Video Ingest — via Inngest Pipeline
SkillMediaDownload, transcribe, and summarize videos via the Inngest pipeline. Use when the user asks to grab/download/transcribe/ingest a video, save a YouTube video, or process any video URL. Also handles batch ingest of multiple URLs. This skill triggers the durable Inngest workflow, do NOT run yt-dlp, mlx-whisper, or scp manually.
Use Video Ingest — via Inngest Pipeline in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Video Ingest — via Inngest Pipeline and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Video Ingest skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
What this skill tells your AI
The instructions your AI receives, as published by joelhooks/joelclaw in skills/video-ingest/SKILL.md and read by Ahel’s review.
Videos are ingested through the Inngest event bus. Do not run yt-dlp, mlx-whisper, scp, or create vault notes manually. The pipeline handles everything: download → NAS transfer → transcription → vault note → summary enrichment.
Quick Start
joelclaw send pipeline/video.requested -d '{"url":"URL_HERE"}'
# legacy alias still accepted
joelclaw send pipeline/video.download -d '{"url":"URL_HERE"}'
That's it. The event chain handles the rest.
Alternative (raw curl):
curl -s -X POST "http://localhost:8288/e/$INNGEST_EVENT_KEY" \
-H "Content-Type: application/json" \
-d '{"name":"pipeline/video.requested","data":{"url":"URL_HERE"}}'
Pipeline Flow
pipeline/video.requested — you send this (legacy alias: pipeline/video.download)
↓
video-download function — yt-dlp → /tmp → NAS transfer
↓ emits
pipeline/video.downloaded — logged by system-logger
pipeline/transcript.requested — auto-triggered (legacy alias: pipeline/transcript.process)
↓
transcript-process function — mlx-whisper (M4 Pro, ~5min/hr of video)
↓ emits
pipeline/transcript.processed — logged
content/summarize.requested — auto-triggered (legacy alias: content/summarize)
↓
content-summarize function — pi enrichment → vault note with summary
↓ emits
content/summarized — logged, done
Before Sending: Health Check
Always verify the pipeline is healthy before sending events:
# Inngest server
curl -s http://localhost:8288/health
# Worker (should show functions including video-download)
curl -s http://localhost:3111/ | python3 -c "
import json,sys
d=json.load(sys.stdin)
fns = [f.get('id','?') for f in d.get('functions',[])]
print(f'Worker OK — {len(fns)} functions: {', '.join(fns)}')
"
# Docker container running
docker ps --filter ancestor=inngest/inngest --format "table {{.Status}}\t{{.Ports}}"
If the worker is down:
kubectl -n joelclaw rollout restart deployment/system-bus-worker
kubectl -n joelclaw rollout status deployment/system-bus-worker --timeout=180s
joelclaw refresh
Monitoring a Run
Watch progress in real-time
# Worker logs — shows step execution + failures
kubectl logs -n joelclaw deploy/system-bus-worker -f
# Docker logs — shows event dispatch
docker logs -f $(docker ps -q --filter ancestor=inngest/inngest) 2>&1 | grep -v DEBUG
Check if events fired
# Look for the video's events in Docker logs
docker logs $(docker ps -q --filter ancestor=inngest/inngest) 2>&1 | grep -i "video\|transcript\|summarize" | tail -20
Dashboard
Open http://localhost:8288 in browser — shows functions, events, runs with per-step traces.
Verify completion
# Check if vault note was created
ls -la ~/Vault/Resources/videos/*SLUG*
# Check canonical telemetry for pipeline entries
joelclaw otel search "video|transcript|summarize" --hours 24
Batch Ingest
Send multiple events. Inngest queues and processes them with concurrency control:
joelclaw send pipeline/video.requested -d '{"url":"https://youtube.com/watch?v=XXXX"}'
joelclaw send pipeline/video.requested -d '{"url":"https://youtube.com/watch?v=YYYY"}'
joelclaw send pipeline/video.requested -d '{"url":"https://youtube.com/watch?v=ZZZZ"}'
Manual Transcript (Non-YouTube)
For audio files already on disk, or raw text from Granola/Fathom:
# From audio file
joelclaw send pipeline/transcript.requested -d '{"source":"manual","audioPath":"/path/to/audio.mp4","title":"Recording Title","slug":"recording-title"}'
# From raw text (Granola, Fathom, etc.)
joelclaw send pipeline/transcript.requested -d '{"source":"granola","text":"transcript text...","title":"Meeting Title","slug":"meeting-title"}'
Re-run Summary Only
If the vault note exists but needs a better summary:
joelclaw send content/summarize.requested -d '{"vaultPath":"/Users/joel/Vault/Resources/videos/SLUG.md"}'
Options
| Field | Default | Description |
|---|---|---|
url | required | YouTube or video URL |
maxQuality | "1080" | Max video resolution: "720", "1080", "4k" |
Where Things End Up
| What | Location |
|---|---|
| Video + metadata | NAS: /volume1/home/joel/video/YYYY/SLUG/ |
| Vault note | ~/Vault/Resources/videos/SLUG.md |
| Daily note link | ~/Vault/Daily/YYYY-MM-DD.md under ## Videos |
| Runtime telemetry | joelclaw otel (otel_events in Typesense/ClickHouse) |
| Durable source receipt | Vault note plus the originating Inngest event/run |
Troubleshooting
If events are accepted (200 OK) but nothing happens:
-
Check Docker→worker connectivity — the most common issue:
docker logs $(docker ps -q --filter ancestor=inngest/inngest) 2>&1 | grep -E "ERROR|Unable" | tail -5If you see "Unable to reach SDK URL" → see the inngest skill's serveHost gotcha.
-
Check worker is actually running:
kubectl get deploy -n joelclaw system-bus-worker kubectl get pods -n joelclaw -l app=system-bus-worker -
Check worker errors for the specific function:
kubectl logs -n joelclaw deploy/system-bus-worker --tail=80 -
Use inngest-debug skill for deep inspection of specific run IDs via GraphQL.
What NOT to Do
- ❌ Don't run
yt-dlpdirectly — the pipeline handles download + NAS transfer - ❌ Don't run
mlx_whisperdirectly — the pipeline handles transcription - ❌ Don't
scpto NAS manually — the pipeline handles transfer - ❌ Don't create vault notes manually — the pipeline creates them with proper frontmatter
- ❌ Don't use codex/background tasks for video processing — Inngest is durable and has retries
Signals
- GitHub stars
- 64
- Forks
- 2
- Last commit
- Sep 2026
Ahel review
K2info
exfiltration
Automated review, not a security audit. Ruleset v1+k2.
Advanced
- Item type
- skill
- Key
video-ingest-joelhooks- Source
- github.com/joelhooks/joelclaw