG

Preferred: headless Chrome (no install needed):

"/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:

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

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.

Step 8: Set Thumbnail

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

Step 9: Add to Playlist

The AGENCY Community playlist ID is PLZNP0SKU2SqjHOy01UjDxhSRtcluvuw0m.

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

Parallelization Strategy

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

Output

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

Existing Skills Used

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

agency-meetup-publish

同仓库更多 Skills

同仓库更多 Skills

AGENCY Meetup Publish

Prerequisites

Pipeline Overview

Step 1: Identify the Meeting

Step 2: Download from Zoom

Step 3: Add Intro (and Outro if Available)

Re-encode intro to match meeting

Trim meeting start

Concatenate

Step 4: Generate Timecodes from Transcript

Step 5: Write Description

Step 6: Create Thumbnail

Template approach

Render to PNG

Step 7: Upload to YouTube

Step 8: Set Thumbnail

Step 9: Add to Playlist

Parallelization Strategy

Output

Existing Skills Used

AGENCY Meetup Publish

Prerequisites

Pipeline Overview

Step 1: Identify the Meeting

Step 2: Download from Zoom

Step 3: Add Intro (and Outro if Available)

Re-encode intro to match meeting

Trim meeting start

Concatenate

Step 4: Generate Timecodes from Transcript

Step 5: Write Description

Step 6: Create Thumbnail

Template approach

Render to PNG

Step 7: Upload to YouTube

Step 8: Set Thumbnail

Step 9: Add to Playlist

Parallelization Strategy

Output

Existing Skills Used