Agent skill · data analytics · jeremylongshore
clay-performance-tuning
Optimize Clay table enrichment throughput, reduce processing time, and
Why this skill is useful
Provides specific optimization techniques and scripts for enhancing Clay table enrichment performance that the AI wouldn't reliably generate on its own.
What it needs
Requires clay account access. About 4k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Clay Performance Tuning Overview Optimize Clay table processing speed, enrichment hit rates, and credit efficiency. Clay processes enrichment columns sequentially per row, and each enrichment column makes external API calls. Performance tuning focuses on reducing wasted enrichments, ordering columns optimally, and managing table auto-run behavior. Prerequisites Clay table with enrichment columns configured Understanding of which providers are in your waterfall Access to Clay table settings and column configuration Instructions Step 1: Order Enrichment Columns by Speed Clay runs enrichment columns left-to-right. Place fast columns first: Column Type Typical Speed Position ------------- --------------- ---------- Company lookup (Clearbit) ~100ms First (fastest) Email finder (single provider) ~200ms Second Email waterfall (multi-provider) 1-10s Middle Claygent AI research 5-30s Later HTTP API (outbound call) Variable Last AI text generation 2-5s After Claygent Why order matters: Fast columns populate data that slow columns may need as input (e.g., company name feeds into Claygent research prompt). Step 2: Add Conditional Run Rules Prevent enrichments from running on rows that won't yield results: This prevents: Waterfall enrichment on rows with missing domains (wasted credits) Claygent research on low-value prospects (expensive AI credits) CRM pushes for incomplete records Step 3: Optimize Input Data Before Import Step 4: Limit Waterfall Depth Each additional waterfall provider adds 1-5 seconds per row and burns credits if the previous providers already found data: Rule of thumb: Apollo + one backup provider covers 80-85% of findable work emails. Adding more providers gives diminishing returns. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/clay-performance-tuning