Agent skill

Clay Performance Tuning

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Optimize Clay table enrichment throughput, reduce processing time, and improve hit rates.

MITAuto-check passed

Install Clay Performance Tuning

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill clay-performance-tuning -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace clay-performance-tuning --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/clay-performance-tuning .claude/skills/clay-performance-tuning && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
clay-performance-tuning
GitHub stars
2.8k
Token cost
~2k tokens
SKILL.md length
442 words
Files
1
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Optimize Clay table enrichment throughput, reduce processing time, and improve hit rates.

  • Works in 6 steps: Order Enrichment Columns by Speed → Add Conditional Run Rules → Optimize Input Data Before Import → …
  • Experiencing slow enrichment
  • SKILL.md covers Overview, Prerequisites, Instructions and Error Handling, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Clay Performance Tuning is an agent skill from jeremylongshore/tons-of-skills-marketplace. Optimize Clay table enrichment throughput, reduce processing time, and improve hit rates. Use when experiencing slow enrichment, poor email find rates, or needing to process large tables efficiently. Trigger with phrases like "clay performance", "optimize clay", "clay slow", "clay throughput", "clay fast enrichment", "clay batch optimization".

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Designed for Claude Code

The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Experiencing slow enrichment
  • Poor email find rates
  • Needing to process large tables efficiently
  • With phrases like clay performance

Example prompts

  • “clay performance”
  • “optimize clay”
  • “clay slow”
  • “/clay-performance-tuning”

Requirements

  • Compatibility (from SKILL.md): Designed for Claude Code
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(curl:*)

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Order Enrichment Columns by Speed
  2. Add Conditional Run Rules
  3. Optimize Input Data Before Import
  4. Limit Waterfall Depth
  5. Use Table-Level Auto-Update Controls
  6. Schedule Large Imports for Off-Peak

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Bash(curl:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript and yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • university.clay.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Designed for Claude Code

    From compatibility in the SKILL.md frontmatter.

Context cost

Clay Performance Tuning loads about 2k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 442 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 442 words, ~2,025 tokens.

Download SKILL.mdSave it as .claude/skills/clay-performance-tuning/SKILL.md (or your agent's skills folder).
name
clay-performance-tuning
description
Optimize Clay table enrichment throughput, reduce processing time, and improve hit rates. Use when experiencing slow enrichment, poor email find rates, or needing to process large tables efficiently. Trigger with phrases like "clay performance", "optimize clay", "clay slow", "clay throughput", "clay fast enrichment", "clay batch optimization".
allowed-tools
Read, Write, Edit, Bash(curl:*)
compatibility
Designed for Claude Code
version
1.14.0
license
MIT
author
Jeremy Longshore <jeremy@intentsolutions.io>
tags
saas, clay, api, performance

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 TypeTypical SpeedPosition
Company lookup (Clearbit)~100msFirst (fastest)
Email finder (single provider)~200msSecond
Email waterfall (multi-provider)1-10sMiddle
Claygent AI research5-30sLater
HTTP API (outbound call)VariableLast
AI text generation2-5sAfter 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:

# In Clay column settings > "Only run if" condition:

# Email waterfall: only run if we have enough input data
ISNOTEMPTY(domain) AND ISNOTEMPTY(first_name) AND ISNOTEMPTY(last_name)

# Claygent: only run for high-value prospects
ICP Score >= 60 AND ISNOTEMPTY(Company Name)

# CRM push: only run for enriched, qualified leads
ICP Score >= 70 AND ISNOTEMPTY(Work Email)

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
typescript
// src/clay/pre-process.ts — clean data before sending to Clay
interface RawLead {
  domain?: string;
  email?: string;
  first_name?: string;
  last_name?: string;
}

function preProcessForClay(rows: RawLead[]): {
  ready: RawLead[];
  filtered: { row: RawLead; reason: string }[];
  stats: { total: number; ready: number; filtered: number; deduped: number };
} {
  const personalDomains = new Set([
    'gmail.com', 'yahoo.com', 'hotmail.com', 'outlook.com',
    'icloud.com', 'aol.com', 'protonmail.com', 'mail.com',
  ]);

  const seen = new Set<string>();
  const ready: RawLead[] = [];
  const filtered: { row: RawLead; reason: string }[] = [];
  let deduped = 0;

  for (const row of rows) {
    // Normalize domain
    const domain = row.domain?.toLowerCase().trim().replace(/^(https?:\/\/)?(www\.)?/, '').replace(/\/.*$/, '');

    // Filter invalid
    if (!domain || !domain.includes('.')) {
      filtered.push({ row, reason: 'invalid domain' });
      continue;
    }
    if (personalDomains.has(domain)) {
      filtered.push({ row, reason: 'personal email domain' });
      continue;
    }
    if (!row.first_name?.trim() || !row.last_name?.trim()) {
      filtered.push({ row, reason: 'missing name' });
      continue;
    }

    // Deduplicate
    const key = `${domain}:${row.first_name?.toLowerCase()}:${row.last_name?.toLowerCase()}`;
    if (seen.has(key)) {
      deduped++;
      continue;
    }
    seen.add(key);

    ready.push({ ...row, domain });
  }

  return {
    ready,
    filtered,
    stats: {
      total: rows.length,
      ready: ready.length,
      filtered: filtered.length,
      deduped,
    },
  };
}

// Usage
const { ready, stats } = preProcessForClay(rawLeads);
console.log(`Pre-processing: ${stats.total} total -> ${stats.ready} ready (${stats.filtered} filtered, ${stats.deduped} deduped)`);
// Typical result: 30-50% of rows filtered, saving that many credits
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:

yaml
# Before: 5-provider waterfall (slow, expensive)
# Each provider: ~2 credits, ~2s
# Worst case: 10 credits, 10s per row
waterfall_deep:
  providers: [apollo, hunter, prospeo, dropcontact, findymail]
  max_time_per_row: "~10s"
  max_credits_per_row: 10

# After: 2-provider waterfall (fast, cheap)
# Covers 80%+ of findable emails with 2 providers
waterfall_optimized:
  providers: [apollo, hunter]
  max_time_per_row: "~4s"
  max_credits_per_row: 4
  coverage_loss: "~5-10%"

Rule of thumb: Apollo + one backup provider covers 80-85% of findable work emails. Adding more providers gives diminishing returns.

Step 5: Use Table-Level Auto-Update Controls
yaml
# Table Settings in Clay UI:
table_auto_update: ON   # Parent switch: if OFF, nothing auto-runs
column_settings:
  company_lookup:
    auto_run: ON          # Runs on every new row
  email_waterfall:
    auto_run: ON          # Runs on every new row (if condition met)
    condition: "ISNOTEMPTY(domain)"
  claygent_research:
    auto_run: OFF         # Manual trigger only (expensive)
  crm_push:
    auto_run: ON          # Auto-push qualified leads
    condition: "ICP Score >= 70"
Step 6: Schedule Large Imports for Off-Peak

Clay's enrichment providers respond faster during off-peak hours (US nighttime):

typescript
// src/clay/scheduler.ts
function shouldProcessNow(rowCount: number): { proceed: boolean; reason: string } {
  const hour = new Date().getUTCHours();
  const isOffPeak = hour >= 2 && hour <= 8; // 2am-8am UTC

  if (rowCount < 100) {
    return { proceed: true, reason: 'Small batch — process anytime' };
  }

  if (rowCount >= 1000 && !isOffPeak) {
    return {
      proceed: false,
      reason: `Large batch (${rowCount} rows). Schedule for 02:00-08:00 UTC for faster provider responses.`,
    };
  }

  return { proceed: true, reason: isOffPeak ? 'Off-peak — optimal time' : 'Medium batch — acceptable' };
}
Show full SKILL.md (183 more words)Show less

Error Handling

IssueCauseSolution
Table stuck processingProvider rate limit hitWait for reset or reduce concurrency
Slow enrichment (>10s/row)Deep waterfall (5+ providers)Reduce to 2-3 providers
Low hit rate (<40%)Bad input dataPre-validate and filter before import
Credits burning with no resultsNo conditional run rulesAdd "Only run if" conditions to columns
Enrichment re-runs on editTable auto-update triggeredTurn off auto-update during bulk edits

Output

Produce a reviewed optimization record with table scope, baseline volume and credit use, selected conditions/waterfall, expected and observed throughput, data-quality impact, owner, and rollback threshold. Avoid representing provider or credit-saving estimates as guaranteed results; confirm them with observed workspace telemetry before expanding the rollout.

Examples

In a staging table, add a conditional run for rows with a valid business email and limit the waterfall to two providers, then compare hit rate, cost, and latency to the prior baseline. Keep the former table configuration available; restore it if qualification quality or downstream CRM coverage drops.

Resources

Next Steps

For cost optimization, see clay-cost-tuning.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/clay-performance-tuning of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287

Compare with similar skills

Clay Performance Tuning next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Clay Performance Tuning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Clay Performance Tuning this skilljeremylongshore/tons-of-skills-marketplace2.8k—~2kAutomated safety check: PassMIT
SQL Optimizationgithub/awesome-copilot40k2 repos~2.3kAutomated safety check: PassMIT
Database Optimizerdavila7/claude-code-templates33k8 repos~2.5kAutomated safety check: PassMIT
Postgresql Optimizationdavila7/claude-code-templates33k4 repos~951Automated safety check: PassMIT
Data Table Managern8n-io/n8n207k—~2.3kAutomated safety check: PassCustom licence
Agent Performance Optimizerruvnet/ruflo74k2 repos~3.6kAutomated safety check: PassMIT

Similar skills

  • SQL Optimization

    github/awesome-copilot

    Official

    Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across all SQL databases (MySQL, PostgreSQL, SQL Server…

    40k GitHub starsUsed in 2 repos~2.3k tokens
    DatabasesAuto-check passed
  • Database Optimizer

    davila7/claude-code-templates

    Expert database optimizer specializing in modern performance tuning, query optimization, and scalable architectures.

    33k GitHub starsUsed in 8 repos~2.5k tokens
    DatabasesAuto-check passed
  • Postgresql Optimization

    davila7/claude-code-templates

    PostgreSQL database optimization workflow for query tuning, indexing strategies, performance analysis, and production database management.

    33k GitHub starsUsed in 4 repos~951 tokens
    DatabasesAuto-check passed
  • Official

    Load before calling data-tables or parse-file. An agent skill from n8n-io/n8n.

    207k GitHub stars~2.3k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Agent skill for performance-optimizer - invoke with $agent-performance-optimizer

    74k GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check passed
  • Prompt Optimizer

    affaan-m/ECC

    分析原始提示,识别意图和差距,匹配ECC组件(技能/命令/代理/钩子),并输出一个可直接粘贴的优化提示。仅提供咨询角色——绝不自行执行任务。触发时机:当用户说“优化提示”、“改进我的提示”、“如何编写提示”、“帮我优化这个指令”或明确要求提高提示质量时。中文等效表达同样触发:“优化prompt”、“改进prompt”、“怎么写prompt”、“帮我优化这个指令”。不触发时机:当用户希望直接执行任…

    277k GitHub starsUsed in 2 repos~2.4k tokens
    DevelopmentAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Questions about Clay Performance Tuning

What does Clay Performance Tuning do?

Optimize Clay table enrichment throughput, reduce processing time, and improve hit rates. Clay Performance Tuning is an agent skill from jeremylongshore/tons-of-skills-marketplace. Optimize Clay table enrichment throughput, reduce processing time, and improve hit rates.

When should I use Clay Performance Tuning?

Clay Performance Tuning fits situations like: experiencing slow enrichment; poor email find rates; needing to process large tables efficiently; with phrases like clay performance.

How do I install Clay Performance Tuning in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill clay-performance-tuning -a claude-code`. Or copy the skill folder (skills/.curated/clay-performance-tuning in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/clay-performance-tuning in your project. Claude Code loads it when a task matches its description.

How do I install Clay Performance Tuning in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill clay-performance-tuning -a codex`. Or copy the skill folder (skills/.curated/clay-performance-tuning in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/clay-performance-tuning in your project. Codex loads it when a task matches its description.

Can I use Clay Performance Tuning in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill clay-performance-tuning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clay-performance-tuning, .gemini/skills/clay-performance-tuning, .github/skills/clay-performance-tuning and .opencode/skills/clay-performance-tuning in your project.

What does Clay Performance Tuning need to run?

SKILL.md names no scripts, command-line tools or credentials: Clay Performance Tuning is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash(curl:*). Compatibility (from SKILL.md): Designed for Claude Code.

Does Clay Performance Tuning access the network?

SKILL.md names 1 domain. As links in the text: university.clay.com. This is read from the text; nothing was executed.

Is Clay Performance Tuning safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Clay Performance Tuning use?

Clay Performance Tuning is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Clay Performance Tuning use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Clay Performance Tuning?

Skills that share tags, products or a category with Clay Performance Tuning: SQL Optimization (github/awesome-copilot, 40k stars), Database Optimizer (davila7/claude-code-templates, 33k stars), Postgresql Optimization (davila7/claude-code-templates, 33k stars) and Data Table Manager (n8n-io/n8n, 207k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Clay Performance Tuning?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.