Cylinder O Grid logo

Cylinder O Grid

CommunityPopular
Cai-aa
cylinder-o-grid

Plan, create, adapt, and quality-audit coin-style five-block O-grid hexahedral meshes for cylindrical CAE models. Use for software-independent O-grid planning or implementation in a selected preprocessor, including requests mentioning 钱币原理、圆柱网格、中心正方形、顶点切到圆周、结构化六面体网格, mapped square-to-circle partitions, or HEX8 meshes. Includes a generic planner and an Abaqus/CAE execution adapter; do not claim automated support in another CAE application without a matching adapter or proved live native-tool path.

Overview

PublisherCai-aa
RepositoryCAE-Agent-Hub
Skill namecylinder-o-grid
Stars
1K
Forks
130
Bundled files
9
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.

  • 9 bundled files

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

  • Open source

    Published by Cai-aa on GitHub. Read the source before you install it.

Installation

Install the Cylinder O Grid 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.
    https://github.com/Cai-aa/CAE-Agent-Hub/tree/main/Skill/General/cylinder-o-grid
  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/Cai-aa/CAE-Agent-Hub.git /tmp/CAE-Agent-Hub
mkdir -p .claude/skills
cp -r /tmp/CAE-Agent-Hub/Skill/General/cylinder-o-grid .claude/skills/cylinder-o-grid
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cylinder O Grid 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 Cylinder O Grid 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 Cylinder O Grid 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.

Cylinder O-Grid

Create a reviewable coin-style O-grid and accept it only after topology, mesh, and analysis checks pass in the selected CAE workflow.

Establish the task

Collect or infer only low-risk inputs:

  • Identify the target preprocessor, solver, analysis type, and whether the task is plan-only or a live implementation.
  • Distinguish a new cylinder from an existing production part.
  • Record radius R, length L, cylinder axis, units, and any interfaces or local refinement zones.
  • Record the requested brick family and the exact solver-specific formulation when known.
  • Record either target element size or counts for one square side/90-degree arc, radial layers, and axial layers.
  • Ask before changing geometry, deleting an existing mesh, replacing a model, or relaxing a quality gate.

If live access to the target CAE application is unavailable, generate a plan and preview, label them as unexecuted in that application, and do not claim that the mesh was created or validated there.

Enforce the topology

Use a circular cross-section with one centered, axis-aligned square. Connect each square vertex to the circle along the same 45-degree radial direction. Preserve these invariants:

  • Keep 0 < a < R/sqrt(2), where a is the square half-width.
  • Create five sweepable cross-section regions: one center block and four outer sectors.
  • Use the same count n_side on every square side and corresponding 90-degree outer arc.
  • Use the same n_radial on all four vertex-to-circle connector edges.
  • Use the same n_axial on all edges parallel to the cylinder axis.
  • Keep partitions continuous through the full cylinder length and share nodes at every internal boundary.
  • Reject free tetrahedral fallback unless the user explicitly changes the objective.

Read references/topology.md before selecting the square size or element counts.

Route to the target software

  • For every target, first produce and review the software-independent plan with scripts/plan_ogrid.py.
  • For Abaqus/CAE, read references/abaqus.md. Use scripts/abaqus_build_ogrid.py only for a clean, straight cylinder aligned with global Z; adapt the workflow for existing or differently oriented parts.
  • For another CAE preprocessor, translate the five logical blocks, edge roles, mapped quadrilateral controls, axial sweep, and quality gates into its native operations. Use only available registered tools or documented native APIs. No non-Abaqus automated builder is bundled, so deliver plan-only evidence if live construction and readback cannot be proved.

Do not infer solver element codes from the generic HEX8 label. Report both the generic brick family and the exact target formulation actually assigned.

Execute the workflow

  1. Inspect the current model and preserve a checkpoint before mutation.
  2. Produce an O-grid plan and preview with scripts/plan_ogrid.py.
  3. Select the applicable software route and confirm that its required operations are available.
  4. Partition the cross-section into five logical blocks and propagate them continuously through the cylinder length.
  5. Apply mapped quadrilateral controls on the cross-section and structured or swept hexahedral controls through the axis.
  6. Seed by topological role, not by fragile edge indices.
  7. Generate the mesh and run every gate in references/quality-gates.md, plus target-specific diagnostics.
  8. Save the native model, preview, mesh statistics, quality results, warnings, and any solver audit together.

For live automation, prove the real application session with harmless inspection calls before mutation, save a checkpoint, and preserve raw tool output. A bridge response, generated file, or process return code alone is not mesh-quality or solver-validity evidence.

Use the bundled scripts

Create the software-independent plan:

powershell
python scripts/plan_ogrid.py --radius 10 --length 30 --square-ratio 0.40 --circumferential 48 --radial 6 --axial 24 --output-dir ogrid-plan

Dry-run the Abaqus adapter without importing Abaqus modules:

powershell
python scripts/abaqus_build_ogrid.py --dry-run --radius 10 --length 30 --square-ratio 0.40 --circumferential 48 --radial 6 --axial 24

Run the adapter inside Abaqus/CAE after reviewing the plan:

powershell
abaqus cae noGUI=scripts/abaqus_build_ogrid.py -- --radius 10 --length 30 --square-ratio 0.40 --circumferential 48 --radial 6 --axial 24 --cae-out cylinder_ogrid.cae

Treat the Abaqus builder as a starting point for a clean cylinder. Do not run it against a production model without adapting names, orientation, interfaces, and save path.

Report acceptance evidence

Return:

  • Target application, solver, and execution mode: generic plan, live native workflow, or bundled adapter.
  • Geometry parameters and a/R.
  • n_side, total circumferential count, n_radial, and n_axial.
  • Expected and actual node/element counts.
  • Generic brick family, exact assigned formulation, and verified HEX percentage.
  • Mesh-control technique and axial layering direction.
  • Failed mesh diagnostics, worst aspect-ratio result, negative/zero-volume count, and unmeshed regions.
  • A cross-section image with element edges and an axial/swept view.
  • Any unverified item, unavailable target-specific check, or relaxed threshold.

Never state “high quality” without attached measurements and a visual check of the four square-corner transition zones.

Use assets/coin-ogrid-topology.svg as the software-independent topology reference. Use assets/abaqus-live-smoke.png only as an Abaqus appearance example. Never infer quality metrics from images alone.

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 Cylinder O Grid AI skill do?

Plan, create, adapt, and quality-audit coin-style five-block O-grid hexahedral meshes for cylindrical CAE models. Use for software-independent O-grid planning or implementation in a selected preprocessor, including requests mentioning 钱币原理、圆柱网格、中心正方形、顶点切到圆周、结构化六面体网格, mapped square-to-circle partitions, or HEX8 meshes. Includes a generic planner and an Abaqus/CAE execution adapter; do not claim automated support in another CAE application without a matching adapter or proved live native-tool path.

Why use Cylinder O Grid on TypingMind?

Because you install it once and use it with any model. Cylinder O Grid 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 Cylinder O Grid in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Cai-aa/CAE-Agent-Hub/tree/main/Skill/General/cylinder-o-grid. 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 Cylinder O Grid?

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 Cylinder O Grid?

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

Is the Cylinder O Grid AI skill free?

Yes. It is published on GitHub by Cai-aa 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 👇