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".
Best use case
clay-observability is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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".
Teams using clay-observability should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/clay-observability/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How clay-observability Compares
| Feature / Agent | clay-observability | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Clay Observability
## Overview
Monitor Clay data enrichment pipeline health across four dimensions: credit consumption velocity, enrichment success rates (hit rates), data quality scores, and CRM sync reliability. Clay's credit-based pricing model makes observability essential for cost control.
## Prerequisites
- Clay account with table access
- Metrics infrastructure (Prometheus/Grafana, Datadog, or custom)
- Webhook receiver that logs enrichment results
- Understanding of your enrichment column configuration
## Instructions
### Step 1: Instrument Your Clay Webhook Handler
```typescript
// src/clay/metrics.ts — collect metrics from enriched data flowing back from Clay
interface ClayMetrics {
enrichmentsReceived: number;
enrichmentsWithEmail: number;
enrichmentsWithCompany: number;
enrichmentsWithPhone: number;
estimatedCreditsUsed: number;
averageICPScore: number;
leadsTier: { A: number; B: number; C: number; D: number };
}
class ClayMetricsCollector {
private metrics: ClayMetrics = {
enrichmentsReceived: 0,
enrichmentsWithEmail: 0,
enrichmentsWithCompany: 0,
enrichmentsWithPhone: 0,
estimatedCreditsUsed: 0,
averageICPScore: 0,
leadsTier: { A: 0, B: 0, C: 0, D: 0 },
};
private scoreSum = 0;
record(lead: Record<string, any>, creditsPerRow: number = 6) {
this.metrics.enrichmentsReceived++;
if (lead.work_email) this.metrics.enrichmentsWithEmail++;
if (lead.company_name) this.metrics.enrichmentsWithCompany++;
if (lead.phone_number) this.metrics.enrichmentsWithPhone++;
this.metrics.estimatedCreditsUsed += creditsPerRow;
const score = lead.icp_score || 0;
this.scoreSum += score;
this.metrics.averageICPScore = this.scoreSum / this.metrics.enrichmentsReceived;
if (score >= 80) this.metrics.leadsTier.A++;
else if (score >= 60) this.metrics.leadsTier.B++;
else if (score >= 40) this.metrics.leadsTier.C++;
else this.metrics.leadsTier.D++;
}
getReport(): string {
const m = this.metrics;
const emailRate = m.enrichmentsReceived > 0
? ((m.enrichmentsWithEmail / m.enrichmentsReceived) * 100).toFixed(1)
: '0';
const companyRate = m.enrichmentsReceived > 0
? ((m.enrichmentsWithCompany / m.enrichmentsReceived) * 100).toFixed(1)
: '0';
return [
`=== Clay Enrichment Report ===`,
`Total processed: ${m.enrichmentsReceived}`,
`Email find rate: ${emailRate}%`,
`Company match rate: ${companyRate}%`,
`Avg ICP score: ${m.averageICPScore.toFixed(1)}`,
`Lead distribution: A=${m.leadsTier.A} B=${m.leadsTier.B} C=${m.leadsTier.C} D=${m.leadsTier.D}`,
`Estimated credits used: ${m.estimatedCreditsUsed}`,
`Cost per email found: ${(m.estimatedCreditsUsed / Math.max(m.enrichmentsWithEmail, 1)).toFixed(1)} credits`,
].join('\n');
}
}
```
### Step 2: Set Up Prometheus Metrics (Optional)
```typescript
// src/clay/prometheus-metrics.ts
import { Counter, Gauge, Histogram } from 'prom-client';
// Counters
const clayEnrichmentsTotal = new Counter({
name: 'clay_enrichments_total',
help: 'Total enrichments received from Clay',
labelNames: ['table', 'status'],
});
const clayCreditsUsed = new Counter({
name: 'clay_credits_used_total',
help: 'Estimated Clay credits consumed',
labelNames: ['table', 'enrichment_type'],
});
// Gauges
const clayHitRate = new Gauge({
name: 'clay_enrichment_hit_rate',
help: 'Enrichment hit rate percentage',
labelNames: ['table', 'field'],
});
const clayCreditBalance = new Gauge({
name: 'clay_credit_balance',
help: 'Remaining Clay credits',
});
const clayICPScore = new Histogram({
name: 'clay_icp_score',
help: 'Distribution of ICP scores',
buckets: [20, 40, 60, 80, 100],
labelNames: ['table'],
});
// Record enrichment
function recordEnrichment(table: string, lead: Record<string, any>) {
clayEnrichmentsTotal.inc({ table, status: lead.work_email ? 'enriched' : 'empty' });
clayCreditsUsed.inc({ table, enrichment_type: 'waterfall' }, 6);
clayICPScore.observe({ table }, lead.icp_score || 0);
}
```
### Step 3: Configure Alerting Rules
```yaml
# prometheus/clay-alerts.yml
groups:
- name: clay-enrichment
rules:
- alert: ClayCreditBurnHigh
expr: rate(clay_credits_used_total[1h]) > 200
for: 15m
labels:
severity: warning
annotations:
summary: "Clay credit burn rate > 200/hour. Monthly projection: {{ $value | humanize }} credits"
- alert: ClayLowEmailHitRate
expr: clay_enrichment_hit_rate{field="email"} < 40
for: 30m
labels:
severity: warning
annotations:
summary: "Email find rate below 40% on table {{ $labels.table }}. Check input data quality."
- alert: ClayCreditBalanceLow
expr: clay_credit_balance < 500
labels:
severity: critical
annotations:
summary: "Clay credit balance below 500. Enrichments will stop when credits run out."
- alert: ClayWebhookFailureRate
expr: rate(clay_enrichments_total{status="error"}[15m]) > 0.1
labels:
severity: warning
annotations:
summary: "Clay webhook callback failure rate > 10%"
```
### Step 4: Build a Dashboard
Key panels for a Clay observability dashboard:
```yaml
dashboard_panels:
row_1:
- name: "Credit Balance"
type: gauge
metric: clay_credit_balance
thresholds: [500, 1000, 5000]
- name: "Credits Used Today"
type: stat
metric: increase(clay_credits_used_total[24h])
- name: "Email Hit Rate"
type: gauge
metric: clay_enrichment_hit_rate{field="email"}
thresholds: [40, 60, 80]
row_2:
- name: "Credit Burn Rate (hourly)"
type: timeseries
metric: rate(clay_credits_used_total[1h])
- name: "ICP Score Distribution"
type: histogram
metric: clay_icp_score
row_3:
- name: "Lead Tier Breakdown"
type: piechart
metric: clay_enrichments_total by (tier)
- name: "Cost per Enriched Lead"
type: stat
metric: clay_credits_used_total / clay_enrichments_total{status="enriched"}
```
### Step 5: Daily Summary Report
```typescript
// src/clay/daily-report.ts — generate daily enrichment summary
function generateDailyReport(collector: ClayMetricsCollector): void {
console.log(collector.getReport());
// Post to Slack
if (process.env.SLACK_WEBHOOK_URL) {
fetch(process.env.SLACK_WEBHOOK_URL, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
text: `*Daily Clay Enrichment Report*\n\`\`\`\n${collector.getReport()}\n\`\`\``,
}),
}).catch(console.error);
}
}
```
## Error Handling
| Issue | Cause | Solution |
|-------|-------|----------|
| Credits depleting fast | High waterfall depth or uncapped tables | Add credit burn alert, reduce waterfall |
| Hit rate near 0% | Invalid input data (personal domains, typos) | Add data quality monitoring, pre-filter |
| Missing metrics | Webhook handler not instrumented | Add metrics collection to callback handler |
| Dashboard shows stale data | Metrics not being pushed | Verify Prometheus scrape config |
## Resources
- [Prometheus Client Libraries](https://prometheus.io/docs/instrumenting/clientlibs/)
- [Grafana Dashboard Examples](https://grafana.com/grafana/dashboards/)
- [Clay University -- Actions & Data Credits](https://university.clay.com/docs/actions-data-credits)
## Next Steps
For incident response, see `clay-incident-runbook`.Related Skills
windsurf-observability
Monitor Windsurf AI adoption, feature usage, and team productivity metrics. Use when tracking AI feature usage, measuring ROI, setting up dashboards, or analyzing Cascade effectiveness across your team. Trigger with phrases like "windsurf monitoring", "windsurf metrics", "windsurf analytics", "windsurf usage", "windsurf adoption".
webflow-observability
Set up observability for Webflow integrations — Prometheus metrics for API calls, OpenTelemetry tracing, structured logging with pino, Grafana dashboards, and alerting for rate limits, errors, and latency. Trigger with phrases like "webflow monitoring", "webflow metrics", "webflow observability", "monitor webflow", "webflow alerts", "webflow tracing".
vercel-observability
Set up Vercel observability with runtime logs, analytics, log drains, and OpenTelemetry tracing. Use when implementing monitoring for Vercel deployments, setting up log drains, or configuring alerting for function errors and performance. Trigger with phrases like "vercel monitoring", "vercel metrics", "vercel observability", "vercel logs", "vercel alerts", "vercel tracing".
veeva-observability
Veeva Vault observability for enterprise operations. Use when implementing advanced Veeva Vault patterns. Trigger: "veeva observability".
vastai-observability
Monitor Vast.ai GPU instance health, utilization, and costs. Use when setting up monitoring dashboards, configuring alerts, or tracking GPU utilization and spending. Trigger with phrases like "vastai monitoring", "vastai metrics", "vastai observability", "monitor vastai", "vastai alerts".
twinmind-observability
Monitor TwinMind transcription quality, meeting coverage, action item extraction rates, and memory vault health. Use when implementing observability, or managing TwinMind meeting AI operations. Trigger with phrases like "twinmind observability", "twinmind observability".
speak-observability
Monitor Speak API health, assessment latency, session metrics, and pronunciation score distributions. Use when implementing observability, or managing Speak language learning platform operations. Trigger with phrases like "speak observability", "speak observability".
snowflake-observability
Set up Snowflake observability using ACCOUNT_USAGE views, alerts, and external monitoring. Use when implementing Snowflake monitoring dashboards, setting up query performance tracking, or configuring alerting for warehouse and pipeline health. Trigger with phrases like "snowflake monitoring", "snowflake metrics", "snowflake observability", "snowflake dashboard", "snowflake alerts".
shopify-observability
Set up observability for Shopify app integrations with query cost tracking, rate limit monitoring, webhook delivery metrics, and structured logging. Trigger with phrases like "shopify monitoring", "shopify metrics", "shopify observability", "monitor shopify API", "shopify alerts", "shopify dashboard".
salesforce-observability
Set up observability for Salesforce integrations with API limit monitoring, error tracking, and alerting. Use when implementing monitoring for Salesforce operations, tracking API consumption, or configuring alerting for Salesforce integration health. Trigger with phrases like "salesforce monitoring", "salesforce metrics", "salesforce observability", "monitor salesforce", "salesforce alerts", "salesforce API usage dashboard".
retellai-observability
Retell AI observability — AI voice agent and phone call automation. Use when working with Retell AI for voice agents, phone calls, or telephony. Trigger with phrases like "retell observability", "retellai-observability", "voice agent".
replit-observability
Monitor Replit deployments with health checks, uptime tracking, resource usage, and alerting. Use when setting up monitoring for Replit apps, building health dashboards, or configuring alerting for deployment health and performance. Trigger with phrases like "replit monitoring", "replit metrics", "replit observability", "monitor replit", "replit alerts", "replit uptime".