Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Suzhou-Tongyuan/sysplorer-mcp-server --skill ty-cadtool-modelinggit clone --depth 1 https://github.com/Suzhou-Tongyuan/sysplorer-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/suzhou-tongyuan/sysplorer-mcp-server/ty-cadtool-modeling)<a href="https://agentmods.dev/skills/suzhou-tongyuan/sysplorer-mcp-server/ty-cadtool-modeling"><img src="https://agentmods.dev/badge/skills/suzhou-tongyuan/sysplorer-mcp-server/ty-cadtool-modeling/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/suzhou-tongyuan/sysplorer-mcp-server/ty-cadtool-modeling"><img src="https://agentmods.dev/badge/skills/suzhou-tongyuan/sysplorer-mcp-server/ty-cadtool-modeling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00405 | $0.04321 |
| Opus 5.5 | $0.00162 | $0.01728 |
| Sonnet 5.5 | $0.00081 | $0.00864 |
| Haiku 4.5 | $0.00040 | $0.00432 |
Grade A, and why
ty-cadtool-modeling scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 19d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TY CADToolbox Modeling (geometry-driven)
Convert a real CAD assembly into a Sysplorer Modelica model with the CADToolbox Python API, driven through the Sysplorer MCP. Unlike ty-mechanical-modeling (which hand-authors TY library components from a text scenario), this skill is geometry-first: mass, inertia and centroid come from the solid, and the topology comes from joints you place on real parts. GenerateMoModel then emits a laid-out .mo automatically.
Use this only when there is (or will be) a geometry file to import. If the user only describes a mechanism in words with no CAD file, switch to ty-mechanical-modeling.
The mental model: replicate the official UI process, blind
The CADToolbox help docs (新手入门 + 应用案例) drive every model through the same five named stages; only stages ②–③ differ by domain. The GUI user picks geometry features and the tool infers positions and axes (闪电模式 + 特征拾取智能推理). You instead drive it blind through MCP, so your job at each stage is to reproduce what that UI step does with the API — e.g. where the user picks a circular face and the tool snaps the joint to its axis, you Measure that circle's centre + axis and pass the numbers. Keeping the official stage names in mind lets you map cleanly to the docs and to what the user sees.
After GenerateMoModel, the model is an ordinary Modelica physical model, so the downstream discipline of ty-sysplorer-modeling-rules applies: check_model → translate → simulate → result; paths only via Agent CWD / GetDirectory; and the hard bans (ClearAll, ChangeDirectory, Exit) still hold. Layout is produced by GenerateMoModel (its own engine lays out components, connections, joints), so manual smart_layout writeback is normally unnecessary — only fall back to it if the generated diagram is unusable.
Minimal Reading
| Need | Read |
|---|---|
| How to drive CADToolbox through MCP (the bridge) | references/mcp-workflow.md |
| Full API surface (every function, grouped) | references/api-reference.md |
| Multibody element rules (joints, markers, contacts, naming, coords, closed loops) | references/multibody-elements.md |
| Get a joint's exact position & axis from geometry (replicate 闪电模式智能推理 while blind) | references/joint-placement.md |
| Fluid element rules (tank/rib slicing, ports, media) | references/fluid-elements.md |
| Failures and repair | references/common-errors.md |
| New multibody model (5-stage walkthrough) | workflows/build-multibody-from-cad.md |
| New fluid (tank) model (5-stage walkthrough) | workflows/build-fluid-from-cad.md |
| Iterate / re-enter the toolbox on an existing model | workflows/iterate-existing-model.md |
| Ready-to-edit run_sysplorer_api templates | templates/run-script-skeleton.md |
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/api-reference.md 19 KB
- references/common-errors.md 7.3 KB
- references/fluid-elements.md 5.7 KB
- references/joint-placement.md 16 KB
- references/mcp-workflow.md 6.5 KB
- references/multibody-elements.md 12 KB
- skill_info.json 646 B
- SKILL_ZH.md 14 KB
- templates/run-script-skeleton.md 7.9 KB
- workflows/build-fluid-from-cad.md 5.3 KB
- workflows/build-multibody-from-cad.md 8.1 KB
- workflows/iterate-existing-model.md 2.1 KB
- 使用说明.md 4.4 KB
- 版本说明.md 9.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 19d ago First seen · 118 lines · 405 tokens per session scan A 224ed5cffa4c
ty-cadtool-modeling is a skill published in the GitHub repository Suzhou-Tongyuan/sysplorer-mcp-server (10 stars, last pushed 20d ago), licensed MIT. It adds 405 tokens to every session and 4,321 once invoked, about $0.0016 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.