CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Well-structured incident runbook that keeps the overview lean while routing exact commands to three clearly signaled reference files. The main improvement opportunity is adding an explicit verify-mitigation feedback checkpoint in the inline phase flow.

Suggestions

Add an explicit 'verify the mitigation' checkpoint after the Mitigate phase (e.g. re-run the Quick Triage probe to confirm the fault is resolved before communicating closure), since key rotation and traffic rerouting are destructive/batch-like operations.

Consider trimming the Overview's framing of Groq as 'a third-party inference provider' — Claude already knows this — and lead directly with the response options (wait / fall back to a model / fall back to a provider).

Inline at least one concrete mitigation command (e.g. the fallback-routing invocation or 401 key-rotation curl) so the runbook remains actionable even before opening the references.

DimensionReasoningScore

Conciseness

The body is a lean overview that assumes competence and points detailed material to references; a few framing sentences (e.g. characterizing Groq as a third-party provider) are mildly trimmable but justified.

4 / 5

Actionability

The inline curl probe is fully executable and copy-paste ready, and the five-phase flow points to specific reference files for exact commands; mitigation step execution itself is deferred to references rather than shown inline.

4 / 5

Workflow Clarity

A clear five-phase numbered sequence with an Error Handling table providing escalation checkpoints; the re-triage loop implicitly validates mitigations, though an explicit 'verify mitigation' feedback step is not stated inline.

4 / 5

Progressive Disclosure

A clear overview with three one-level-deep references, each introduced with a one-line content summary and a markdown link, making navigation easy and appropriately split.

5 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: it concisely states the capability, gives an explicit 'Use when' clause, and lists concrete natural-language trigger phrases. It is specific, complete, and clearly distinct from other skills.

DimensionReasoningScore

Specificity

Lists four concrete, specific actions — 'triage, mitigation, fallback, and postmortem' — giving comprehensive coverage of the incident-response domain.

5 / 5

Completeness

Explicitly answers both 'what' (execute Groq incident response: triage/mitigation/fallback/postmortem) and 'when' (Use when responding to Groq-related outages...) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides six natural phrases an on-call user would actually say ('groq incident', 'groq outage', 'groq down', 'groq on-call', 'groq emergency', 'groq broken'), comprehensive coverage.

5 / 5

Distinctiveness Conflict Risk

A clear, narrow niche (Groq-specific incident response) with distinct Groq-prefixed triggers, giving minimal conflict risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.