TwinCAT ST Master - Expert in Beckhoff IEC 61131-3 ExST development
Use this skill when implementing advanced TwinCAT 3 (ExST) features. It covers Properties (GET/SET), Methods, initialization lifecycles (FB_init, FB_reinit, FB_exit), State Machine patterns, pragmas (attributes, conditional compiling, regions, message output), and PlcTaskSystemInfo access.
Use this skill when the user asks about data types, arrays, structures (STRUCT), enumerations (ENUM), pointers (POINTER), references (REFERENCE), or dynamic memory allocation (NEW/DELETE). It also contains critical rules for memory alignment (pack_mode) to minimize padding bytes.
Use this skill ALWAYS before generating or modifying the names of any variables, Function Blocks (FB), Data Types (DUT), Functions, Methods, Properties, or Interfaces. It contains the mandatory Beckhoff Hungarian notation rules, prefixes (b, n, f, st, fb, etc.), and shading/name resolution rules to avoid conflicts.
Use this skill to correctly format ST (Structured Text) logic, operators, and control flow statements. It includes precedence rules, IF/CASE/FOR/WHILE loops syntax, mathematical/bitwise operator rules (MOD, SHL, ADR, BITADR), and the list of reserved IEC keywords.
Use this skill ONLY when the user reports a build error, a compilation warning, or when `CheckPlcSyntaxAsync` fails. It contains specific fixes for TwinCAT IL Errors (4200-4213) and explanations for standard Compiler Warnings (1502-1990).
Admin access level
Server config contains admin-level keywords
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
TwinCAT coding agent for Beckhoff PLC development, with strict rules for Structured Text, naming conventions, PLC-aware tooling, syntax checks, and safe project validation workflows.
TwinCAT-Agent provides:
twincat agentIn practice, it can automate TwinCAT XAE engineering actions on Windows (via a local MCP server), search Beckhoff InfoSys documentation and symbols (via a remote MCP server), and enforce a safer TwinCAT workflow than a generic assistant (naming conventions, PLC-aware operations, syntax checks, and a safe activation/login sequence).
Jump to: ✅ Requirements | 🧩 Install with Claude Code | 🧩 Install with GitHub Copilot CLI | 🚀 Quickstart
This repository is intended for developers and automation engineers working with:
Start Claude Code:
claude
Add this GitHub repo as a marketplace:
/plugin marketplace add TechIndustryX/twincat-agent
Install the TwinCAT plugin from that marketplace:
/plugin install twincat@twincat-plugins
If Claude prompts you to apply plugin changes without restarting:
/reload-plugins
Update the TwinCAT plugin:
/plugin update
Select the TwinCAT agent:
/agents
twincat
Add this GitHub repo as a marketplace:
copilot plugin marketplace add TechIndustryX/twincat-agent
Install the plugin:
copilot plugin install TechIndustryX/twincat-agent
Start Copilot CLI:
copilot
Select the TwinCAT agent:
/agent
twincat
Enable unrestricted approvals (recommended to avoid repeated prompts):
/allow-all on
After the plugin is installed, the working flow is the same regardless of which supported assistant you use.
Open a terminal in the folder that contains the target .plcproj:
cd C:\Path\To\Your\TwinCAT\Project
Start your assistant:
copilot
or:
claude
Select a recent model (example: GPT-5.4 or Sonnet) using whatever model selection command or UI your assistant provides.
Select the twincat agent.
Copilot CLI:
/agent
twincat
Claude Code:
/agents
twincat
If you are using Copilot CLI, enable unrestricted approvals:
/allow-all on
Start with a concrete prompt:
Create a state machine in the example MAIN program.
From there, the twincat agent should resolve the project, initialize TwinCAT automation, inspect the PLC tree, and work through the change using the configured TwinCAT rules.
The Beckhoff InfoSys MCP server can also be used independently, without installing the rest of this repository.
Available tools include:
infosys_get_page: returns a documentation page rendered as clean Markdowninfosys_search: searches across indexed Beckhoff InfoSys documentation pagesinfosys_search_symbols: searches IEC symbols such as function blocks, functions, structs, enums, and interfacesinfosys_search_code: searches Structured Text examples, variable names, and code fragments inside the documentationThis project is licensed under the PolyForm Noncommercial License 1.0.0.
You are free to use, modify, and distribute this software for personal, academic, and non-commercial purposes (e.g., hobby projects, personal study, testing, and open-source research). For commercial usage (e.g. consulting, integration into paid industrial projects, or enterprise environments), a commercial license is required. Please contact me directly to discuss commercial licensing options.
npx claudepluginhub techindustryx/twincat-agent --plugin twincatAccess thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams