Agent skill

Clay Reference Architecture

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

Design production Clay enrichment pipelines with table schemas, waterfall patterns, and CRM sync.

MITAuto-check passedSales & Support

Install Clay Reference Architecture

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

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

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace clay-reference-architecture --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-reference-architecture .claude/skills/clay-reference-architecture && 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-reference-architecture
GitHub stars
2.8k
Token cost
~2.1k tokens
SKILL.md length
285 words
Files
3 (incl. references)
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Design production Clay enrichment pipelines with table schemas, waterfall patterns, and CRM sync.

  • Works in 5 steps: Choose Your Integration Pattern → Design Table Schema → Configure Waterfall Pattern → …
  • Architecting new Clay integrations
  • SKILL.md covers Overview, Prerequisites, Instructions and Error Handling, plus 4 more sections
  • Reaches api.hubapi.com

What it does

Clay Reference Architecture is an agent skill from jeremylongshore/tons-of-skills-marketplace. Design production Clay enrichment pipelines with table schemas, waterfall patterns, and CRM sync. Use when architecting new Clay integrations, reviewing data flow design, or establishing enrichment pipeline standards. Trigger with phrases like "clay architecture", "clay best practices", "clay pipeline design", "clay reference", "clay data flow".

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/implementation-guide.md` and `references/implementation.md`). Compatibility notes: Designed for Claude Code

It sits in Sales & Support, covering CRM management. 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

  • Architecting new Clay integrations
  • Reviewing data flow design
  • Establishing enrichment pipeline standards
  • With phrases like clay architecture

Example prompts

  • “clay architecture”
  • “clay best practices”
  • “clay pipeline design”
  • “/clay-reference-architecture”

Requirements

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

Workflow steps

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

  1. Choose Your Integration Pattern
  2. Design Table Schema
  3. Configure Waterfall Pattern
  4. Implement ICP Scoring
  5. CRM Sync Architecture

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
    • Grep

    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 yaml).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.hubapi.com

    Also links to:

    • 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 Reference Architecture loads about 2.1k tokens when it runs, and up to ~4.8k if it reads all its reference files. Until then it costs about 94 tokens; SKILL.md has 285 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.8k

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). 285 words, ~2,082 tokens.

Download SKILL.mdSave it as .claude/skills/clay-reference-architecture/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
clay-reference-architecture
description
Design production Clay enrichment pipelines with table schemas, waterfall patterns, and CRM sync. Use when architecting new Clay integrations, reviewing data flow design, or establishing enrichment pipeline standards. Trigger with phrases like "clay architecture", "clay best practices", "clay pipeline design", "clay reference", "clay data flow".
allowed-tools
Read, Write, Edit, Grep
compatibility
Designed for Claude Code
version
1.14.0
license
MIT
author
Jeremy Longshore <jeremy@intentsolutions.io>
tags
saas, clay, clay-reference

Clay Reference Architecture

Overview

Production architecture for Clay-based lead enrichment and go-to-market data operations. Covers the three integration patterns (webhook-only, webhook + HTTP API, and full Enterprise API), table schema design, and CRM synchronization flows.

Prerequisites

  • Clay account with appropriate plan tier
  • Clear understanding of data volume and enrichment needs
  • CRM integration target (HubSpot, Salesforce, etc.)
  • Defined Ideal Customer Profile (ICP)

Instructions

Step 1: Choose Your Integration Pattern
Pattern A: Webhook-Only (All Plans)
──────────────────────────────────────
Your App ──POST──> Clay Webhook ──> Clay Table ──> Enrichment
                                                      │
                                         Manual export via CSV
                                         or native CRM action

Pattern B: Webhook + HTTP API Callback (Growth+ Plans)
──────────────────────────────────────────────────────
Your App ──POST──> Clay Webhook ──> Clay Table ──> Enrichment
                                                      │
                                                HTTP API Column
                                                      │
                                               POST to your app
                                                      │
                                                  CRM / DB

Pattern C: Full Automation with Enterprise API (Enterprise)
──────────────────────────────────────────────────────────
Your App ──POST──> Clay Webhook ──> Clay Table ──> Enrichment
    │                                                  │
    │                                           HTTP API Column
    │                                                  │
    └──Enterprise API──> Person/Company lookup    POST to your app
                         (lightweight, fast)           │
                                                   CRM / DB
Step 2: Design Table Schema

Standard Lead Enrichment Table:

┌─────────────────────────────────────────────────────────────┐
│ CLAY TABLE: Outbound Leads                                  │
├─────────────┬───────────────┬──────────────────────────────┤
│ Input Cols  │ Enrichment    │ AI + Formula + Output        │
├─────────────┼───────────────┼──────────────────────────────┤
│ domain      │ Company Name  │ ICP Score (formula)          │
│ first_name  │ Employee Count│ Lead Tier (formula: A/B/C)   │
│ last_name   │ Industry      │ Personalized Opener (AI)     │
│ source      │ Tech Stack    │ Recent News (Claygent)       │
│ linkedin_url│ Work Email    │ CRM Push (HTTP API)          │
│             │ Job Title     │ Outreach Push (HTTP API)     │
│             │ Phone Number  │                              │
│             │ LinkedIn URL  │                              │
└─────────────┴───────────────┴──────────────────────────────┘

Column execution order (left to right):
1. Company enrichment (Clearbit) ─ fast, provides context for later columns
2. Person enrichment (Apollo/PDL) ─ medium speed
3. Email waterfall (Apollo > Hunter) ─ conditional: requires domain + name
4. Phone lookup (if needed) ─ conditional: ICP Score >= 80
5. ICP Score formula ─ instant, computes from enriched data
6. Claygent research ─ slow, conditional: ICP Score >= 60
7. AI personalization ─ conditional: ICP Score >= 70
8. CRM push (HTTP API) ─ conditional: ICP Score >= 70 + has email
Step 3: Configure Waterfall Pattern
yaml
# Recommended waterfall configuration
email_waterfall:
  strategy: "cheapest-first, stop-on-match"
  providers:
    - name: apollo
      credits: 2
      coverage: ~70%
      speed: fast
    - name: hunter
      credits: 2
      coverage: ~60%
      speed: fast
  combined_coverage: ~83%
  max_credits: 4

company_enrichment:
  strategy: "single provider"
  provider: clearbit
  credits: 2
  coverage: ~90%
  fallback: apollo (if Clearbit returns empty)

person_enrichment:
  strategy: "primary + fallback"
  providers:
    - name: apollo
      credits: 2
    - name: people_data_labs
      credits: 3
Step 4: Implement ICP Scoring
# Clay Formula Column: ICP Score (0-100)
LET(
  # Company size scoring (0-30)
  size, IF(Employee Count > 1000, 30,
       IF(Employee Count > 200, 25,
       IF(Employee Count > 50, 15,
       IF(Employee Count > 10, 5, 0)))),

  # Industry match (0-30)
  industry, IF(OR(
    Industry = "Software",
    Industry = "Technology",
    Industry = "SaaS",
    Industry = "Information Technology"
  ), 30, IF(OR(
    Industry = "Financial Services",
    Industry = "Healthcare"
  ), 20, 10)),

  # Title seniority (0-25)
  title, IF(OR(
    CONTAINS(Job Title, "CEO"), CONTAINS(Job Title, "CTO"),
    CONTAINS(Job Title, "VP"), CONTAINS(Job Title, "C-Suite")
  ), 25, IF(OR(
    CONTAINS(Job Title, "Director"), CONTAINS(Job Title, "Head of")
  ), 20, IF(
    CONTAINS(Job Title, "Manager"), 10, 5
  ))),

  # Data completeness (0-15)
  data, IF(ISNOTEMPTY(Work Email), 10, 0) +
        IF(ISNOTEMPTY(Phone Number), 5, 0),

  size + industry + title + data
)

# Lead Tier Column
IF(ICP Score >= 80, "A",
IF(ICP Score >= 60, "B",
IF(ICP Score >= 40, "C", "D")))
Step 5: CRM Sync Architecture
yaml
# HubSpot integration via HTTP API column
crm_sync:
  trigger: "ICP Score >= 70 AND ISNOTEMPTY(Work Email)"
  method: POST
  url: "https://api.hubapi.com/crm/v3/objects/contacts"
  dedup_key: email  # Prevent duplicate contacts
  field_mapping:
    email: "{{Work Email}}"
    firstname: "{{first_name}}"
    lastname: "{{last_name}}"
    company: "{{Company Name}}"
    jobtitle: "{{Job Title}}"
    hs_lead_status: "NEW"
    clay_icp_score: "{{ICP Score}}"
    clay_enrichment_date: "{{_clay_enriched_at}}"

# Alternative: Use Clay's native HubSpot/Salesforce action columns
# (simpler setup, fewer credits, built-in dedup)
native_crm_action:
  type: "HubSpot: Create/Update Contact"
  dedup: "Match on email"
  auto_run: true
  condition: "ICP Score >= 70"

Error Handling

IssueCauseSolution
Enrichment credits exhaustedToo many lookups per rowUse conditional runs, connect own API keys
Duplicate CRM recordsNo dedup key in CRM pushUse email as unique identifier
Low email coverageSingle provider waterfallAdd second provider (Apollo + Hunter)
Slow table processingToo many enrichment columnsAdd conditional runs, order by speed
Stale enrichment dataNo re-enrichment scheduleRe-run quarterly on existing contacts

Output

Document the approved lead-enrichment architecture: data sources and purposes, provider and CRM boundaries, deduplication key, qualification policy, retention and access controls, monitoring, cost guardrails, and incident/rollback owner. Treat a table or CRM sync as production-ready only after its observed records, permissions, and failure behavior match the reviewed design.

Examples

Build a staging table with synthetic leads, require a valid email and approved ICP threshold before any CRM action, and prove that repeated events update the same CRM record rather than creating duplicates. If enrichment quality or the consent basis is unclear, suppress sync and resolve the data-policy decision before importing the source to production.

Resources

Next Steps

For multi-environment configuration, see clay-multi-env-setup.

© 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

SKILL.md and 2 other files (references) in skills/.curated/clay-reference-architecture of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • references/implementation-guide.md
  • references/implementation.md

Open the folder on GitHubat commit cfae287

Compare with similar skills

Clay Reference Architecture 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 Reference Architecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Clay Reference Architecture this skilljeremylongshore/tons-of-skills-marketplace2.8k—~2.1kAutomated safety check: PassMIT
GEO Prospect Trackerzubair-trabzada/geo-seo-claude11k—~1.7kAutomated safety check: NotesMIT
Soql Lib Query Builderbeyond-the-cloud-dev/soql-lib154—~4.3kAutomated safety check: PassMIT
Sf DatacloudJaganpro/sf-skills424—~2.7kAutomated safety check: PassMIT
B2b Sdr AgentiPythoning/b2b-sdr-agent-template190—~744Automated safety check: PassMIT-0
Soql Lib Selectorbeyond-the-cloud-dev/soql-lib154—~2kAutomated safety check: PassMIT

Similar skills

  • GEO Prospect Tracker

    zubair-trabzada/geo-seo-claude

    Tracks GEO agency leads and clients through a sales pipeline in a local JSON file, with notes, audit scores, deal values and a pipeline summary.

    11k GitHub stars~1.7k tokensUpdated yesterday
    Sales & SupportAuto-check: notes
  • Soql Lib Query Builder

    beyond-the-cloud-dev/soql-lib

    Builds Salesforce SOQL queries using the SOQL Lib fluent builder API (SOQL.cls).

    154 GitHub stars~4.3k tokensUpdated 7 days ago
    Sales & SupportAuto-check passed
  • Sf Datacloud

    Jaganpro/sf-skills

    Salesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows.

    424 GitHub stars~2.7k tokensUpdated 5 mo ago
    Sales & SupportAuto-check passed
  • B2b Sdr Agent

    iPythoning/b2b-sdr-agent-template

    Open-source B2B AI SDR template. An agent skill from iPythoning/b2b-sdr-agent-template.

    190 GitHub stars~744 tokensUpdated 11 days ago
    Sales & SupportAuto-check passed
  • Soql Lib Selector

    beyond-the-cloud-dev/soql-lib

    Creates Salesforce Apex selector classes using the SOQL Lib selector pattern.

    154 GitHub stars~2k tokensUpdated 7 days ago
    Sales & SupportAuto-check passed
  • Dev Setup

    Portwood-Global-Solutions/Portwood

    Get from a fresh clone of Portwood to a working, fully-tested Salesforce org.

    126 GitHub stars~1.1k tokensUpdated yesterday
    Sales & SupportAuto-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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    Auto-check passed

Categories

Questions about Clay Reference Architecture

What does Clay Reference Architecture do?

Design production Clay enrichment pipelines with table schemas, waterfall patterns, and CRM sync. Clay Reference Architecture is an agent skill from jeremylongshore/tons-of-skills-marketplace. Design production Clay enrichment pipelines with table schemas, waterfall patterns, and CRM sync.

When should I use Clay Reference Architecture?

Clay Reference Architecture fits situations like: architecting new Clay integrations; reviewing data flow design; establishing enrichment pipeline standards; with phrases like clay architecture.

How do I install Clay Reference Architecture in Claude Code?

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

How do I install Clay Reference Architecture in Codex?

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

Can I use Clay Reference Architecture 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-reference-architecture -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-reference-architecture, .gemini/skills/clay-reference-architecture, .github/skills/clay-reference-architecture and .opencode/skills/clay-reference-architecture in your project.

What does Clay Reference Architecture need to run?

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

Does Clay Reference Architecture access the network?

SKILL.md names 2 domains. In commands or code: api.hubapi.com; the agent is likely to contact it when it follows the instructions. As links in the text: university.clay.com. This is read from the text; nothing was executed.

Is Clay Reference Architecture 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 Reference Architecture use?

Clay Reference Architecture 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 Reference Architecture use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.7k tokens, read only when the agent opens those files.

What are the alternatives to Clay Reference Architecture?

Skills that share tags, products or a category with Clay Reference Architecture: GEO Prospect Tracker (zubair-trabzada/geo-seo-claude, 11k stars), Soql Lib Query Builder (beyond-the-cloud-dev/soql-lib, 154 stars), Sf Datacloud (Jaganpro/sf-skills, 424 stars) and B2b Sdr Agent (iPythoning/b2b-sdr-agent-template, 190 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Clay Reference Architecture?

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.