agentleFS
lubusINlubusIN/frappe-skills/project-triage/SKILL.md

project-triage

Skill68 starsChanged 10 days agoMITView on GitHub

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.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 10 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before making any code changes to understand the codebase

    line 13
  2. Distinctive:

    When debugging to determine which apps/versions are involved

    line 14
  3. Distinctive:

    Check for these patterns:

    line 26
  4. Very specific:

    bench command not found: Not in bench environment, use fm shell or activate venv

    line 85
  5. Distinctive:

    Permission errors: Check if running as correct user

    line 86
  6. Distinctive:

    If project structure is unclear:

    line 90
  7. Very specific:

    Look for hooks.py to identify app root

    line 91
  8. Very specific:

    Look for sites/common_site_config.json for bench root

    line 92
  9. Distinctive:

    Check git remote for app repository identification

    line 93
  10. Distinctive:

    Use this output to route to the appropriate skill:

    line 107
  11. Distinctive:

    Never modify code: before completing triage - understand the project first

    line 115
  12. Distinctive:

    Verify site exists: before running site-specific commands

    line 117
  13. Distinctive:

    Check developer_mode: before making schema changes (required for DocType modifications)

    line 118

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

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

# Or check apps directory
ls apps/

2) Check Frappe version

# 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

# 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+

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.