Skip to main content
deepgram-incident-runbook Execute Deepgram incident response procedures for production issues.
Use when handling Deepgram outages, debugging production failures,
or responding to service degradation.
Trigger: "deepgram incident", "deepgram outage", "deepgram production issue",
"deepgram down", "deepgram emergency", "deepgram 500 errors".
설치로 이동 Skills Marketplace 커뮤니티가 만든 AI 스킬을 발견하고 탐색하세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/jeremylongshore/claude-code-plugins-plus-skills --skill deepgram-incident-runbook명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Zip 다운로드 다운로드 중... 이 저장소의 다른 Skills Implement user sign-up and sign-in flows with Clerk.
Use when building authentication UI, customizing sign-in experience,
or implementing OAuth social login.
Trigger with phrases like "clerk sign-in", "clerk sign-up",
"clerk login flow", "clerk OAuth", "clerk social login".
Implement session management and middleware with Clerk.
Use when managing user sessions, configuring route protection,
or implementing token refresh and custom JWT templates.
Trigger with phrases like "clerk session", "clerk middleware",
"clerk route protection", "clerk token", "clerk JWT".
Configure enterprise SSO, role-based access control, and organization management.
Use when implementing SSO integration, configuring role-based permissions,
or setting up organization-level controls.
Trigger with phrases like "clerk SSO", "clerk RBAC",
"clerk enterprise", "clerk roles", "clerk permissions", "clerk organizations".
jeremylongshore
jeremylongshore/claude-code-plugins-plus-skills
GitHub 저장소 열기 name deepgram-incident-runbook description Execute Deepgram incident response procedures for production issues.
Use when handling Deepgram outages, debugging production failures,
or responding to service degradation.
Trigger: "deepgram incident", "deepgram outage", "deepgram production issue",
"deepgram down", "deepgram emergency", "deepgram 500 errors".
allowed-tools Read, Write, Edit, Bash(curl:*), Bash(kubectl:*) version 1.13.0 license MIT author Jeremy Longshore <jeremy@intentsolutions.io> tags ["saas","deepgram","debugging","incident-response"] compatibility Designed for Claude Code, also compatible with Codex and OpenClaw
Deepgram Incident Runbook
Overview
Standardized incident response for Deepgram-related production issues. Includes automated triage script, severity classification (SEV1-SEV4), immediate mitigation actions, fallback activation, and post-incident review template.
Quick Reference
Severity Classification
Level Definition Response Time Example SEV1 Complete outage, all transcriptions failing Immediate 100% 5xx errors SEV2 Major degradation, >50% error rate < 15 min Specific model failing SEV3 Minor degradation, elevated latency < 1 hour P95 > 30s SEV4 Single feature affected, cosmetic < 24 hours Diarization inaccurate
Instructions
Step 1: Automated Triage (First 5 Minutes)
#!/bin/bash
set -euo pipefail
echo "=== Deepgram Incident Triage ==="
echo "Timestamp: $(date -u +%Y-%m-%dT%H:%M:%SZ) "
echo ""
echo "--- Status Page ---"
STATUS=$(curl -s -o /dev/null -w "%{http_code}" https://status.deepgram.com)
echo "Status page: HTTP
$STATUS
echo
""
echo
"--- API Connectivity ---"
"\nHTTP: %{http_code} | Latency: %{time_total}s\n"
'https://api.deepgram.com/v1/projects'
"Authorization: Token $DEEPGRAM_API_KEY "
head
echo
""
echo
"--- Transcription Test ---"
"\n%{http_code}"
'https://api.deepgram.com/v1/listen?model=nova-3&smart_format=true'
"Authorization: Token $DEEPGRAM_API_KEY "
"Content-Type: application/json"
'{"url":"https://static.deepgram.com/examples/Bueller-Life-moves-702702706.wav"}'
echo
"$RESULT "
tail
echo
"Transcription: HTTP $HTTP_CODE "
echo
""
echo
"--- Model Tests ---"
for
in
do
"%{http_code}"
"https://api.deepgram.com/v1/listen?model=$MODEL "
"Authorization: Token $DEEPGRAM_API_KEY "
"Content-Type: application/json"
'{"url":"https://static.deepgram.com/examples/Bueller-Life-moves-702702706.wav"}'
echo
"$MODEL : HTTP $CODE "
done
echo
""
echo
"--- Internal Metrics ---"
echo
"Health endpoint unavailable"
Step 2: SEV1 Response (Complete Outage) import { createClient } from '@deepgram/sdk' ;
class DeepgramFallbackService {
private primaryClient : ReturnType <typeof createClient>;
private isInFallbackMode = false ;
private failedRequests : Array <{ url : string ; options : any ; timestamp : Date }> = [];
constructor (apiKey : string this .primaryClient = createClient (apiKey);
}
async transcribe (url : string , options : any if (this .isInFallbackMode ) {
return this .handleFallback (url, options);
}
try {
const { result, error } = await this .primaryClient .listen .prerecorded .transcribeUrl (
{ url }, options
);
if (error) throw error;
return { source : 'deepgram' , result };
} catch (err) {
console .error ('Deepgram failed, entering fallback mode' );
this .isInFallbackMode = true ;
return this .handleFallback (url, options);
}
}
private handleFallback (url : string , options : any this .failedRequests .push ({ url, options, timestamp : new Date () });
console .warn (`Queued for replay: ${url} (${this .failedRequests.length} in queue)` );
return {
source : 'fallback' ,
message : 'Transcription queued — Deepgram is currently unavailable' ,
queuePosition : this .failedRequests .length ,
};
}
async replayQueue (console .log (`Replaying ${this .failedRequests.length} queued requests...` );
const queue = [...this .failedRequests ];
this .failedRequests = [];
this .isInFallbackMode = false ;
for (const req of queue) {
try {
await this .transcribe (req.url , req.options );
console .log (`Replayed: ${req.url} ` );
} catch (err : any ) {
console .error (`Replay failed: ${req.url} — ${err.message} ` );
this .failedRequests .push (req);
}
}
}
}
Step 3: SEV2 Response (Partial Degradation) async function mitigateSev2 (const client = createClient (process.env .DEEPGRAM_API_KEY !);
const testUrl = 'https://static.deepgram.com/examples/Bueller-Life-moves-702702706.wav' ;
console .log ('=== SEV2 Mitigation ===' );
const models = ['nova-3' , 'nova-2' , 'base' , 'whisper-large' ] as const ;
const working : string [] = [];
const broken : string [] = [];
for (const model of models) {
try {
const { error } = await client.listen .prerecorded .transcribeUrl (
{ url : testUrl }, { model }
);
if (error) throw error;
working.push (model);
console .log (` [OK] ${model} ` );
} catch {
broken.push (model);
console .log (` [FAIL] ${model} ` );
}
}
console .log (`\nWorking models: ${working.join(', ' )} ` );
console .log (`Broken models: ${broken.join(', ' )} ` );
if (working.length > 0 ) {
console .log (`\nAction: Switch to ${working[0 ]} until ${broken.join(', ' )} recovers` );
} else {
console .log ('\nAction: All models failing — escalate to SEV1' );
}
const features = [
{ name : 'diarize' , opts : { diarize : true } },
{ name : 'smart_format' , opts : { smart_format : true } },
{ name : 'utterances' , opts : { utterances : true } },
];
console .log ('\n--- Feature Tests ---' );
for (const { name, opts } of features) {
try {
const { error } = await client.listen .prerecorded .transcribeUrl (
{ url : testUrl }, { model : working[0 ] ?? 'nova-3' , ...opts }
);
console .log (` [${error ? 'FAIL' : 'OK' } ] ${name} ` );
} catch {
console .log (` [FAIL] ${name} ` );
}
}
}
Step 4: SEV3/SEV4 Mitigation
function configureSev3Mitigation (return {
timeout : 60000 ,
maxRetries : 5 ,
model : 'nova-2' ,
diarize : false ,
smart_format : true ,
utterances : false ,
summarize : false ,
detect_topics : false ,
};
}
function configureSev4Mitigation (brokenFeature : string const overrides : Record <string , any > = {};
overrides[brokenFeature] = false ;
console .log (`Disabled ${brokenFeature} — filing Deepgram support ticket` );
return overrides;
}
Step 5: Post-Incident Review Template ## Deepgram Incident Report
**Date:** YYYY-MM-DD
**Duration:** HH:MM start — HH:MM end (X minutes total)
**Severity:** SEV1/2/3/4
**On-Call:** [Name]
### Timeline
| Time (UTC) | Event |
|------------|-------|
| HH:MM | Alert fired: [alert name] |
| HH:MM | On-call acknowledged |
| HH:MM | Triage completed, classified as SEV[N] |
| HH:MM | Mitigation applied: [action taken] |
| HH:MM | Service restored |
| HH:MM | All-clear confirmed |
### Impact
- **Failed requests:** N
- **Affected users:** N
- **Revenue impact:** $X
- **SLA impact:** X minutes of downtime
### Root Cause
[Description of root cause — Deepgram outage / configuration issue / etc.]
### What Went Well
- [Item 1]
- [Item 2]
### What Could Be Improved
- [Item 1]
- [Item 2]
### Action Items
| Action | Owner | Due Date |
|--------|-------|----------|
| [Action 1] | [Name] | YYYY-MM-DD |
| [Action 2] | [Name] | YYYY-MM-DD |
Step 6: Escalation Matrix Level Contact When L1 On-call engineer Alert fires L2 Team lead 15 min without resolution L3 Deepgram support (support@deepgram.com ) Confirmed Deepgram-side issue L4 Engineering director SEV1 > 1 hour
Output
Automated triage script (bash, runs in <30s)
SEV1 fallback service with request queue and replay
SEV2 model/feature diagnosis and auto-fallback
SEV3/SEV4 mitigation configurations
Post-incident review template
Error Handling Issue Cause Solution Triage script can't reach Deepgram Network or DNS Check outbound HTTPS to api.deepgram.com Fallback queue growing Extended outage Alert if queue > 1000, consider alternate STT Replay failures Audio URLs expired Re-fetch audio from source before replay Status page shows green but API fails Partial outage not yet reflected Report to Deepgram support immediately
Resources 