twincat-export-preparation
Prepares and validates model exports for TwinCAT PLC environments.
Install
mkdir -p .claude/skills/twincat-export-preparation && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13136" && unzip -o skill.zip -d .claude/skills/twincat-export-preparation && rm skill.zipInstalls to .claude/skills/twincat-export-preparation
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when planning, reviewing, or preparing TwinCAT-facing TE model export work in StandardML - Codex. This skill is for PLC-friendly export preparation, inspectable inference-path design, and deployment-readiness discipline, not for generic deployment discussion.Key capabilities
- →Plan TwinCAT-facing TE model exports
- →Simplify or decompose models for PLC-friendliness
- →Review model families for export plausibility
- →Prepare deployment-facing technical notes
- →Check for preservation of inspectable intermediate quantities
- →Ground TwinCAT/PLC claims in repository code or reference notes
How it works
The skill requires reading specific reference documents, then identifies the candidate model, separates facts from inference, checks for preservation of inspectable quantities, and prefers structured models.
Inputs & outputs
When to use twincat-export-preparation
- →Preparing model export
- →Validating PLC export readiness
- →Reviewing TwinCAT inference paths
About this skill
TwinCAT Export Preparation
Prepare TwinCAT-facing TE model export work with the repository's deployment constraints made explicit before any implementation claim is accepted.
Use This Skill For
- TwinCAT or Beckhoff-facing export planning;
- PLC-friendly model simplification or decomposition planning;
- review of whether a model family is export-plausible;
- preparation of deployment-facing technical notes or backlog items;
- checking whether a workflow preserves inspectable intermediate quantities.
Do Not Use This Skill For
- generic model-accuracy review with no deployment implications;
- broad DevOps or cloud deployment discussion;
- claiming deployment readiness without repository evidence.
Required Checks
Before making TwinCAT/export claims:
- Read
doc/reference_codes/testrig_twincat_ml_reference.md. - Read
doc/technical/2026-03/2026-03-26/2026-03-26-15-43-43_twincat_ml_export_and_testrig_reference_analysis.md. - Read the relevant
doc/reference_summaries/notes for: speed, torque, oil temperature, encoder zeroing, andDataValid. - Read the current repository model/report note most relevant to the export candidate.
Workflow
- Identify the candidate model or workflow being evaluated for TwinCAT-facing preparation.
- Separate: reference-backed deployment facts, current repository implementation, and open inference.
- Check whether the proposed path preserves: explicit operating variables, inspectable intermediate quantities, and analytical-versus-ML separation.
- Prefer harmonic quantities, conditioned coefficients, or other explicit decomposition outputs over opaque end-to-end inference stories.
- State clearly whether the result is: deployment-plausible, export-preparable, or actually deployment-ready.
Repository Priorities
- Treat rotational transmission error as the target signal.
- Keep speed, torque, oil temperature, angle, encoder zeroing, and
DataValidsemantics explicit when they matter. - Prefer structured or hybrid models with inspectable components over opaque black-box deployment stories.
- Keep TwinCAT/PLC claims grounded in repository code, reference notes, or clearly labeled inference.
Output Pattern
Prefer this structure:
- What the reference and current repository actually support.
- What makes the candidate export-plausible or not.
- What export/simplification steps are still required.
- What remains speculative or unimplemented.
File Targets To Read First
doc/reference_codes/testrig_twincat_ml_reference.mddoc/reference_summaries/doc/technical/2026-03/2026-03-26/2026-03-26-15-43-43_twincat_ml_export_and_testrig_reference_analysis.md- relevant
doc/guide/ - relevant
scripts/models/ - relevant
scripts/training/
Typical Outputs
- TwinCAT export-preparation note;
- PLC-friendly feasibility review;
- required simplification/export checklist;
- deployment-readiness boundary statement.
When not to use it
- →For generic model-accuracy review without deployment implications
- →For broad DevOps or cloud deployment discussions
- →For claiming deployment readiness without repository evidence
Limitations
- →The skill is specifically for TwinCAT-facing TE model export work.
- →It requires reading specific reference documents before making export claims.
- →The skill prioritizes structured or hybrid models over opaque black-box deployment stories.
How it compares
This skill enforces a disciplined approach to preparing models for TwinCAT export by requiring specific documentation checks and a structured workflow, ensuring PLC-friendliness and inspectable inference paths, unlike a generic model prepar
Compared to similar skills
twincat-export-preparation side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| twincat-export-preparation (this skill) | 0 | 4mo | No flags | Advanced |
| langchain-architecture | 8 | 2mo | Review | Intermediate |
| voice-agents | 8 | 6mo | No flags | Intermediate |
| ai-agents-architect | 5 | 6mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
langchain-architecture
wshobson
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
voice-agents
davila7
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu
ai-agents-architect
davila7
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.
llm-app-patterns
davila7
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
mlir-development
gmh5225
Expertise in MLIR (Multi-Level Intermediate Representation) and CIR (Clang IR) development for domain-specific compilation and high-level optimizations. Use this skill when building ML compilers, domain-specific languages, or working with multi-level compilation pipelines.
compiler-development
gmh5225
Expertise in compiler development using LLVM infrastructure including frontend design, IR generation, optimization passes, and code generation. Use this skill when building custom programming languages, implementing DSL compilers, or working on compiler internals.