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".
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 (Clay incident response), lists specific failure scenarios it handles, and provides explicit trigger guidance with natural user phrases. It uses proper third-person voice and covers both the 'what' and 'when' comprehensively. The description is well-structured and would be easily distinguishable from other skills in a large collection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: incident response procedures for enrichment failures, credit exhaustion, data flow outages, webhook delivery failures, and CRM sync breaks. | 3 / 3 |
Completeness | Clearly answers both 'what' (execute Clay incident response procedures for enrichment failures, credit exhaustion, data flow outages) and 'when' (explicit 'Use when' clause and 'Trigger with phrases like' section). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'clay incident', 'clay outage', 'clay down', 'clay emergency', 'clay broken', 'clay enrichment stopped', plus contextual terms like 'webhook delivery fails' and 'CRM sync breaks'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (Clay platform incident response) with domain-specific triggers that are unlikely to conflict with other skills. | 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 solid incident runbook with strong actionability — the executable triage script, decision tree, and specific resolution steps are excellent. The main weakness is that generic templates (communication, postmortem) and the severity table add bulk without proportional value, since Claude can generate these on demand. The workflow is well-sequenced with appropriate validation checkpoints throughout.
Suggestions
Move the communication template and postmortem template to a separate file (e.g., clay-incident-templates.md) and reference it, keeping the main runbook focused on triage and resolution.
Remove or significantly condense the severity level table — Claude can classify severity from the decision tree context without a formal table definition.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some content that could be tightened — the communication template and postmortem template are generic boilerplate that Claude already knows how to produce, and the severity table's 'Response Time' column adds little actionable value for an AI agent. The triage script and decision tree are well-justified. | 2 / 3 |
Actionability | The triage script is fully executable bash with concrete curl commands, the decision tree provides specific UI navigation paths, and each P1/P2 resolution has numbered concrete steps. The error handling table maps specific symptoms to specific fixes. | 3 / 3 |
Workflow Clarity | The workflow follows a clear sequence: triage → decision tree → resolution → communication → postmortem. The decision tree includes explicit branching with validation at each step (check credits, test webhook, check providers), and resolutions include verification steps (e.g., 'Verify: Send test payload to new webhook URL'). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a logical flow, and references clay-data-handling and clay-observability. However, the communication template, postmortem template, and error handling table could be split into separate reference files to keep the main runbook focused on the critical triage and resolution path. | 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.