Frappe Manager logo

Frappe Manager

Organization
lubusIN
frappe-manager

Use Frappe Manager (FM) for Docker-based development and testing environments. Use when setting up local dev, running isolated tests, or managing agent-driven Frappe development workflows.

Overview

PublisherlubusIN
Repositoryfrappe-skills
Skill namefrappe-manager
Stars
62
Forks
23
Bundled files
7
LicenseMIT
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.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by lubusIN on GitHub. Read the source before you install it.

Installation

Install the Frappe Manager 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.
  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/lubusIN/frappe-skills.git /tmp/frappe-skills
mkdir -p .claude/skills
cp -r /tmp/frappe-skills/frappe-manager .claude/skills/frappe-manager
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Frappe Manager 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 Frappe Manager 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 Frappe Manager 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.

Frappe Manager

Manage Docker-based Frappe development environments using Frappe Manager (FM).

When to use

  • Setting up a local Frappe development environment
  • Creating isolated test environments
  • Agent-driven development (vibe coding) workflows
  • Quick prototyping without full bench setup
  • Reproducible environments across machines

Inputs required

  • Docker installed and running
  • Python 3.11+ with pipx
  • Site/bench name
  • Apps to install (frappe, erpnext, hrms, custom)
  • Environment type (dev/prod)

Procedure

0) Install Frappe Manager

bash
# Install via pipx
pipx install frappe-manager

# Enable shell completion
fm --install-completion

1) Create a site

bash
# Basic site (frappe only)
fm create mysite

# Site with ERPNext
fm create mysite --apps erpnext:version-15

# Site with multiple apps
fm create mysite --apps erpnext --apps hrms --environment dev

# Production site with SSL
fm create example.com --apps erpnext --env prod --ssl letsencrypt

2) Manage sites

bash
# List all sites
fm list

# Start/stop site
fm start mysite
fm stop mysite

# View site info
fm info mysite

# View logs (follow)
fm logs mysite -f

# Delete site
fm delete mysite

3) Development workflow

bash
# Access shell inside container
fm shell mysite

# Inside container - common commands:
bench new-app my_custom_app
bench --site mysite install-app my_custom_app
bench --site mysite migrate
bench build --app my_custom_app
bench --site mysite run-tests --app my_custom_app

# Exit shell
exit

# Open in VSCode
fm code mysite

# Open with debugger
fm code mysite --debugger

4) Agent-driven development

Perfect for AI agents developing Frappe apps:

bash
# 1. Setup: Create fresh environment
fm create testsite --apps erpnext:version-15 --environment dev
fm start testsite

# 2. Develop: Enter shell, create app
fm shell testsite
bench new-app my_app
bench --site testsite install-app my_app
# ... make code changes ...
exit

# 3. Test: Run tests
fm shell testsite
bench --site testsite run-tests --app my_app
exit

# 4. Verify: Check logs
fm logs testsite -f

# 5. Reset if needed: Start fresh
fm stop testsite
fm delete testsite
fm create testsite --apps erpnext:version-15 --environment dev

5) Internal service management (fmx)

Inside the container, use fmx for service control:

bash
fm shell mysite

fmx status      # Check service status
fmx restart     # Restart Frappe services
fmx start       # Start services
fmx stop        # Stop services

Verification

  • Site accessible at http://mysite.localhost
  • Can login with admin credentials (default: admin/admin)
  • Custom app installed and visible
  • Tests run successfully inside container
  • Logs show no critical errors

Failure modes / debugging

  • Docker not running: Start Docker daemon
  • Port conflict: Use different site name or check port 80/443
  • Site not accessible: Check fm list for status, try fm start
  • App not installing: Check fm logs for errors
  • Slow startup: First run downloads images—be patient

Escalation

References

Guardrails

  • Always backup before operations: Run fm backup <site> before major changes or updates
  • Use named sites: Avoid generic names; use descriptive site names for project identification
  • Check SSH access: Ensure SSH keys are configured for private repos before app installation
  • Verify Docker status: Run fm doctor to check Docker and FM health before operations
  • Use fm shell for commands: Always enter container shell before running bench commands

Common Mistakes

MistakeWhy It FailsFix
Running bench commands outside fm shell"Command not found" or wrong siteAlways fm shell <site> first
Wrong site contextOperations affect wrong siteCheck prompt shows correct site; use bench --site <site>
Missing volumes on recreateData lossUse fm recreate --keep-volumes or backup first
Not checking fm doctorSilent configuration issuesRun fm doctor to diagnose problems
Using localhost in site URLDNS resolution issuesUse <site>.localhost format for local access
Forgetting to fm start after rebootSite not accessibleRun fm start <site> or fm start --all

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Frappe Manager AI skill do?

Use Frappe Manager (FM) for Docker-based development and testing environments. Use when setting up local dev, running isolated tests, or managing agent-driven Frappe development workflows.

Why use Frappe Manager on TypingMind?

Because you install it once and use it with any model. Frappe Manager 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 Frappe Manager in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lubusIN/frappe-skills/tree/main/frappe-manager. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Frappe Manager?

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 Frappe Manager?

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

Is the Frappe Manager AI skill free?

Yes. It is published on GitHub by lubusIN under the MIT license. 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 👇