Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Incident response procedures for Granola meeting capture failures and outages. Use when meetings aren't recording, transcription fails mid-meeting, integrations stop syncing, or the Granola service is down. Trigger: "granola incident", "granola outage", "granola down", "granola not recording", "granola emergency".
.claude/skills/jeremylongshore-granola-incident-runbook/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 99% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 82% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 131% | 0% |
Standard operating procedures for Granola incidents — from individual recording failures to organization-wide outages. Covers triage, remediation, communication, escalation, and post-incident review. Designed for IT admins, team leads, and individual users.
bash# Quick status check curl -s "https://status.granola.ai/api/v2/status.json" 2>/dev/null | python3 -c " import json, sys try: data = json.load(sys.stdin) indicator = data.get('status', {}).get('indicator', 'unknown') desc = data.get('status', {}).get('description', 'Unknown') print(f'Status: {indicator} — {desc}') except: print('Cannot reach status page — possible network issue') " || echo "Network error — check internet connection"
| Severity | Description | Response Time | Example | |----------|-------------|---------------|---------| | P1 Critical | Org-wide outage, data loss risk | Immediate | Granola service down, no one can record | | P2 High | Multiple users affected | < 1 hour | Recording fails for a team, sync broken | | P3 Medium | Single user issue | < 4 hours | One person's transcription stopped | | P4 Low | Minor issue, workaround exists | < 24 hours | UI glitch, slow processing |
Scope assessment questions:
Severity: P3 (single user) or P2 (team-wide)
Immediate actions:
pgrep -l GranolaRoot cause investigation:
Backup: Take manual notes. After fixing, re-record the next meeting.
Severity: P3
Immediate actions:
Root cause: Granola stops transcription after ~15 minutes of no detected audio. Bluetooth devices can cause intermittent dropouts.
Severity: P3
Immediate actions:
If still failing after 30 minutes: The transcript was captured but enhancement may be queued. Submit support ticket with the meeting date/time.
Severity: P3
Immediate actions:
Common causes:
| Integration | Likely Cause | Fix | |-------------|-------------|-----| | Slack | Bot removed from channel | /invite @Granola in the channel | | Notion | Database deleted | Reconnect (new database created) | | HubSpot | OAuth token expired | Reconnect in Settings | | Zapier | Connection expired | Re-authenticate Granola in Zapier |
Severity: P1 Critical
Immediate actions:
:rotating_light: Granola is currently experiencing a service outage.
Status: https://status.granola.ai
Impact: Meeting recordings and AI enhancement are unavailable.
Workaround: Take notes manually in Google Docs or your preferred editor.
I'll update when service is restored.
Next update: [time + 30 min]Level 1: User Self-Service
→ Restart Granola, check permissions, verify audio
→ Time: 5 minutes
Level 2: IT Support / Team Admin
→ Run debug bundle (granola-debug-bundle)
→ Check org-wide status, verify SSO/SCIM
→ Time: 15-30 minutes
Level 3: Granola Support
→ Submit ticket at help.granola.ai
→ Attach debug bundle
→ Enterprise: Priority support, dedicated contact
→ Time: 1-24 hours depending on severity
Level 4: Granola Engineering (P1 only)
→ Escalated by Granola Support for service outages
→ Status page updates provided by Granola teamAfter resolution, document:
markdown## Post-Incident Report **Date:** YYYY-MM-DD **Severity:** P1/P2/P3/P4 **Duration:** [start time] — [resolution time] **Impact:** [# users affected, # meetings missed] **Timeline:** - HH:MM — Issue first reported - HH:MM — Triage and severity assigned - HH:MM — Workaround communicated - HH:MM — Root cause identified - HH:MM — Fix applied / service restored **Root Cause:** [description] **Resolution:** [what fixed it] **Prevention:** [what to change to prevent recurrence] **Action Items:** - [ ] [who] [what] [by when]
| Scenario | First Response | |----------|---------------| | Can't reach status.granola.ai | Check your internet; try from phone network | | Restart doesn't fix recording | Force quit (pkill -9 Granola), clear caches, relaunch | | Multiple users reporting same issue | Likely P1/P2 — check status page, post to team Slack | | Issue persists after all troubleshooting | Create debug bundle, submit to help@granola.ai |
Proceed to granola-data-handling for data export, retention, and GDPR compliance.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 14,798 | 10,725 | -28% | 1 | 1 | 0% | 1,728 | 3,073 | +78% | 0 | 0 | — |
case-02 | fail→pass | 14,971 | 9,185 | -39% | 1 | 1 | 0% | 1,899 | 3,778 | +99% | 0 | 0 | — |
case-03 | fail→fail | 19,916 | 12,202 | -39% | 1 | 1 | 0% | 2,864 | 4,368 | +53% | 0 | 0 | — |
case-04 | pass→pass | 11,511 | 8,724 | -24% | 1 | 1 | 0% | 2,124 | 2,788 | +31% | 0 | 0 | — |
case-05 | fail→pass | 18,224 | 6,519 | -64% | 1 | 1 | 0% | 2,055 | 3,063 | +49% | 0 | 0 | — |
case-06 | fail→pass | 15,038 | 5,099 | -66% | 1 | 1 | 0% | 1,541 | 2,807 | +82% | 0 | 0 | — |
case-07 | pass→pass | 13,516 | 12,203 | -10% | 1 | 1 | 0% | 2,126 | 3,118 | +47% | 0 | 0 | — |
case-08 | pass→pass | 16,078 | 13,713 | -15% | 1 | 1 | 0% | 1,760 | 3,470 | +97% | 0 | 0 | — |
case-09 | fail→pass | 17,188 | 12,089 | -30% | 1 | 1 | 0% | 1,923 | 3,108 | +62% | 0 | 0 | — |
case-10 | pass→pass | 13,454 | 8,684 | -35% | 1 | 1 | 0% | 1,345 | 2,562 | +90% | 0 | 0 | — |
case-11 | fail→pass | 9,631 | 15,299 | +59% | 1 | 1 | 0% | 1,597 | 3,685 | +131% | 0 | 0 | — |
case-12 | pass→pass | 9,230 | 5,772 | -37% | 1 | 1 | 0% | 1,606 | 2,917 | +82% | 0 | 0 | — |
case-13 | fail→fail | 15,582 | 7,779 | -50% | 1 | 1 | 0% | 1,746 | 2,414 | +38% | 0 | 0 | — |
case-14 | fail→pass | 8,185 | 2,331 | -72% | 1 | 1 | 0% | 1,357 | 2,365 | +74% | 0 | 0 | — |
case-15 | pass→pass | 16,653 | 4,221 | -75% | 1 | 1 | 0% | 1,994 | 2,732 | +37% | 0 | 0 | — |
case-16 | pass→pass | 15,433 | 9,725 | -37% | 1 | 1 | 0% | 1,817 | 2,771 | +53% | 0 | 0 | — |
case-17 | fail→pass | 20,092 | 9,577 | -52% | 1 | 1 | 0% | 2,422 | 2,777 | +15% | 0 | 0 | — |
case-18 | pass→pass | 7,666 | 8,243 | +8% | 1 | 1 | 0% | 1,302 | 2,473 | +90% | 0 | 0 | — |
case-19 | fail→pass | 15,708 | 9,811 | -38% | 1 | 1 | 0% | 1,800 | 2,795 | +55% | 0 | 0 | — |
case-20 | fail→fail | 17,685 | 19,580 | +11% | 1 | 1 | 0% | 2,860 | 5,183 | +81% | 0 | 0 | — |
case-21 | pass→pass | 13,884 | 12,169 | -12% | 1 | 1 | 0% | 2,163 | 3,947 | +82% | 0 | 0 | — |
case-22 | pass→pass | 16,583 | 14,047 | -15% | 1 | 1 | 0% | 2,403 | 4,317 | +80% | 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 +36 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.