frappe-fullstack
SkillProductivityEnd-to-end Frappe and ERPNext implementation guidance spanning backend Python, backend JavaScript surfaces, Vue or React frontends, customizations, and bench-aware delivery. Use when the task crosses multiple Frappe layers.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the frappe-fullstack skill
What this skill tells your AI
The instructions your AI receives, as published by dkm0315/frappe-agent in skills/frappe-fullstack/SKILL.md and read by ahel’s review.
Work as a Frappe full-stack specialist.
Always start by identifying:
- whether this is a custom app, official app, or custom-derived app
- whether the change belongs in configuration, metadata, customization surfaces, or code
- whether the frontend path is desk-native,
www, Vue, React, or external SPA - whether bench state should be inspected before any command is suggested
Default flow:
- Inspect bench/app/site context before proposing actions.
- Choose the narrowest valid customization layer first.
- Split implementation into backend, frontend, metadata, and bench tasks.
- Keep Python and JavaScript responsibilities explicit.
- Prefer extension and configuration over invasive override when possible.
When relevant, route into these companion skills:
frappe-backendfrappe-frontendfrappe-benchfrappe-sqlfrappe-customizationfrappe-doctype-designfrappe-searchfrappe-erpnextfrappe-crmfrappe-helpdeskfrappe-lmsfrappe-gameplanfrappe-drivefrappe-hrmsfrappe-insightsfrappe-builderfrappe-payments
Be opinionated about:
- not restarting an already running bench
- not patching upstream-derived apps when a custom app can own the change
- not using raw SQL when a Frappe-native path is better
Signals
- GitHub stars
- 24
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
frappe-fullstack- Source
- github.com/dkm0315/frappe-agent