zoom/SKILL.md
Create and manage Zoom meetings and access cloud recordings via the Zoom API. Use for queries like "create a Zoom meeting", "list my Zoom meetings", "show my Zoom recordings", or "schedule a meeting for tomorrow".
npx skillsauth add glebis/claude-skills zoomInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Manage Zoom meetings and cloud recordings via the Zoom API.
Note: All times passed to create/update commands are interpreted as local time. The script auto-detects your timezone if not explicitly specified with --timezone.
This skill uses two authentication methods:
| Feature | Auth Type | Credentials File |
|---------|-----------|------------------|
| Meetings | Server-to-Server OAuth | ~/.zoom_credentials/credentials.json |
| Recordings | User OAuth (General App) | ~/.zoom_credentials/oauth_token.json |
Check status:
python3 scripts/zoom_meetings.py setup
meeting:read:meeting:adminmeeting:read:list_meetings:adminmeeting:write:meeting:adminuser:read:user:adminmkdir -p ~/.zoom_credentials
cat > ~/.zoom_credentials/credentials.json << 'EOF'
{
"account_id": "YOUR_ACCOUNT_ID",
"client_id": "YOUR_CLIENT_ID",
"client_secret": "YOUR_CLIENT_SECRET"
}
EOF
Server-to-Server apps cannot access cloud recordings. You need a separate General App:
http://localhost:8888/callbackcloud_recording:read:list_user_recordingscloud_recording:read:list_recording_files# Open this URL in browser (replace CLIENT_ID):
https://zoom.us/oauth/authorize?response_type=code&client_id=YOUR_CLIENT_ID&redirect_uri=http://localhost:8888/callback
# After authorizing, you'll be redirected to:
# http://localhost:8888/callback?code=AUTHORIZATION_CODE
# Exchange the code for tokens (replace values):
python3 -c "
import requests, json
resp = requests.post('https://zoom.us/oauth/token',
auth=('CLIENT_ID', 'CLIENT_SECRET'),
data={'grant_type': 'authorization_code', 'code': 'AUTH_CODE', 'redirect_uri': 'http://localhost:8888/callback'})
data = resp.json()
data['client_id'] = 'CLIENT_ID'
data['client_secret'] = 'CLIENT_SECRET'
data['expires_at'] = __import__('time').time() + data.get('expires_in', 3600)
with open(__import__('pathlib').Path.home() / '.zoom_credentials/oauth_token.json', 'w') as f:
json.dump(data, f, indent=2)
print('Saved!')
"
# Check setup
python3 scripts/zoom_meetings.py setup
# List upcoming meetings
python3 scripts/zoom_meetings.py list
# Create a meeting
python3 scripts/zoom_meetings.py create "Team Standup" --start "2025-01-15T10:00:00" --duration 30
# List recordings
python3 scripts/zoom_meetings.py recordings --start 2025-01-01
# List meetings
python3 scripts/zoom_meetings.py list # upcoming
python3 scripts/zoom_meetings.py list --type previous # past
python3 scripts/zoom_meetings.py list --limit 10 --json
# Get meeting details
python3 scripts/zoom_meetings.py get MEETING_ID
# Create meeting (times are treated as LOCAL time)
python3 scripts/zoom_meetings.py create "Topic" # instant
python3 scripts/zoom_meetings.py create "Topic" --start "2025-01-15T14:00:00" # scheduled (local time)
python3 scripts/zoom_meetings.py create "Topic" --duration 60 --timezone "Europe/Berlin"
python3 scripts/zoom_meetings.py create "Topic" --agenda "Discussion points" --waiting-room
python3 scripts/zoom_meetings.py create "Topic" --invite "[email protected]" # send invite
python3 scripts/zoom_meetings.py create "Topic" --invite "[email protected]" --invite "[email protected]" # multiple
# Update meeting
python3 scripts/zoom_meetings.py update MEETING_ID --topic "New Topic"
python3 scripts/zoom_meetings.py update MEETING_ID --start "2025-01-16T10:00:00"
# Delete meeting (requires meeting:delete:meeting:admin scope)
python3 scripts/zoom_meetings.py delete MEETING_ID
# List all recordings (default: last 30 days)
python3 scripts/zoom_meetings.py recordings
# With date range
python3 scripts/zoom_meetings.py recordings --start 2025-01-01 --end 2025-01-31
# Show download URLs
python3 scripts/zoom_meetings.py recordings --show-downloads
# Get specific meeting's recordings
python3 scripts/zoom_meetings.py recording MEETING_ID
# JSON output
python3 scripts/zoom_meetings.py recordings --json
# Zoom Meetings (3 upcoming)
## Weekly Team Sync
**ID:** 123456789
**Start:** 2025-01-15 14:00:00 UTC
**Duration:** 60 minutes
**Join URL:** https://zoom.us/j/123456789
Add --json for structured output suitable for piping to other tools.
| Type | Description | |------|-------------| | MP4 | Video recording | | M4A | Audio only | | TRANSCRIPT | Text transcript (VTT) | | CHAT | Chat messages | | TIMELINE | Speaker timeline | | SUMMARY | AI meeting summary |
| User says | Command |
|-----------|---------|
| "List my Zoom meetings" | list |
| "Show past meetings" | list --type previous |
| "Create a meeting for tomorrow at 2pm" | create "Meeting" --start "2025-01-15T14:00:00" |
| "Show my Zoom recordings" | recordings --start 2025-01-01 |
| "Get the recording for meeting X" | recording MEETING_ID |
pip install requests
| File | Purpose |
|------|---------|
| ~/.zoom_credentials/credentials.json | S2S OAuth credentials |
| ~/.zoom_credentials/token.json | S2S cached token |
| ~/.zoom_credentials/oauth_token.json | User OAuth tokens (auto-refreshes) |
join_before_host is account-level. This setting is locked at the Zoom account admin level. Setting it via API per-meeting is silently ignored if the account setting overrides it. Must change in Zoom admin settings (Security → "Allow participants to join before host") first, then API calls respect it.join_before_host won't work even if the API accepts it.development
--- name: agency-docs-updater description: End-to-end pipeline for publishing Claude Code lab meetings. Accepts optional args: date (YYYYMMDD, "yesterday", "today") and lab number (e.g. "04"). Examples: "yesterday 04", "20260420 05", "04" (today, lab 04), "" (today, auto-detect lab). --- # Agency Docs Updater Execute ALL steps automatically in sequence. Only pause if a step fails and cannot be recovered. Read `references/learnings.md` before starting for known pitfalls. **Configuration**: pat
tools
This skill should be used when applying proper typography to prose text or files in Russian, English, German, or French — smart quotes per locale («ёлочки», “curly”, „Gänsefüßchen“, « guillemets »), correct dashes (тире, em/en dash, Gedankenstrich, tiret), non-breaking spaces, ranges, ellipsis, and French espaces insécables before ! ? ; :. Fully deterministic via a pinned typograf-based CLI; never apply these rules by hand. Triggers on "типографика", "typograf", "оттипографь", "smart quotes", "fix typography", "неразрывные пробелы".
development
This skill should be used when inspecting or applying advanced OpenType features of a font (woff2/otf/ttf) — ligatures, stylistic sets (ss01–ss20), character variants (cvXX), texture healing, slashed zero, tabular/oldstyle figures, fractions, small caps, case-sensitive forms — and generating the CSS to enable them. Interviews the user via cenno to pick features. Triggers on "OpenType features", "font features", "stylistic sets", "ligatures", "texture healing", "tabular figures", "what can this font do".
tools
--- name: pre-session-portrait description: Build a compressed, visualizable "portrait" of a consulting/coaching client before a session, so the paid hour is spent solving, not scoping. Runs a 7-lens JTBD-inspired interview (where / how / what / problem / ideal / tension / jobs-to-be-done) that takes rich open answers in and compresses them to an 11-field YAML portrait out. Delivers three ways: raw paste-into-a-clean-chat prompt, a secret GitHub gist link, or a Codex CLI one-liner. Use when prep