Agent skill

Deepgram Incident Runbook

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Execute Deepgram incident response procedures for production issues.

MITAuto-check passedDevOps & Cloud

Install Deepgram Incident Runbook

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill deepgram-incident-runbook -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace deepgram-incident-runbook --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/deepgram-incident-runbook .claude/skills/deepgram-incident-runbook && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deepgram-incident-runbook
GitHub stars
2.8k
Token cost
~2.6k tokens
SKILL.md length
311 words
Files
2 (incl. references)
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Execute Deepgram incident response procedures for production issues.

  • Works in 6 steps: Automated Triage (First 5 Minutes) → SEV1 Response (Complete Outage) → SEV2 Response (Partial Degradation) → …
  • Handling Deepgram outages
  • SKILL.md covers Prerequisites, Examples, Overview and Quick Reference, plus 5 more sections
  • Calls curl; reaches status.deepgram.com and api.deepgram.com; needs DEEPGRAM_API_KEY

What it does

Deepgram Incident Runbook is an agent skill from jeremylongshore/tons-of-skills-marketplace. 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".

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/implementation.md`). Compatibility notes: Designed for Claude Code

It sits in DevOps & Cloud, covering Incident response and Runbooks and postmortems. It works with Deepgram. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Handling Deepgram outages
  • Debugging production failures
  • Responding to service degradation

Example prompts

  • “deepgram incident”
  • “deepgram outage”
  • “deepgram production issue”
  • “/deepgram-incident-runbook”

Requirements

  • A credential in DEEPGRAM_API_KEY
  • Compatibility (from SKILL.md): Designed for Claude Code
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(curl:*), Bash(kubectl:*)

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Automated Triage (First 5 Minutes)
  2. SEV1 Response (Complete Outage)
  3. SEV2 Response (Partial Degradation)
  4. SEV3/SEV4 Mitigation
  5. Post-Incident Review Template
  6. Escalation Matrix

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Bash(curl:*)
    • Bash(kubectl:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • status.deepgram.com
    • api.deepgram.com
    • static.deepgram.com

    Also links to:

    • github.com
    • console.deepgram.com
    • developers.deepgram.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • DEEPGRAM_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Designed for Claude Code

    From compatibility in the SKILL.md frontmatter.

Context cost

Deepgram Incident Runbook loads about 2.6k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 311 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 311 words, ~2,627 tokens.

Download SKILL.mdSave it as .claude/skills/deepgram-incident-runbook/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
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:*)
compatibility
Designed for Claude Code
version
1.13.0
license
MIT
author
Jeremy Longshore <jeremy@intentsolutions.io>
tags
saas, deepgram, debugging, incident-response

Deepgram Incident Runbook

Prerequisites

  • An incident ID, commander, affected service/environment, escalation route, and authorized redacted diagnostic access.
  • A data/consent owner and documented safe mitigation or rollback action.

Examples

For elevated transcription errors, declare scope, capture aggregate health and redacted correlation IDs, stabilize with the documented circuit-breaker/rollback, and verify recovery against the SLO. Escalate provider or data-impact incidents through the approved path; do not attach customer audio, transcripts, or credentials to the incident channel.

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

LevelDefinitionResponse TimeExample
SEV1Complete outage, all transcriptions failingImmediate100% 5xx errors
SEV2Major degradation, >50% error rate< 15 minSpecific model failing
SEV3Minor degradation, elevated latency< 1 hourP95 > 30s
SEV4Single feature affected, cosmetic< 24 hoursDiarization inaccurate

Instructions

Step 1: Automated Triage (First 5 Minutes)
bash
#!/bin/bash
set -euo pipefail
echo "=== Deepgram Incident Triage ==="
echo "Timestamp: $(date -u +%Y-%m-%dT%H:%M:%SZ)"
echo ""

# 1. Check Deepgram status page
echo "--- Status Page ---"
STATUS=$(curl -s -o /dev/null -w "%{http_code}" https://status.deepgram.com)
echo "Status page: HTTP $STATUS"

# 2. Test API connectivity
echo ""
echo "--- API Connectivity ---"
curl -s -w "\nHTTP: %{http_code} | Latency: %{time_total}s\n" \
  'https://api.deepgram.com/v1/projects' \
  -H "Authorization: Token $DEEPGRAM_API_KEY" | head -5

# 3. Test transcription
echo ""
echo "--- Transcription Test ---"
RESULT=$(curl -s -w "\n%{http_code}" \
  -X POST 'https://api.deepgram.com/v1/listen?model=nova-3&smart_format=true' \
  -H "Authorization: Token $DEEPGRAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://static.deepgram.com/examples/Bueller-Life-moves-702702706.wav"}')
HTTP_CODE=$(echo "$RESULT" | tail -1)
echo "Transcription: HTTP $HTTP_CODE"

# 4. Test multiple models
echo ""
echo "--- Model Tests ---"
for MODEL in nova-3 nova-2 base; do
  CODE=$(curl -s -o /dev/null -w "%{http_code}" \
    -X POST "https://api.deepgram.com/v1/listen?model=$MODEL" \
    -H "Authorization: Token $DEEPGRAM_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"url":"https://static.deepgram.com/examples/Bueller-Life-moves-702702706.wav"}')
  echo "$MODEL: HTTP $CODE"
done

# 5. Query internal metrics (if available)
echo ""
echo "--- Internal Metrics ---"
curl -s localhost:3000/health 2>/dev/null || echo "Health endpoint unavailable"
Step 2: SEV1 Response (Complete Outage)
typescript
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) {
    // Queue for later replay
    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,
    };
  }

  // Call when Deepgram recovers
  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)
typescript
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 ===');

  // Test each model to find working ones
  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}`);
    }
  }

  // Recommended actions
  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');
  }

  // Test features
  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
typescript
// SEV3: Elevated latency — increase timeouts and enable aggressive retry
function configureSev3Mitigation() {
  return {
    timeout: 60000,          // Increase from 30s to 60s
    maxRetries: 5,           // Increase from 3 to 5
    model: 'nova-2',         // Fallback to proven model
    diarize: false,          // Disable to reduce processing
    smart_format: true,      // Keep basic formatting
    utterances: false,       // Disable to reduce processing
    summarize: false,        // Disable
    detect_topics: false,    // Disable
  };
}

// SEV4: Single feature broken — disable and continue
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
markdown
## 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
LevelContactWhen
L1On-call engineerAlert fires
L2Team lead15 min without resolution
L3Deepgram support (support@deepgram.com)Confirmed Deepgram-side issue
L4Engineering directorSEV1 > 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

IssueCauseSolution
Triage script can't reach DeepgramNetwork or DNSCheck outbound HTTPS to api.deepgram.com
Fallback queue growingExtended outageAlert if queue > 1000, consider alternate STT
Replay failuresAudio URLs expiredRe-fetch audio from source before replay
Status page shows green but API failsPartial outage not yet reflectedReport to Deepgram support immediately

Resources

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/.curated/deepgram-incident-runbook of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • references/implementation.md

Open the folder on GitHubat commit cfae287

Compare with similar skills

Deepgram Incident Runbook next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deepgram Incident Runbook compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deepgram Incident Runbook this skilljeremylongshore/tons-of-skills-marketplace2.8k—~2.6kAutomated safety check: PassMIT
Oncallpigweed-project/pigweed548—~963Automated safety check: PassApache-2.0
Activation Governance Chaos RolloutAli-Marandi/DataSense107—~1.9kAutomated safety check: PassMIT
Incident Response686f6c61/alfred-dev117—~1.1kAutomated safety check: PassMIT
Superset Incident Triagesuperset-sh/superset15k—~1kAutomated safety check: PassCustom licence
Post-Incident DebriefVeryGoodOpenSource/vgv-wingspan109—~1.9kAutomated safety check: PassMIT

Similar skills

  • Oncall

    pigweed-project/pigweed

    Pigweed oncall rotation runbooks and maintenance workflows (such as rolling CIPD client tools for b/315378787).

    548 GitHub stars~963 tokensUpdated today
    DevOps & CloudAuto-check passed
  • Design, validate, and govern fail-closed customer-activation automations that use an Outbox/worker pattern.

    107 GitHub stars~1.9k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • Incident Response

    686f6c61/alfred-dev

    Protocolo de respuesta ante incidentes en produccion: triaje, mitigacion, causa raiz y postmortem.

    117 GitHub stars~1.1k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • Superset Incident Triage

    superset-sh/superset

    Does a read-only first pass on a possible production incident: gathers deploy, Sentry and health-check signals, proposes a severity and status message, then stops for human approval.

    15k GitHub stars~1k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Post-Incident Debrief

    VeryGoodOpenSource/vgv-wingspan

    Produces a blameless post-incident debrief with timeline, root cause and follow-up actions after an outage, failed release or significant bug, while details are fresh.

    109 GitHub stars~1.9k tokensUpdated 4 days ago
    DevOps & CloudAuto-check passed
  • SRE Engineer

    Jeffallan/claude-skills

    Defines SLIs, SLOs and error budgets, and sets up golden-signal monitoring, blameless postmortems, toil automation and chaos experiments for production systems.

    12k GitHub stars~1.7k tokensUpdated 8 days ago
    DevOps & CloudAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Deepgram Incident Runbook

What does Deepgram Incident Runbook do?

Execute Deepgram incident response procedures for production issues. Deepgram Incident Runbook is an agent skill from jeremylongshore/tons-of-skills-marketplace. Execute Deepgram incident response procedures for production issues.

When should I use Deepgram Incident Runbook?

Deepgram Incident Runbook fits situations like: handling Deepgram outages; debugging production failures; responding to service degradation.

How do I install Deepgram Incident Runbook in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill deepgram-incident-runbook -a claude-code`. Or copy the skill folder (skills/.curated/deepgram-incident-runbook in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/deepgram-incident-runbook in your project. Claude Code loads it when a task matches its description.

How do I install Deepgram Incident Runbook in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill deepgram-incident-runbook -a codex`. Or copy the skill folder (skills/.curated/deepgram-incident-runbook in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/deepgram-incident-runbook in your project. Codex loads it when a task matches its description.

Can I use Deepgram Incident Runbook in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill deepgram-incident-runbook -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deepgram-incident-runbook, .gemini/skills/deepgram-incident-runbook, .github/skills/deepgram-incident-runbook and .opencode/skills/deepgram-incident-runbook in your project.

What does Deepgram Incident Runbook need to run?

Going by SKILL.md and its folder, Deepgram Incident Runbook needs the command-line tools its instructions call (curl) and credentials named DEEPGRAM_API_KEY. Our summary lists: A credential in DEEPGRAM_API_KEY. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash(curl:*), Bash(kubectl:*). Compatibility (from SKILL.md): Designed for Claude Code.

Does Deepgram Incident Runbook access the network?

SKILL.md names 6 domains. In commands or code: status.deepgram.com, api.deepgram.com and static.deepgram.com; the agent is likely to contact these when it follows the instructions. As links in the text: github.com, console.deepgram.com and developers.deepgram.com. This is read from the text; nothing was executed.

Is Deepgram Incident Runbook safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deepgram Incident Runbook use?

Deepgram Incident Runbook is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deepgram Incident Runbook use?

About 2.6k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.

What are the alternatives to Deepgram Incident Runbook?

Skills that share tags, products or a category with Deepgram Incident Runbook: Oncall (pigweed-project/pigweed, 548 stars), Activation Governance Chaos Rollout (Ali-Marandi/DataSense, 107 stars), Incident Response (686f6c61/alfred-dev, 117 stars) and Superset Incident Triage (superset-sh/superset, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deepgram Incident Runbook?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.