Project Triage logo

Project Triage

Organization
lubusIN
project-triage

Detect Frappe project type, installed apps, version, and tooling. Use as the first step when working on any Frappe/ERPNext codebase to understand the project structure before making changes.

Overview

PublisherlubusIN
Repositoryfrappe-skills
Skill nameproject-triage
Stars
62
Forks
23
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

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

Installation

Install the Project Triage 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/project-triage .claude/skills/project-triage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Project Triage 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 Project Triage 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 Project Triage 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 Project Triage

Quickly analyze a Frappe project to determine its type, installed apps, version, and available tooling.

When to use

  • First step when opening a new Frappe project
  • Before making any code changes to understand the codebase
  • When debugging to determine which apps/versions are involved
  • To identify the development environment (Bench vs Frappe Manager)

Inputs required

  • Project root path (where apps/, sites/, or app code lives)
  • Access to run shell commands (for version checks)

Procedure

0) Identify project structure

Check for these patterns:

PatternProject Type
apps/ + sites/ directoriesBench installation
docker-compose.yml with frappeFrappe Manager site
pyproject.toml or setup.py with frappeStandalone app
doctype/ directoryInside an app module

1) Detect installed apps

bash
# Inside Bench/FM shell
bench --site <site> list-apps

# Or check apps directory
ls apps/

2) Check Frappe version

bash
# Inside Bench/FM shell
bench version

# Or check from Python
bench --site <site> console
>>> frappe.__version__

3) Identify tooling

File/DirectoryTooling
ProcfileStandard bench
docker-compose.ymlDocker/FM
cypress/UI testing available
.github/workflows/CI configured
package.json with @frappe/*JS build tooling

4) Check development mode

bash
# Check site config
bench --site <site> console
>>> frappe.conf.developer_mode

Verification

  • Project type identified (bench/FM/standalone app)
  • Installed apps listed
  • Frappe version known
  • Development mode status confirmed
  • Available tooling documented

Failure modes / debugging

  • No site found: May be inside an app directory, navigate to bench root
  • bench command not found: Not in bench environment, use fm shell or activate venv
  • Permission errors: Check if running as correct user

Escalation

If project structure is unclear:

  1. Look for hooks.py to identify app root
  2. Look for sites/common_site_config.json for bench root
  3. Check git remote for app repository identification

Output format

After triage, document:

Project Type: [bench|frappe-manager|standalone-app]
Frappe Version: X.Y.Z
Installed Apps: [list]
Developer Mode: [yes|no]
Tooling: [list]
Site Name: <site>

Use this output to route to the appropriate skill:

  • DocType work → doctype-development
  • API work → api-development
  • Testing → testing
  • Enterprise patterns → enterprise-patterns

Guardrails

  • Never modify code before completing triage - understand the project first
  • Check for custom apps that may override standard behavior
  • Verify site exists before running site-specific commands
  • Check developer_mode before making schema changes (required for DocType modifications)
  • Note Node.js version - frontend builds require compatible Node (typically 18+ for v15)

Common Mistakes

MistakeWhy It FailsFix
Running bench migrate without siteAffects wrong/default siteAlways use --site sitename
Assuming ERPNext is installedImport errors, missing DocTypesCheck list-apps output first
Missing FM shell contextbench commands not foundUse fm shell sitename first
Wrong directory levelCommands fail silentlyNavigate to bench root (where apps/ exists)
Ignoring custom app overridesUnexpected behaviorCheck hooks.py for overrides
Not checking Python versionSyntax/compatibility errorsVerify Python >= 3.10 for v15+

Frequently asked questions

What does the Project Triage AI skill do?

Detect Frappe project type, installed apps, version, and tooling. Use as the first step when working on any Frappe/ERPNext codebase to understand the project structure before making changes.

Why use Project Triage on TypingMind?

Because you install it once and use it with any model. Project Triage 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 Project Triage in TypingMind?

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

Which AI models can use Project Triage?

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 Project Triage?

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

Is the Project Triage 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 👇