Workflows Inbound Lead Routing logo

Workflows Inbound Lead Routing

Organization
clay-run
workflows-inbound-lead-routing

Guide customers through building an inbound lead-routing workflow in Clay Workflows. Use when a customer wants to route inbound leads from a form, webhook, data warehouse, or other source to a rep, sequence, or CRM.

Overview

Publisherclay-run
Repositoryagent-plugins
Skill nameworkflows-inbound-lead-routing
Stars
145
Forks
24
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by clay-run on GitHub. Read the source before you install it.

Installation

Install the Workflows Inbound Lead Routing AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/clay-run/agent-plugins/tree/main/clay/skills/workflows-inbound-lead-routing
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/clay-run/agent-plugins.git /tmp/agent-plugins
mkdir -p .claude/skills
cp -r /tmp/agent-plugins/clay/skills/workflows-inbound-lead-routing .claude/skills/workflows-inbound-lead-routing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Workflows Inbound Lead Routing in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Workflows Inbound Lead Routing on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Workflows Inbound Lead Routing is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Inbound lead routing

Description

Guide customers through building an inbound lead routing workflow in Clay Workflows. Use this skill when a customer wants to route inbound leads — from a form, webhook, data warehouse, or other source — to a rep, sequence, or CRM. Be opinionated and directive. Recommend the right approach, explain why, and keep the build moving forward.


Trigger

When a customer asks to build an inbound lead routing workflow, or describes a use case involving routing form submissions, webhook events, or inbound signups to reps or sequences.


Instructions

Follow the host agent's existing policies for reasoning, planning, requesting user input, and approvals. This skill supplies routing requirements and workflow guidance; it does not define a separate interaction policy. Treat the example questions below as inputs to establish, not a mandatory interview script.

Step 1 — Establish the Trigger

Start by telling the customer:

"For inbound lead routing, we'll use a webhook as the trigger. This is the standard approach because it lets your form, data warehouse, or website fire events directly into Clay in real time."

Available triggers (present as alternatives only if the customer pushes back or has a specific constraint):

  • Manual CSV upload
  • Manual trigger with manual inputs
  • Schedule-based
  • Signal/intent-based
  • New audience member added
  • Audience segment updated on schedule
  • Webhook (recommended default)

Establish the lead source if it is not already known:

"Are you capturing leads through an inbound form, like Typeform, or is this coming from another source like your data warehouse or website?"

  • If yes to a form → confirm webhook is the right trigger, proceed.
  • If another source → confirm it can emit a webhook. If not, explore schedule or CSV alternatives.

Step 2 — Establish the Routing Requirements

Establish the five inputs below, along with the trigger, enrichment level, scoring criteria, and routing tiers. Reuse information already provided or available in the workspace. Let the host agent’s policies determine which remaining decisions require user input and how to request it.

Q1 — CRM

"Which CRM are you using?"

For every CRM, including Salesforce and HubSpot, follow workflows-discover-actions to verify a suitable write action in the live workspace catalog and confirm the user can access the required connected account before proposing that route. If the action exists but no usable account is connected, establish that setup requirement. Recommend a webhook only if no suitable native action is available.

Q2 — Scoring Model

"Do you have an existing lead scoring model, or do we need to build one?"

  • Has one → use the existing scoring logic; you'll implement it in a Run Code node
  • Doesn't have one → tell them: "No problem. We'll build one together in a Run Code node. It'll use firmographic data, form fields, and intent signals from your enrichment steps."

Q3 — Rep Routing

"When a tier 1 lead comes in, how do you want the rep to be notified?"

Options (pick one):

  • Slack message
  • CRM task
  • Email

Q4 — Sequencer

"Are you using an external sequencer like Outreach or Salesloft, or Clay's native sequencer?"

  • External sequencer → will need a webhook or native integration node to push to it
  • Clay sequencer → can be handled natively within the workflow

Q5 — Disqualification Handling

Collect both preferences together:

  • "Add disqualified leads to a nurture sequence?"
  • "Tag or update disqualified leads in the CRM?"

If both answers are no, end without further action.


Step 3 — Build the Workflow

Keep enrichment and scoring steps sequential. Use the conditional step to branch into the tier-specific routing outcomes.

The standard happy path:

Webhook Trigger
  → Run Enrichment (firmographic + contact data)
  → Run Code (scoring model)
  → Conditional Logic (tier routing)
  → Route (rep notification / sequence / disqualify)

Walk the customer through each node:

Node 1: Run Enrichment

"First, we'll enrich the inbound lead to fill in any missing data — company size, industry, job title, and any intent signals. This gives the scoring model everything it needs."

Use the person-level, company-level, or combined enrichment requirement established above.

Node 2: Run Code (Scoring Model)

"Next, we'll run a scoring model to tier the lead. This code node will take the enriched data and output a score or tier (e.g., Tier 1 / Tier 2 / Disqualified)."

If building from scratch:

Translate the established lead-quality criteria into a scoring formula.

Typical inputs to the scoring model:

  • Firmographic data (company size, industry, revenue)
  • Form fields (role, use case, company name)
  • Intent signals (from enrichment nodes)
Node 3: Conditional Logic

Use the established tiers to route based on the score.

Standard structure:

  • Tier 1 → notify rep immediately
  • Tier 2 → add to marketing/sales sequence
  • Disqualified → handle per customer preference (dead, nurture, CRM tag)

Additional conditional branches to offer if relevant:

  • Language/market-based routing (e.g., route French-speaking leads to a French sequence)
  • Company segment routing (e.g., SMB vs. Enterprise)
Node 4: Route

Build the routing outcome based on answers from Step 2:

If routing to a rep:

  • Slack → set up a Slack message node with their preferred format
  • CRM task → create a task in Salesforce or HubSpot
  • Email → send a notification email with lead summary

If adding to a sequence:

  • Clay sequencer → add directly via native node
  • External sequencer (Outreach, Salesloft, etc.) → push via webhook or native integration

If disqualifying:

  • Dead end → no further action needed
  • Nurture → add to a nurture sequence
  • CRM tag → update lead/contact record in CRM

Step 4 — Summarize and Build

Summarize the proposed workflow as part of the host agent’s planning process:

Here's the workflow we're going to build:

  1. [Selected trigger] trigger from [source]
  2. Enrich at [person/company/both] level
  3. Score the lead using [existing model / model we'll build] based on [inputs]
  4. Route Tier 1 leads to [rep via Slack/CRM task/email], Tier 2 to [sequence], and disqualified leads to [dead end/nurture/CRM tag]

Follow the host agent’s approval policy before making changes.

When building, follow the workflows entry-point skill for the actual node and graph edits — this skill is the consultative playbook only.


Tone Guidelines

  • Be opinionated and directive. Don't present every option as equal — recommend the right approach and explain why.
  • If a customer proposes something that will make the workflow harder to maintain (e.g., parallel branches, skipping enrichment), push back and explain the tradeoff.
  • Use plain language. Avoid jargon unless the customer introduces it first.

Frequently asked questions

What does the Workflows Inbound Lead Routing AI skill do?

Guide customers through building an inbound lead-routing workflow in Clay Workflows. Use when a customer wants to route inbound leads from a form, webhook, data warehouse, or other source to a rep, sequence, or CRM.

Why use Workflows Inbound Lead Routing on TypingMind?

Because you install it once and use it with any model. Workflows Inbound Lead Routing is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Workflows Inbound Lead Routing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/clay-run/agent-plugins/tree/main/clay/skills/workflows-inbound-lead-routing. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Workflows Inbound Lead Routing?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Workflows Inbound Lead Routing?

As many as you like. As long as a model supports skills, you can use Workflows Inbound Lead Routing with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Workflows Inbound Lead Routing AI skill free?

It is published on GitHub by clay-run. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇