Sponsor Suno AI Music arrow_forward
Slash Command

Make Builder

Design Make.com scenarios with AI assistance

Type
Slash Command
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026

What Make Builder is

Make Builder is a slash command 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 slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Make Builder gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Make Builder

Claude Code

  1. Download make-builder.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

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/commands/make-builder.md, shared under the repository's MIT license. Read the full file on GitHub.

Create visual Make.com automation scenarios with detailed module configuration.

Usage

When the user requests a Make.com scenario, design a complete visual workflow with module-by-module instructions.

Scenario Templates

1. AI Email Auto-Responder

Flow:

Gmail: Watch emails
  → OpenAI: Generate response
  → Gmail: Send email
  → Google Sheets: Log conversation

Module Configuration:

  1. Gmail: Watch emails
  • Connection: Your Gmail
  • Folder: INBOX
  • Criteria: Unread messages
  • Max results: 10
  1. OpenAI: Create completion
  • Connection: Your OpenAI API
  • Model: gpt-4
  • Max tokens: 500
  • Temperature: 0.7
  • Prompt: Draft a professional response to:\n\nFrom: {{1.from}}\nSubject: {{1.subject}}\nBody: {{1.textPlain}}
  1. Gmail: Send an email
  • To: {{1.from}}
  • Subject: Re: {{1.subject}}
  • Content: {{2.choices[0].message.content}}
  1. Google Sheets: Add a row
  • Spreadsheet: Email Log
  • Sheet: Responses
  • From: {{1.from}}
  • Subject: {{1.subject}}
  • Response: {{2.choices[0].message.content}}
  • Date: {{now}}

2. Lead Qualification with AI

Flow:

Webhook: Custom webhook
  → OpenAI: Score lead
  → Router:
     ├─ High score → Slack notification + HubSpot deal
     ├─ Medium score → Email nurture
     └─ Low score → Archive to Airtable

Module Configuration:

  1. Webhook
  • Create a custom webhook
  • Expected data: name, email, company, role, budget
  1. OpenAI: Create completion
  • Prompt: Score this lead from 0-100:\nName: {{1.name}}\nCompany: {{1.company}}\nRole: {{1.role}}\nBudget: {{1.budget}}\n\nProvide only the numeric score.
  • Parse: Use Text parser to extract number
  1. Router
  • Route 1 Filter: {{3.score}} Greater than 70
  • Route 2 Filter: {{3.score}} Between 40 and 70
  • Fallback: All other cases

4A. Slack: Create a message (High route)

  • Channel: #sales-leads
  • Text: Hot lead: {{1.name}} from {{1.company}} - Score: {{3.score}}

4B. HubSpot: Create a deal (High route)

  • Deal name: {{1.company}} - {{1.name}}
  • Stage: Qualification
  • Amount: {{1.budget}}
  1. ActiveCampaign: Add contact to list (Medium route)
  • Email: {{1.email}}
  • List: Nurture Campaign
  • Tags: medium-priority,{{1.role}}
  1. Airtable: Create a record (Low route)
  • Base: Leads
  • Table: Archived
  • Fields: Map all lead data + score

3. Content Distribution Pipeline

Flow:

RSS: Read feed
  → Filter: New items only
  → OpenAI: Rewrite for social
  → Iterator: For each platform
     ├─ Twitter: Post
     ├─ LinkedIn: Post
     └─ Facebook: Post

Module Configuration:

  1. RSS: Watch RSS feed items
  • URL: Your RSS feed
  • Maximum number of returned items: 5
  1. Filter
  • Condition: {{1.published}} After {{addHours(now; -24)}}
  • Label: "Only items from last 24 hours"
  1. OpenAI: Create completion
  • Prompt: Rewrite this article for social media (280 chars max):\n\nTitle: {{1.title}}\nContent: {{1.contentSnippet}}\n\nMake it engaging with relevant hashtags.
  1. Set multiple variables
  • platforms: ["twitter", "linkedin", "facebook"]
  • content: {{3.choices[0].message.content}}
  • link: {{1.link}}
  1. Iterator
  • Array: {{4.platforms}}

6A. Twitter: Create a tweet

  • Text: {{4.content}}\n\n{{4.link}}

6B. LinkedIn: Create a post

  • Text: {{4.content}}\n\n{{4.link}}

6C. Facebook: Create a post

  • Message: {{4.content}}
  • Link: {{4.link}}

4. Document Processing Workflow

Flow:

Google Drive: Watch files
  → Filter: PDFs only
  → OCR.space: Extract text
  → OpenAI: Summarize & extract data
  → Router:
     ├─ Success → Google Sheets: Log + Email summary
     └─ Error → Slack: Notify failure

Module Configuration:

  1. Google Drive: Watch files
  • Folder: Inbox
  • Types: application/pdf
  • Limit: 10
  1. Filter
  • Condition: File name contains "invoice" OR "receipt"
  1. HTTP: Make a request (OCR.space)
  • URL:
  • Method: POST
  • Headers: apikey: YOUR_OCR_KEY
  • Body: file: {{1.data}}
  1. OpenAI: Create completion
  • Prompt: Extract structured data from this document:\n\n{{3.ParsedResults[0].ParsedText}}\n\nProvide: Date, Amount, Vendor, Category
  • Format: JSON mode
  1. Google Sheets: Add a row
  • Spreadsheet: Document Log
  • Date: {{4.date}}
  • Amount: {{4.amount}}
  • Vendor: {{4.vendor}}
  • Category: {{4.category}}
  1. Gmail: Send an email
  • To: [email protected]
  • Subject: New document processed: {{1.name}}
  • Body: Summary of extracted data

Error Handler on all modules:

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 Builder?

Make Builder is a slash command for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Design Make.com scenarios with AI assistance

How do I install Make Builder in Claude Code?

Download make-builder.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Make Builder in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Make Builder 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.