Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Configure Fathom webhooks for real-time meeting notifications. Use when setting up automated meeting processing, receiving real-time transcripts, or triggering workflows when meetings complete. Trigger with phrases like "fathom webhook", "fathom notifications", "fathom real-time", "fathom event handler".
.claude/skills/jeremylongshore-fathom-webhooks-events/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 13% | 0% |
Fathom webhooks send meeting data to your URL when recordings are ready. Webhooks can include summary, transcript, and action items. Configure in Settings or via API.
bashcurl -X POST -H "X-Api-Key: ${FATHOM_API_KEY}" \ -H "Content-Type: application/json" \ https://api.fathom.ai/external/v1/webhooks \ -d '{ "url": "https://your-app.com/webhooks/fathom", "include_summary": true, "include_transcript": true, "include_action_items": true, "fire_on_own_meetings": true, "fire_on_shared_meetings": false }'
Navigate to Settings > Integrations > Webhooks > Create Webhook.
json{ "type": "meeting_content_ready", "recording_id": "rec-abc123", "url": "https://fathom.video/call/abc123", "share_url": "https://fathom.video/share/abc123", "title": "Product Review Q1", "summary": "Discussed roadmap priorities...", "transcript": [...], "action_items": [...] }
pythonfrom flask import Flask, request, jsonify app = Flask(__name__) @app.route("/webhooks/fathom", methods=["POST"]) def fathom_webhook(): event = request.json if event.get("type") == "meeting_content_ready": recording_id = event["recording_id"] summary = event.get("summary", "") actions = event.get("action_items", []) # Process meeting data print(f"Meeting ready: {event.get('title')} ({len(actions)} action items)") return jsonify({"received": True}), 200
bash# Test with webhook.site curl -X POST https://webhook.site/your-uuid \ -H "Content-Type: application/json" \ -d '{"type": "meeting_content_ready", "recording_id": "test"}' # Or use ngrok for local testing ngrok http 5000
For performance optimization, see fathom-performance-tuning.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 8,256 | 4,785 | -42% | 1 | 1 | 0% | 1,560 | 1,398 | -10% | 0 | 0 | — |
case-02 | fail→pass | 17,667 | 7,138 | -60% | 1 | 1 | 0% | 2,647 | 2,033 | -23% | 0 | 0 | — |
case-03 | fail→pass | 15,695 | 7,636 | -51% | 1 | 1 | 0% | 2,425 | 1,846 | -24% | 0 | 0 | — |
case-04 | fail→pass | 9,173 | 2,106 | -77% | 1 | 1 | 0% | 1,433 | 1,015 | -29% | 0 | 0 | — |
case-05 | fail→pass | 6,006 | 4,231 | -30% | 1 | 1 | 0% | 1,077 | 1,222 | +13% | 0 | 0 | — |
case-06 | fail→pass | 11,366 | 3,198 | -72% | 1 | 1 | 0% | 1,588 | 1,193 | -25% | 0 | 0 | — |
case-07 | pass→pass | 10,080 | 1,762 | -83% | 1 | 1 | 0% | 1,659 | 916 | -45% | 0 | 0 | — |
case-08 | fail→pass | 15,726 | 4,422 | -72% | 1 | 1 | 0% | 2,264 | 1,302 | -42% | 0 | 0 | — |
case-09 | fail→pass | 11,991 | 2,803 | -77% | 1 | 1 | 0% | 2,229 | 923 | -59% | 0 | 0 | — |
case-10 | pass→pass | 11,397 | 2,252 | -80% | 1 | 1 | 0% | 1,514 | 940 | -38% | 0 | 0 | — |
case-11 | pass→pass | 6,678 | 3,909 | -41% | 1 | 1 | 0% | 1,189 | 1,188 | -0% | 0 | 0 | — |
case-12 | pass→pass | 10,134 | 4,597 | -55% | 1 | 1 | 0% | 1,546 | 1,357 | -12% | 0 | 0 | — |
case-13 | fail→pass | 11,154 | 6,552 | -41% | 1 | 1 | 0% | 1,975 | 1,611 | -18% | 0 | 0 | — |
case-14 | fail→pass | 8,594 | 3,375 | -61% | 1 | 1 | 0% | 1,597 | 1,306 | -18% | 0 | 0 | — |
case-15 | pass→pass | 11,142 | 1,868 | -83% | 1 | 1 | 0% | 2,087 | 965 | -54% | 0 | 0 | — |
case-16 | pass→pass | 9,206 | 3,032 | -67% | 1 | 1 | 0% | 1,542 | 1,193 | -23% | 0 | 0 | — |
case-17 | fail→pass | 11,567 | 2,957 | -74% | 1 | 1 | 0% | 1,695 | 948 | -44% | 0 | 0 | — |
case-18 | fail→pass | 7,927 | 3,111 | -61% | 1 | 1 | 0% | 1,207 | 1,002 | -17% | 0 | 0 | — |
case-19 | pass→pass | 5,881 | 2,078 | -65% | 1 | 1 | 0% | 1,010 | 958 | -5% | 0 | 0 | — |
case-20 | pass→pass | 13,946 | 10,878 | -22% | 1 | 1 | 0% | 2,710 | 2,820 | +4% | 0 | 0 | — |
case-21 | fail→fail | 8,532 | 5,804 | -32% | 1 | 1 | 0% | 1,362 | 1,553 | +14% | 0 | 0 | — |
case-22 | pass→fail | 14,945 | 3,718 | -75% | 1 | 1 | 0% | 2,282 | 1,154 | -49% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +50 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.