clay-observability
Monitor Clay enrichment pipeline health, credit consumption, and data quality metrics. Use when setting up dashboards for Clay operations, configuring alerts for credit burn, or tracking enrichment success rates. Trigger with phrases like "clay monitoring", "clay metrics", "clay observability", "monitor clay", "clay alerts", "clay dashboard", "clay credit tracking".
84
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 well-crafted skill description that clearly defines its scope around Clay platform monitoring and observability. It provides specific capabilities, explicit 'Use when' guidance, and a comprehensive list of trigger phrases. The description is concise, uses third-person voice, and carves out a distinct niche that would be easy for Claude to differentiate from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: monitoring pipeline health, credit consumption, data quality metrics, setting up dashboards, configuring alerts for credit burn, and tracking enrichment success rates. | 3 / 3 |
Completeness | Clearly answers both 'what' (monitor pipeline health, credit consumption, data quality metrics) and 'when' (setting up dashboards, configuring alerts, tracking success rates) with explicit trigger phrases listed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'clay monitoring', 'clay metrics', 'clay observability', 'clay alerts', 'clay dashboard', 'clay credit tracking', plus domain terms like 'enrichment', 'credit burn', and 'success rates'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Clay' platform focus combined with monitoring/observability niche. The trigger terms are all Clay-specific, making conflicts with other skills very unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%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, actionable skill with executable code examples covering metrics collection, Prometheus alerting, and reporting. Its main weaknesses are the lack of validation checkpoints in the workflow (e.g., verifying metrics flow before building dashboards) and some verbosity in the full class implementation that could be tightened. The content structure is reasonable but would benefit from offloading the optional Prometheus setup to a referenced file.
Suggestions
Add a validation checkpoint after Step 1 (e.g., 'Send a test webhook payload and verify metrics are recorded correctly before proceeding') to catch instrumentation issues early.
Add a verification step after Step 3 to test alert rules fire correctly (e.g., using Prometheus unit testing or manually triggering thresholds).
Consider moving the Prometheus-specific setup (Steps 2-3) into a separate referenced file since it's marked optional, keeping SKILL.md focused on the core metrics collection and reporting pattern.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary content. The Prerequisites section explaining what you need is somewhat obvious, and the full class implementation with getReport() is verbose when a more focused snippet would suffice. The Prometheus metrics section is well-structured but the dashboard panel YAML is a custom pseudo-format that adds bulk without being directly executable. | 2 / 3 |
Actionability | The skill provides fully executable TypeScript code for metrics collection, real Prometheus alert rules in proper YAML, and concrete metric names/labels. The code is copy-paste ready with proper imports, types, and complete implementations. The dashboard panel config, while not native Grafana JSON, gives specific metric queries and thresholds. | 3 / 3 |
Workflow Clarity | The five steps are clearly sequenced from instrumentation through alerting to reporting, which is logical. However, there are no validation checkpoints — no step to verify metrics are flowing correctly, no way to test alerts before going live, and no feedback loop for when the webhook handler fails to collect metrics. For an observability pipeline where misconfiguration means silent failures, this is a notable gap. | 2 / 3 |
Progressive Disclosure | The content is well-sectioned with clear headers, and the error handling table is a nice touch. However, the Prometheus metrics setup (Step 2) is marked 'Optional' but still takes significant space inline. With no bundle files, the single reference to 'clay-incident-runbook' is unverifiable. The skill could benefit from splitting the Prometheus/Grafana specifics into a separate reference file. | 2 / 3 |
Total | 9 / 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
3a2d27d
- 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.