Frappe Agent Interpreter logo

Frappe Agent Interpreter

Organization
Impertio-Studio
frappe-agent-interpreter

Use when receiving vague or unclear ERPNext/Frappe development requests that need interpretation. Transforms requirements like 'make invoice auto-calculate' or 'add approval workflow' into concrete technical specifications. Determines which Frappe mechanisms to use and maps to the full 61-skill catalog. Keywords: vague requirement, clarify scope, translate business need, technical spec, implementation plan, what does this mean, unclear requirement, translate to code, how to build this.

Overview

PublisherImpertio-Studio
RepositoryFrappe_Claude_Skill_Package
Skill namefrappe-agent-interpreter
Stars
180
Forks
53
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

    Published by Impertio-Studio on GitHub. Read the source before you install it.

Installation

Install the Frappe Agent Interpreter 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/Impertio-Studio/Frappe_Claude_Skill_Package.git /tmp/Frappe_Claude_Skill_Package
mkdir -p .claude/skills
cp -r /tmp/Frappe_Claude_Skill_Package/skills/source/agents/frappe-agent-interpreter .claude/skills/frappe-agent-interpreter
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Frappe Agent Interpreter 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 Agent Interpreter 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 Agent Interpreter 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 Code Interpreter Agent

Transforms vague or incomplete Frappe/ERPNext development requests into clear, actionable technical specifications mapped to the full 61-skill catalog.

Purpose: Bridge the gap between "what the user wants" and "what needs to be built"

When to Use This Agent

USER REQUEST ANALYSIS
|
+-- Request is vague/incomplete
|   "Make the invoice do something when submitted"
|   --> USE THIS AGENT
|
+-- Request lacks technical specifics
|   "Add approval before order confirmation"
|   --> USE THIS AGENT
|
+-- Multiple implementation paths possible
|   "Automate inventory updates"
|   --> USE THIS AGENT
|
+-- Request has clear technical specs already
|   "Create Server Script on validate for Sales Invoice"
|   --> Skip agent, use relevant frappe-* skills directly

Interpretation Workflow

STEP 1: EXTRACT INTENT
  - What is the business problem?
  - What should happen? When? To what data?
  - Who should be affected (roles/users)?

STEP 2: IDENTIFY TRIGGER CONTEXT
  - Document lifecycle event? (save/submit/cancel)
  - User action? (button click, field change)
  - Time-based? (daily, hourly, cron)
  - External event? (webhook, API call)

STEP 3: DETERMINE MECHANISM
  - Client Script, Server Script, or Controller?
  - Hooks configuration needed?
  - Custom app required?
  - v16 extend_doctype_class applicable?

STEP 4: GENERATE SPECIFICATION
  - DocType(s), event/trigger, mechanism, data flow
  - Error handling requirements
  - Version compatibility (v14/v15/v16)

STEP 5: MAP TO SKILLS
  - List required frappe-* skills from full catalog
  - Note dependencies between skills

See references/workflow.md for detailed steps.

Mechanism Selection Matrix

Requirement PatternMechanismCustom App?
"Auto-calculate on form"Client Script + Server ScriptNo
"Validate before save"Server Script (validate)No
"Send notification after submit"Server Script (on_submit)No
"Add button to form"Client ScriptNo
"Scheduled report/sync"hooks.py scheduler_eventsYes
"Filter list per user"Server Script (Permission Query)No
"Custom REST API"Server Script (API) or @frappe.whitelist()Depends
"Complex transaction with rollback"ControllerYes
"External library needed (requests)"ControllerYes
"Approval workflow"Built-in Workflow + optional Server ScriptNo
"Print format customization"Jinja template (Print Format)No
"Custom report"Script Report or Query ReportDepends
"Background processing"frappe.enqueue()Yes
"File upload handling"Controller + File hooksYes
"Cache invalidation"Cache API + hooksYes
"Website/portal page"Web template + routingYes
"UI component (dashboard, etc.)"Page or Custom PageYes

Clarifying Questions Framework

1. WHAT Questions

  • What DocType(s) are involved?
  • What data needs to change?
  • What should the outcome be?

2. WHEN Questions

  • On form load? On field change? Before/after save?
  • Before/after submit? On a schedule? Button click?

3. WHO Questions

  • All users? Specific roles? Document owner only?

4. WHERE Questions

  • In the form (UI)? Database only? Report? External system?

5. ERROR Questions

  • Block the operation? Show warning? Log silently?

6. VERSION Questions (v16 considerations)

  • Target single version or multi-version compatibility?
  • Can we use extend_doctype_class (v16) or need doc_events (v14+)?
  • Type annotations desired? (v16 best practice)

Output Specification Template

ALWAYS generate specifications in this format:

markdown
## Technical Specification

### Summary
[One sentence describing what will be built]

### Business Requirement
[Original user request, clarified]

### Implementation

| Aspect | Value |
|--------|-------|
| **DocType(s)** | [List] |
| **Trigger** | [Event/action] |
| **Mechanism** | [Client Script / Server Script / Controller / etc.] |
| **Version** | [v14 / v15 / v16 / all] |

### Data Flow
1. [Step 1]
2. [Step 2]

### Error Handling
[Strategy]

### Required Skills
- [ ] frappe-skill-name - for [purpose]

### Validation Criteria
[How to verify it works]

Complete Skill Catalog (61 skills)

Syntax Layer (11 skills)

SkillUse For
frappe-syntax-clientscriptsClient Script JS syntax
frappe-syntax-serverscriptsServer Script Python sandbox syntax
frappe-syntax-controllersController class syntax
frappe-syntax-hookshooks.py configuration syntax
frappe-syntax-hooks-eventsDocument event hook syntax
frappe-syntax-whitelisted@frappe.whitelist() syntax
frappe-syntax-jinjaJinja template syntax
frappe-syntax-schedulerScheduler/enqueue syntax
frappe-syntax-customappApp structure syntax
frappe-syntax-doctypesDocType JSON definition syntax
frappe-syntax-reportsReport definition syntax

Core Layer (7 skills)

SkillUse For
frappe-core-databaseDatabase operations, ORM, raw SQL
frappe-core-permissionsPermission system, roles, rules
frappe-core-apiREST API, resource API
frappe-core-workflowWorkflow engine, states, transitions
frappe-core-notificationsEmail, push, system notifications
frappe-core-filesFile upload, attachment, storage
frappe-core-cacheRedis cache, cache invalidation

Implementation Layer (12 skills)

SkillUse For
frappe-impl-clientscriptsClient Script implementation patterns
frappe-impl-serverscriptsServer Script implementation patterns
frappe-impl-controllersController implementation patterns
frappe-impl-hooksHook implementation patterns
frappe-impl-whitelistedWhitelisted method patterns
frappe-impl-jinjaJinja template patterns
frappe-impl-schedulerScheduled task/background job patterns
frappe-impl-customappCustom app development workflow
frappe-impl-reportsReport building patterns
frappe-impl-workflowWorkflow implementation patterns
frappe-impl-websiteWebsite/portal development
frappe-impl-ui-componentsUI component patterns
frappe-impl-integrationsExternal system integration

Error Layer (7 skills)

SkillUse For
frappe-errors-clientscriptsClient Script error patterns
frappe-errors-serverscriptsServer Script error patterns
frappe-errors-controllersController error patterns
frappe-errors-hooksHook error patterns
frappe-errors-apiAPI error patterns
frappe-errors-permissionsPermission error patterns
frappe-errors-databaseDatabase error patterns

Ops Layer (8 skills)

SkillUse For
frappe-ops-benchBench CLI commands
frappe-ops-deploymentProduction deployment
frappe-ops-backupBackup and restore
frappe-ops-performancePerformance tuning
frappe-ops-upgradesVersion upgrade procedures
frappe-ops-cloudCloud hosting (FC, AWS, etc.)
frappe-ops-app-lifecycleApp versioning and releases
frappe-ops-frontend-buildFrontend asset building

Testing Layer (2 skills)

SkillUse For
frappe-testing-unitUnit and integration tests
frappe-testing-cicdCI/CD pipeline setup

Agent Layer (5 skills)

SkillUse For
frappe-agent-interpreterTHIS SKILL - requirement interpretation
frappe-agent-validatorCode validation before deployment
frappe-agent-debuggerDebugging Frappe issues
frappe-agent-migratorData migration planning
frappe-agent-architectArchitecture decision-making

Skill Dependencies Map

MechanismRequired Skills
Client Scriptfrappe-syntax-clientscripts, frappe-impl-clientscripts, frappe-errors-clientscripts
Server Script (Doc Event)frappe-syntax-serverscripts, frappe-impl-serverscripts, frappe-errors-serverscripts
Server Script (API)frappe-syntax-serverscripts, frappe-core-api, frappe-errors-api
Server Script (Scheduler)frappe-syntax-serverscripts, frappe-syntax-scheduler, frappe-impl-scheduler
Server Script (Permission)frappe-syntax-serverscripts, frappe-core-permissions, frappe-errors-permissions
Controllerfrappe-syntax-controllers, frappe-impl-controllers, frappe-errors-controllers
Hooksfrappe-syntax-hooks, frappe-impl-hooks, frappe-errors-hooks
Custom Appfrappe-syntax-customapp, frappe-impl-customapp, frappe-ops-bench
Jinja Templatefrappe-syntax-jinja, frappe-impl-jinja
Database Operationsfrappe-core-database, frappe-errors-database
Whitelisted Methodfrappe-syntax-whitelisted, frappe-impl-whitelisted
Workflowfrappe-core-workflow, frappe-impl-workflow
Reportsfrappe-syntax-reports, frappe-impl-reports
Website/Portalfrappe-impl-website, frappe-syntax-jinja
Integrationfrappe-impl-integrations, frappe-impl-customapp
Background Jobsfrappe-impl-scheduler, frappe-syntax-scheduler
Testingfrappe-testing-unit, frappe-testing-cicd
Deploymentfrappe-ops-deployment, frappe-ops-bench

Common Pattern Recognition

User PhraseMechanismKey Skills
"auto-calculate", "automatically fill"Client Script + Server Scriptfrappe-impl-clientscripts, frappe-impl-serverscripts
"validate", "check before save"Server Script (validate)frappe-impl-serverscripts
"prevent", "block", "don't allow"Server Script + frappe.throw()frappe-errors-serverscripts
"send email", "notify"Server Script or Notificationfrappe-core-notifications
"sync", "integrate", "API"Controller (custom app)frappe-impl-integrations
"every day", "schedule"Scheduler or hooks.pyfrappe-impl-scheduler
"only see their own"Permission Queryfrappe-core-permissions
"approval", "authorize"Built-in Workflowfrappe-core-workflow, frappe-impl-workflow
"add button", "custom action"Client Scriptfrappe-impl-clientscripts
"print format", "PDF"Jinja Templatefrappe-impl-jinja
"report", "dashboard"Script/Query Reportfrappe-impl-reports
"deploy", "go live"Deployment workflowfrappe-ops-deployment
"test", "CI"Testing frameworkfrappe-testing-unit
"cache", "performance"Cache + optimizationfrappe-core-cache, frappe-ops-performance

Version Awareness

ALWAYS consider version compatibility:

Featurev14v15v16
Server Script sandboxYesYesYes
extend_doctype_classNoNoYes
Chrome PDF renderingNoNoYes
Data maskingNoNoYes
UUID naming ruleNoNoYes
Type annotations (best practice)NoNoYes
Scheduler tick (seconds)2406060
job_id dedupNoYesYes

Agent Output Checklist

Before completing interpretation, ALWAYS verify:

  • Business requirement is clear and unambiguous
  • Trigger/event is identified
  • Mechanism is selected with justification
  • DocType(s) are specified
  • Data flow is documented
  • Error handling approach is defined
  • Version compatibility is noted (v14/v15/v16)
  • Required frappe-* skills are listed from full catalog
  • Validation criteria are defined
  • v16 considerations noted (extend_doctype_class, type annotations)

See references/checklists.md for detailed checklists. See references/examples.md for interpretation examples.

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 Agent Interpreter AI skill do?

Use when receiving vague or unclear ERPNext/Frappe development requests that need interpretation. Transforms requirements like 'make invoice auto-calculate' or 'add approval workflow' into concrete technical specifications. Determines which Frappe mechanisms to use and maps to the full 61-skill catalog. Keywords: vague requirement, clarify scope, translate business need, technical spec, implementation plan, what does this mean, unclear requirement, translate to code, how to build this.

Why use Frappe Agent Interpreter on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Impertio-Studio/Frappe_Claude_Skill_Package/tree/main/skills/source/agents/frappe-agent-interpreter. 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 Agent Interpreter?

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 Agent Interpreter?

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

Is the Frappe Agent Interpreter AI skill free?

Yes. It is published on GitHub by Impertio-Studio 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 👇