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".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

92%

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

A highly actionable, well-sequenced incident runbook with executable commands and clear decision logic. Its main weakness is progressive disclosure: everything lives inline in a single long SKILL.md with no reference files to offload templates or extended procedures.

Suggestions

Move the communication templates and postmortem template into a references/ file (e.g. references/templates.md) and link to it from the body, so SKILL.md stays a lean overview.

Extract the detailed 429/auth-mitigation procedures into a references file, keeping only the decision-tree summary inline, to reduce repetition between the Quick Triage and Immediate Mitigations sections.

Add a short 'References' pointer near the top so the offloaded detail files are clearly signaled and discoverable.

Dimension	Reasoning	Score
Conciseness	Lean, executable content with no concept-explanation fluff; every section (triage, decision tree, mitigations, templates) earns its place, assuming Claude's competence. Minor repetition of the curl command is negligible.	3 / 3
Actionability	Fully executable bash/curl and TypeScript snippets that are copy-paste ready, plus concrete severity tables and decision branches — no pseudocode or abstract direction.	3 / 3
Workflow Clarity	Clear sequence ('Quick Triage (Run First)'), an explicit decision tree with feedback branches, and verification checkpoints (e.g. 'Test new key' before production deploy in key rotation). Not capped because validation is present for the destructive steps.	3 / 3
Progressive Disclosure	Well-organized into clear sections, but the ~240-line skill is monolithic with no bundle files (references/scripts/assets absent) and no offloading of detail content into separate files, so content that could be split (templates, postmortem) is inline rather than one level deep.	2 / 3
	Total	11 / 12 Passed

Description

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.

A strong, well-scoped description that clearly communicates capabilities, trigger conditions, and distinctiveness without fluff. It uses imperative/third-person voice consistent with the good examples and avoids verbosity.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'triage, mitigation, fallback, and postmortem' — matching the anchor for listing several specific actions rather than vague language.	3 / 3
Completeness	Explicitly states what it does ('Execute Groq incident response: triage, mitigation, fallback, and postmortem') and when to use it ('Use when responding to Groq-related outages, investigating errors, or running post-incident reviews'), with explicit trigger phrases.	3 / 3
Trigger Term Quality	Provides natural phrases a user would say ('groq incident', 'groq outage', 'groq down', 'groq on-call', 'groq emergency', 'groq broken'), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Groq incident response) with provider-specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 6e3a65f

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.