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".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description with strong trigger terms and clear completeness. Its main weakness is that the 'what' portion could be more specific about the concrete actions involved in incident response (e.g., checking logs, restarting services, escalation steps) rather than using the somewhat abstract phrase 'incident response procedures'. The explicit trigger term list is a notable strength.
Suggestions
Replace the abstract 'execute incident response procedures' with specific concrete actions like 'check service health, review error logs, diagnose API failures, coordinate escalation, and apply known fixes for Deepgram production issues'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Deepgram incident response) and a general action (execute incident response procedures), but doesn't list specific concrete actions like 'check service health endpoints, review error logs, restart services, escalate to on-call engineers'. The phrase 'incident response procedures' is somewhat abstract. | 2 / 3 |
Completeness | Clearly answers both 'what' (execute Deepgram incident response procedures for production issues) and 'when' (handling outages, debugging production failures, responding to service degradation) with explicit trigger terms listed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'deepgram incident', 'deepgram outage', 'deepgram down', 'deepgram 500 errors', 'deepgram emergency', and 'deepgram production issue'. These are terms users would naturally use when experiencing Deepgram production problems. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific vendor name 'Deepgram' combined with incident response context. Very unlikely to conflict with other skills unless there are multiple Deepgram-related skills, and even then the 'incident/outage/production' focus narrows it clearly. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable incident runbook with executable code for every severity level and a clear escalation workflow. Its main weakness is that it's quite long as a single file — the full TypeScript classes and bash scripts inline make it token-heavy, and the post-incident template could be a separate referenced file. Overall it provides excellent operational guidance with concrete, copy-paste-ready code.
Suggestions
Extract the full DeepgramFallbackService class, triage bash script, and post-incident template into separate referenced files (e.g., TRIAGE.sh, FALLBACK_SERVICE.ts, POST_INCIDENT_TEMPLATE.md) to improve progressive disclosure and reduce token cost.
Trim the SEV2 mitigation code slightly — the feature testing loop could be condensed since the pattern is identical to the model testing loop above it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some content that could be tightened — the full fallback service class is quite long, and the post-incident template, while useful, adds significant length. However, most content is operational rather than explanatory, and it avoids explaining basic concepts to Claude. | 2 / 3 |
Actionability | Excellent actionability — the triage bash script is fully executable and copy-paste ready, the TypeScript fallback service is complete and functional, model testing code is concrete, and mitigation configurations provide specific values. Every step has concrete, runnable code or specific actions. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced from triage (Step 1) through severity-specific responses (Steps 2-4) to post-incident review (Step 5) and escalation (Step 6). Validation is built into the triage script, the SEV2 response includes diagnostic checks before action, and the fallback service includes replay with error handling. The escalation matrix provides clear time-based checkpoints. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and tables, but it's a monolithic document with ~200+ lines of inline code that could benefit from splitting — e.g., the fallback service class, triage script, and post-incident template could each be separate referenced files. The Resources section at the end provides external links but no internal file references for detailed content. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
70e9fa4
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.