clay-incident-runbook

Execute Clay incident response procedures for enrichment failures, credit exhaustion, and data flow outages. Use when Clay enrichments stop working, webhook delivery fails, or CRM sync breaks in production. Trigger with phrases like "clay incident", "clay outage", "clay down", "clay emergency", "clay broken", "clay enrichment stopped".

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-3

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 diagnostics and embedded verification steps, undermined only by a bundle reference that is duplicated inline and never linked from the body.

Suggestions

Link references/implementation-guide.md from the body (e.g., a '## Advanced remediation' section pointing to it) so the bundle is discoverable and clearly signaled.

De-duplicate the triage commands, decision tree, and postmortem template that appear in both the body and implementation-guide.md — keep the concise version in the body and defer the expanded kubectl/secret-rotation details to the reference.

Consider moving the full communication and postmortem templates into the reference file, leaving a one-line pointer in the body to reduce inline boilerplate.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence — a compact overview, an executable triage script, a decision tree, and fill-in templates, with no padding explaining concepts Claude already knows; it earns its tokens rather than being verbose.	3 / 3
Actionability	Provides fully executable bash (specific curl probes with HTTP-code interpretation), concrete UI navigation ('Settings > Plans & Billing', 'Table Settings > Auto-update'), and copy-paste-ready communication/postmortem templates.	3 / 3
Workflow Clarity	A clearly sequenced five-step flow (triage → decision tree → resolutions → communication → postmortem) with a YES/NO branching decision tree and embedded verification checkpoints ('Verify: Send test payload to new webhook URL', 'Test: Run HTTP API column on single row manually').	3 / 3
Progressive Disclosure	The bundle file references/implementation-guide.md exists but is never linked or signaled from the body, and its triage commands, decision tree, and postmortem template are duplicated inline — content that should be separate is inline and the reference is present but not clearly signaled.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, concise description that uses third-person voice, states concrete capabilities, gives an explicit 'Use when' clause, and supplies natural trigger phrases for a well-scoped Clay niche.

Dimension	Reasoning	Score
Specificity	Names the domain (Clay incident response) and enumerates concrete failure scenarios — 'enrichment failures, credit exhaustion, and data flow outages' — matching the multiple-specific-actions anchor rather than the vague 'Names domain and some actions' level below.	3 / 3
Completeness	Explicitly answers both what ('Execute Clay incident response procedures...') and when ('Use when Clay enrichments stop working, webhook delivery fails, or CRM sync breaks in production'), with explicit trigger phrases, satisfying the top anchor.	3 / 3
Trigger Term Quality	Provides natural terms a user would actually say — 'clay incident', 'clay outage', 'clay down', 'clay emergency', 'clay broken', 'clay enrichment stopped' — giving good coverage rather than just 'some relevant keywords'.	3 / 3
Distinctiveness Conflict Risk	Targets a clear Clay-specific niche with distinct 'clay incident/outage/down' triggers, making it unlikely to fire for unrelated skills; not generic like the level-1 example.	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
Path: plugins/saas-packs/clay-pack/skills/clay-incident-runbook/SKILL.md
Commit: 4c47e33

Reviewed: about 11 hours 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.