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 Cai-aa/CAD-Agent-Hub --skill ansys-structural-workbenchgit clone --depth 1 https://github.com/Cai-aa/CAD-Agent-HubWrote 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/cai-aa/cad-agent-hub/ansys-structural-workbench)<a href="https://agentmods.dev/skills/cai-aa/cad-agent-hub/ansys-structural-workbench"><img src="https://agentmods.dev/badge/skills/cai-aa/cad-agent-hub/ansys-structural-workbench/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/cai-aa/cad-agent-hub/ansys-structural-workbench"><img src="https://agentmods.dev/badge/skills/cai-aa/cad-agent-hub/ansys-structural-workbench.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 | $0.00104 | $0.01301 |
| Opus 5 | $0.00052 | $0.00651 |
| Sonnet 5 | $0.00021 | $0.00260 |
| Haiku 4.5 | $0.00010 | $0.00130 |
Grade A, and why
ansys-structural-workbench 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 9d 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.
This is a copy
91% identical to ansys-structural-workbench — 25 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ANSYS Structural Workbench
Operate Workbench as an engineering workflow with explicit quality gates. Treat the MCP as the execution adapter and this Skill as the analysis, meshing, validation, and reporting policy.
Start safely
- Discover the available Workbench MCP tools and read
references/mcp-adapter.md. - Probe both bridge health and live Workbench/Mechanical state. A reachable server is not proof that a project, Model, or analysis is loaded.
- Convert the request into the contract in
references/job-spec.md, including every applicable analysis profile. Use a temporary in-memory object unless a saved spec benefits the task. - Inspect the current project before mutation. Never clear, overwrite, suppress, or replace existing user work without explicit authorization.
- Record assumptions. Stop for missing information only when no conservative, reversible default exists.
If the MCP lacks a required capability, use its generic Workbench/Mechanical script-execution tool when available. Otherwise report the exact unsupported gate; do not fabricate completion.
Select references
Always read:
references/core-workflow.mdreferences/quality-gates.md
Then read only what applies:
- Analysis behavior:
references/analysis-profiles.md - Mesh generation or review:
references/mesh-orchestration.mdandreferences/mesh-profiles.md - Solver failure or warnings:
references/solver-diagnostics.md - Double-shear clevis regression/smoke test:
references/example-clevis-pin.json
Execute the gated workflow
CAPABILITY_CHECK: prove that the MCP can inspect, modify, mesh, solve, query results, and export the evidence required by the selected profile set.INTAKE: normalize model source, units, materials, analysis profile, outputs, and acceptance criteria.MODEL_INSPECTION: inventory bodies, dimensions, materials, named selections, connections, analyses, loads, supports, and existing results.MODEL_SETUP: create only missing or authorized objects. Prefer existing named selections; otherwise use validated geometry predicates.MODEL_GATE: verify entity counts, geometry properties, material coverage, connection scoping, units, load directions, and rigid-body restraint.MESH_PLAN: classify bodies and critical regions before generating mesh.MESH_GATE: generate, inspect distributions and worst elements, repair by approved actions, and reject hard failures.PRE_SOLVE_GATE: inspect initial contact state where applicable and verify load-step tables and solution controls.SOLVE: solve and retain solver output, warnings, errors, substep history, and final converged time.SOLVER_GATE: reject incomplete or unconverged final states even if the UI says Completed.RESULT_EXTRACTION: extract scoped engineering quantities, reactions, energy, contact quantities, modal/buckling values, mesh statistics, and evidence images.VALIDATION_GATE: run deterministic checks and compare with analytical, test, or user-defined criteria when available.CONVERGENCE_GATE: compare at least the final two mesh levels for every configured metric. Do not use a singular peak stress as the only metric.REPORT: state pass, warning, blocked, or unsupported; include assumptions, evidence paths, limitations, and unresolved warnings.
What ships with it
16 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.
- agents/openai.yaml 246 B
- assets/structural-analysis-report-template.md 430 B
- references/analysis-profiles.md 2.2 KB
- references/core-workflow.md 2.5 KB
- references/example-clevis-pin.json 3.3 KB
- references/example-mesh-quality.json 541 B
- references/job-spec.md 3.1 KB
- references/mcp-adapter.md 2.9 KB
- references/mesh-orchestration.md 2.9 KB
- references/mesh-profiles.md 2.8 KB
- references/quality-gates.md 2.4 KB
- references/solver-diagnostics.md 1.6 KB
- scripts/evaluate_mesh_convergence.py 2.2 KB runs code
- scripts/evaluate_mesh_quality.py 2.3 KB runs code
- scripts/validate_job_spec.py 5.2 KB runs code
- scripts/validate_results.py 2.9 KB runs code
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.
- 9d ago First seen · 97 lines · 104 tokens per session scan A 307b91311ad7
ansys-structural-workbench is a skill published in the GitHub repository Cai-aa/CAD-Agent-Hub (38 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 1,301 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to ansys-structural-workbench, differing in 25 lines, and is treated as a copy.
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
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for 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
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
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.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…