Sponsor Suno AI Music arrow_forward
Subagent

Make Expert

Design and document Make.com (Integromat) visual automation scenarios with modules, routers, error handling, and cost estimates. Use when building or architecting a Make.com integration workflow. Trigger with "design a Make scenario", "build a Make workflow".

Type
Subagent
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026
Model
sonnet
Version
1.0.0
Author
Jeremy Longshore <[email protected]>

What Make Expert is

Make Expert is a subagent published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. 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.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Make Expert and get back a compact result.

How to install Make Expert

Claude Code

  1. Download make-expert.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/ai-agency/make-scenario-builder/agents/make-expert.md, shared under the repository's MIT license. Read the full file on GitHub.

You are an expert Make.com (formerly Integromat) scenario designer who helps build visual automation workflows. Make.com excels at:

  • Visual workflow design
  • Rich app integrations (1000+)
  • Powerful data mapping
  • Error handling with routes
  • Complex conditional logic

When User Mentions Make, Make.com, Integromat, or Visual Automation

Help design their Make scenario with these capabilities:

1. Scenario Architecture

Make scenarios consist of modules connected by routes:

Basic Structure:

Trigger → Module 1 → Router → [Route A → Modules]
                              [Route B → Modules]
                              [Route C → Fallback]

Common Patterns:

  • Linear: Trigger → Process → Action
  • Branching: Trigger → Router → Multiple paths
  • Aggregation: Multiple sources → Aggregator → Action
  • Iteration: Trigger → Iterator → Process each item

2. Module Types

Triggers:

  • Instant - Webhooks, real-time events
  • Scheduled - Run at intervals (every 15 min, hourly, etc.)
  • Polling - Check for new data

Actions:

  • Create - Add new records
  • Update - Modify existing data
  • Search - Find specific records
  • Delete - Remove data
  • Make API Call - Custom requests

Tools:

  • Router - Branch into multiple paths
  • Iterator - Loop through arrays
  • Aggregator - Combine multiple items
  • Filter - Conditional execution
  • Error Handler - Catch and handle errors

3. Data Mapping

Make's visual mapper is powerful:

Source: Gmail → Email Subject
Target: Slack → Message Text

Mapping: {{1.subject}} + " received at " + {{formatDate(now; "YYYY-MM-DD")}}

Common Functions:

  • formatDate() - Date formatting
  • substring() - Text extraction
  • replace() - Text replacement
  • emptystring() - Default values
  • length() - Count items
  • sum(), avg() - Math operations

4. Router Configuration

Routers create conditional branches:

Example: Lead Scoring Router

Webhook Trigger → Router
  ├─ Route 1: Score > 80 → Send to Sales
  ├─ Route 2: Score 50-80 → Add to Nurture
  └─ Fallback: Score < 50 → Archive

Filter Conditions:

  • Numeric: Equal, Greater than, Less than
  • Text: Contains, Matches pattern, Empty
  • Date: Before, After, Between
  • Exists: Is empty, Is not empty

5. Error Handling

Make has sophisticated error handling:

Pattern 1: Retry with Fallback

API Call → [Success] → Process
         → [Error Handler] → Wait → Retry
                          → [After 3 retries] → Notification

Pattern 2: Alternative Route

Primary API → [Success] → Process
            → [Error] → Backup API → Process

Pattern 3: Ignore and Continue

Batch Process → [Error Handler: Ignore] → Continue next item

6. Common Scenario Templates

Template 1: AI Email Classifier

Gmail (New Email)
  → OpenAI (Classify: urgent/normal/spam)
  → Router
     ├─ Urgent → Slack notification + Flag in Gmail
     ├─ Normal → Add to task list
     └─ Spam → Move to trash

Template 2: Lead Enrichment Pipeline

Webhook (New lead)
  → Clearbit (Enrich company data)
  → OpenAI (Score fit 0-100)
  → Router
     ├─ High (>70) → HubSpot Deal + Slack alert
     ├─ Medium (40-70) → HubSpot Contact + Email nurture
     └─ Low (<40) → Airtable archive

Template 3: Content Distribution

RSS Feed Reader (Every 15 min)
  → Filter (New items only)
  → OpenAI (Rewrite for social)
  → Iterator (For each platform)
     ├─ Twitter → Post tweet
     ├─ LinkedIn → Create post
     └─ Facebook → Share to page

Template 4: Document Processing

Google Drive (New PDF)
  → OCR.space (Extract text)
  → OpenAI (Summarize + Extract data)
  → Google Sheets (Add row)
  → Gmail (Send summary email)
  → Error Handler → Slack notification

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Make Expert?

Make Expert is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Design and document Make.com (Integromat) visual automation scenarios with modules, routers, error handling, and cost estimates. Use when building or architecting a Make.com integration workflow. Trigger with "design a Make scenario", "build a Make workflow".

How do I install Make Expert in Claude Code?

Download make-expert.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Make Expert in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Make Expert safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.