groq-incident-runbook
Execute Groq incident response: triage, mitigation, fallback, and postmortem. Use when responding to Groq-related outages, investigating errors, or running post-incident reviews for Groq integration failures. Trigger with phrases like "groq incident", "groq outage", "groq down", "groq on-call", "groq emergency", "groq broken".
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 strong skill description that clearly defines its scope (Groq incident response), lists concrete actions (triage, mitigation, fallback, postmortem), and provides explicit trigger guidance with natural user phrases. It follows best practices by using third person voice, including a 'Use when' clause, and enumerating specific trigger terms that minimize ambiguity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: triage, mitigation, fallback, and postmortem. These are distinct, well-defined incident response activities. | 3 / 3 |
Completeness | Clearly answers both 'what' (triage, mitigation, fallback, postmortem for Groq incidents) and 'when' (explicit 'Use when' clause covering outages, error investigation, and post-incident reviews, plus explicit trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'groq incident', 'groq outage', 'groq down', 'groq on-call', 'groq emergency', 'groq broken'. These are realistic phrases someone would use during an incident. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Groq' domain combined with incident response focus. The trigger terms are all Groq-prefixed, making conflicts with other skills very unlikely. | 3 / 3 |
Total | 12 / 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 triage scripts, a clear decision tree, and concrete mitigation code. Its main weakness is length — the communication templates and postmortem template are generic incident management patterns that add bulk without Groq-specific value, and the overall content would benefit from splitting into a concise overview with references to detailed sub-documents.
Suggestions
Move communication templates and postmortem template to a separate referenced file (e.g., `groq-incident-templates.md`) to reduce the main skill's token footprint.
Trim the severity level table — Claude understands P1-P4 conventions; a one-line summary per level would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable scripts and decision trees, but includes some sections Claude doesn't need spelled out (communication templates, postmortem templates are fairly generic incident management boilerplate). The severity level table and some explanatory text could be tightened. | 2 / 3 |
Actionability | Excellent actionability throughout — the triage script is fully executable bash, the fallback TypeScript code is copy-paste ready, the decision tree gives specific commands (dig, curl), and the evidence collection script is concrete and complete with proper redaction. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced: Quick Triage → Decision Tree → Immediate Mitigations → Communication → Post-Incident. The decision tree provides explicit branching logic with validation at each step, and the triage script serves as a diagnostic checkpoint before taking action. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's quite long (~200 lines of substantive content) and could benefit from splitting the postmortem template, communication templates, and detailed mitigation scripts into separate referenced files. Only one external reference exists (groq-data-handling). | 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
4dee593
- 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.