New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ansys Structural Workbench

by Cai-aa in Cai-aa/CAE-Agent-Hub

Operate or inspect live ANSYS Workbench Mechanical structural simulations through the configured MCP, including model setup, materials, connections, loads, mesh, solve, convergence, validation, and…

MITAuto-check passed

Install Ansys Structural Workbench

skills CLI
$ npx skills add Cai-aa/CAE-Agent-Hub --skill ansys-structural-workbench -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Cai-aa/CAE-Agent-Hub ansys-structural-workbench --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Cai-aa/CAE-Agent-Hub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Skill/Ansys/ansys-structural-workbench .claude/skills/ansys-structural-workbench && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ansys-structural-workbench
GitHub stars
998
Token cost
~2.2k tokens
SKILL.md length
951 words
Files
33 (incl. scripts, references, assets)
Skills in repo
57
Repo updated
First seen
Licence
MIT

At a glance

Operate or inspect live ANSYS Workbench Mechanical structural simulations through the configured MCP, including model setup, materials, connections, loads, mesh, solve, convergence, validation, and…

  • Works in 5 steps: Discover the available Workbench MCP… → Probe both bridge health and live… → Convert the request into the contract in… → …
  • A user asks Codex to create
  • SKILL.md covers Mandatory book-guidance route, Start safely, Select references and Execute the gated workflow, plus 5 more sections
  • Validate a live Workbench structural analysis

What it does

Ansys Structural Workbench is an agent skill from Cai-aa/CAE-Agent-Hub. Operate or inspect live ANSYS Workbench Mechanical structural simulations through the configured MCP, including model setup, materials, connections, loads, mesh, solve, convergence, validation, and reporting. Use whenever a user asks Codex to create, configure, inspect, mesh, solve, troubleshoot, or validate a live Workbench structural analysis. Before model decisions or mutation, load ansys-workbench-practical-reference once as the book-distilled router and then the matching narrow reference Skill. Load…

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 35 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/structural-analysis-report-template.md` and `references/analysis-profiles.md`).

It works with Model Context Protocol. The licence is MIT.

When your agent uses it

  • A user asks Codex to create
  • Validate a live Workbench structural analysis
  • Theory-only questions
  • Fluent/CFX operation

Example prompts

  • “/ansys-structural-workbench”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Discover the available Workbench MCP tools and read references/mcp-adapter.md. Require the registered server name ansys-workbench unless…
  2. Probe both bridge health and live Workbench/Mechanical state. A reachable server is not proof that a project, Model, or analysis is loaded.
  3. Convert the request into the contract in references/job-spec.md, including every applicable analysis profile. Use a temporary in-memory…
  4. Inspect the current project before mutation. Never clear, overwrite, suppress, or replace existing user work without explicit authorization.
  5. Record assumptions. Stop for missing information only when no conservative, reversible default exists.

What it can do on your machine

Read from SKILL.md and the folder at commit 194ef49. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ansys Structural Workbench loads about 2.2k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 190 tokens; SKILL.md has 951 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~190
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Cai-aa/CAE-Agent-Hub at commit 194ef49, republished under its MIT licence (© Cai-aa). 951 words, ~2,234 tokens.

Download SKILL.mdSave it as .claude/skills/ansys-structural-workbench/SKILL.md (or your agent's skills folder). This skill also uses 32 other files; get the full folder from GitHub.
name
ansys-structural-workbench
description
Operate or inspect live ANSYS Workbench Mechanical structural simulations through the configured MCP, including model setup, materials, connections, loads, mesh, solve, convergence, validation, and reporting. Use whenever a user asks Codex to create, configure, inspect, mesh, solve, troubleshoot, or validate a live Workbench structural analysis. Before model decisions or mutation, load ansys-workbench-practical-reference once as the book-distilled router and then the matching narrow reference Skill. Load static-modeling for every Static Structural task, plus nonlinear-contact for contact, friction, plasticity, large deformation, buckling, or nonlinear convergence. Do not use for theory-only questions or Fluent/CFX operation.

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.

Mandatory book-guidance route

Before inspecting settings for engineering acceptance, mutating the model, meshing, or solving, load ansys-workbench-practical-reference once and use it to select the physics-specific book-derived guidance. This is a required intake gate, not an optional source lookup.

  • Every Static Structural task must load ansys-workbench-static-modeling-reference.
  • A static task with contact or friction must load both ansys-workbench-static-modeling-reference and ansys-workbench-nonlinear-contact-reference.
  • Also load ansys-workbench-nonlinear-contact-reference for plasticity, large deflection, buckling, stabilization, changing contact state, or nonlinear convergence.
  • Modal, transient, explicit, thermal, and optimization tasks load only their matching narrow reference Skill; do not load unrelated book domains.

The book-derived Skills govern modeling assumptions and physical checks. This Skill governs live MCP actions, evidence, and safe execution. Record which guidance Skills were loaded in the task intake or final report. Do not repeatedly re-route after the applicable set has been loaded.

Start safely

  1. Discover the available Workbench MCP tools and read references/mcp-adapter.md. Require the registered server name ansys-workbench unless the user configured an equivalent alias.
  2. Probe both bridge health and live Workbench/Mechanical state. A reachable server is not proof that a project, Model, or analysis is loaded.
  3. 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.
  4. Inspect the current project before mutation. Never clear, overwrite, suppress, or replace existing user work without explicit authorization.
  5. 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.md
  • references/quality-gates.md

Then read only what applies:

  • Analysis behavior: references/analysis-profiles.md
  • Mesh generation or review: references/mesh-orchestration.md and references/mesh-profiles.md
  • Mesh repair loop: references/mesh-closed-loop.md
  • Solver failure or warnings: references/solver-diagnostics.md
  • Double-shear clevis regression/smoke test: references/example-clevis-pin.json

Execute the gated workflow

  1. CAPABILITY_CHECK: prove that the MCP can inspect, modify, mesh, solve, query results, and export the evidence required by the selected profile set.
  2. INTAKE: normalize model source, units, materials, analysis profile, outputs, and acceptance criteria.
  3. MODEL_INSPECTION: inventory bodies, dimensions, materials, named selections, connections, analyses, loads, supports, and existing results.
  4. MODEL_SETUP: create only missing or authorized objects. Prefer existing named selections; otherwise use validated geometry predicates.
  5. MODEL_GATE: verify entity counts, geometry properties, material coverage, connection scoping, units, load directions, and rigid-body restraint.
  6. MESH_PLAN: classify bodies and critical regions before generating mesh.
  7. MESH_GATE: generate, extract normalized metrics and worst-element regions, run recommend_mesh_repairs.py, apply at most the configured repair limit through the MCP, regenerate, and reject unresolved hard failures.
  8. PRE_SOLVE_GATE: inspect initial contact state where applicable and verify load-step tables and solution controls.
  9. SOLVE: solve and retain solver output, warnings, errors, substep history, and final converged time.
  10. SOLVER_GATE: reject incomplete or unconverged final states even if the UI says Completed.
  11. RESULT_EXTRACTION: extract scoped engineering quantities, reactions, energy, contact quantities, modal/buckling values, mesh statistics, and evidence images.
  12. VALIDATION_GATE: run deterministic checks and compare with analytical, test, or user-defined criteria when available.
  13. 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.
  14. REPORT: state pass, warning, blocked, or unsupported; include assumptions, evidence paths, limitations, and unresolved warnings.

Each gate must produce a structured status and evidence. Do not continue past a hard failure merely to create a report.

Show full SKILL.md (353 more words)Show less

Geometry and scoping rules

  • Prefer named selections over raw topology IDs.
  • Validate every selection by entity type, body, count, location, size, orientation, and surface/curve type as applicable.
  • Allow temporary entity IDs only after property validation; recreate semantic selections before later operations.
  • Reject zero or ambiguous matches. Never silently choose the nearest entity.
  • Prefer imported CAD for complex geometry. Limit procedural construction to geometries supported by the MCP and straightforward to validate.

Mesh rules

  • Choose beam, shell, or solid representation from structural behavior, not convenience.
  • Prefer sweep or MultiZone only when topology and physics support them; a good quadratic tetrahedral mesh is preferable to distorted hexahedra.
  • Resolve thickness, curvature, holes, fillets, contacts, load introduction, and expected gradients.
  • Inspect metric distributions and worst-element locations, not only a single minimum.
  • Keep opposing contact meshes reasonably similar and prove adequacy with engineering-result convergence.
  • Do not automatically suppress geometry or enable aggressive defeaturing without preserving a record and user intent.

Deterministic scripts

Run with a known-good Python interpreter:

text
python scripts/validate_job_spec.py job.json
python scripts/evaluate_mesh_quality.py mesh-quality.json
python scripts/recommend_mesh_repairs.py mesh-loop.json
python scripts/validate_results.py analysis-results.json
python scripts/validate_contact_results.py contact-results.json
python scripts/evaluate_mesh_convergence.py convergence.json
python scripts/normalize_units.py quantities.json
python scripts/calculate_reference_values.py references.json
python scripts/build_analysis_report.py report-data.json output-report.md

The scripts emit JSON and return exit code 0 for pass, 1 for warning/fail, and 2 for invalid input. Read their output; do not replace it with qualitative judgment.

For a live mesh loop, prepend a JSON-compatible REQUEST object to scripts/mechanical_mesh_bridge.py and send the complete code through workbench_queue_execute_python_tool. Use probe_session, mesh_snapshot, apply_mesh_updates, or generate_mesh. Parse the ANSYS_STRUCTURAL_JSON: stdout marker. Supply exact existing object names and typed property updates; reject ambiguous names and unsupported metric properties.

Non-negotiable rules

  • Never silently change units, materials, load magnitudes, contacts, or supports.
  • Never enable weak springs solely to hide rigid-body motion.
  • Never claim a solve, result, image, mesh statistic, or convergence value that was not observed.
  • Never use an unconverged substep as the final result.
  • Never equate solver completion with model validity.
  • Never judge mesh adequacy from appearance alone.
  • Never compare nominal hand calculations directly with a contact-edge or singular nodal peak without explaining the mismatch.
  • Preserve the project and evidence needed to reproduce the reported state.

Output

Return the live project/system analyzed, execution status, assumptions, model and mesh summary, solver diagnostics, validation matrix, convergence table, result artifacts, and engineering limitations. Match the user's language.

© Cai-aa, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 32 other files (scripts, references, assets) in Skill/Ansys/ansys-structural-workbench of Cai-aa/CAE-Agent-Hub.

  • SKILL.md
  • agents/openai.yaml
  • assets/structural-analysis-report-template.md
  • references/analysis-profiles.md
  • references/core-workflow.md
  • references/example-bolted-joint.json
  • references/example-clevis-pin.json
  • references/example-contact-results.json
  • references/example-mesh-loop.json
  • references/example-mesh-quality.json
  • references/example-reference-values.json
  • references/example-report-data.json
  • references/example-units.json
  • references/job-spec.md
  • references/mcp-adapter.md
  • references/mesh-closed-loop.md
  • references/mesh-orchestration.md
  • references/mesh-profiles.md
  • … and 15 more

Open the folder on GitHubat commit 194ef49

Compare with similar skills

Ansys Structural Workbench next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ansys Structural Workbench compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ansys Structural Workbench this skillCai-aa/CAE-Agent-Hub998—~2.2kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills8.4k6 repos~3.2kAutomated safety check: NotesApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Figma use_figma Plugin API Rules

    warpdotdev/warp

    Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed

  • Stitch to Remotion Walkthrough Videos

    google-labs-code/stitch-skills

    Official

    Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.

    8.4k GitHub starsUsed in 6 repos~3.2k tokens
    Media & CreativeAuto-check: notes

  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed

More from Cai-aa/CAE-Agent-Hub

All 57 skills in this repo

  • Cylinder O Grid

    Cai-aa/CAE-Agent-Hub

    Plan, create, adapt, and quality-audit coin-style five-block O-grid hexahedral meshes for cylindrical CAE models.

    998 GitHub stars~1.6k tokensUpdated 8 days ago
    Auto-check passed

  • Comsol Motor Nvh Evidence

    Cai-aa/CAE-Agent-Hub

    Evidence-first COMSOL Java API and batch workflow for permanent-magnet motor NVH.

    998 GitHub stars~1.3k tokensUpdated 8 days ago
    Auto-check passed

  • Aedt Evidence Electromagnetics

    Cai-aa/CAE-Agent-Hub

    Evidence-first Ansys Electronics Desktop and PyAEDT automation for Maxwell, HFSS, Q3D, Icepak, and related electromagnetic workflows.

    998 GitHub stars~591 tokensUpdated 8 days ago
    Auto-check passed

  • Ansys Mechanical Evidence Structural

    Cai-aa/CAE-Agent-Hub

    Evidence-first Ansys Mechanical structural automation through Workbench RunWB2 journals, Mechanical Scripting/ACT ExtAPI, or PyMechanical gRPC.

    998 GitHub stars~554 tokensUpdated 8 days ago
    Auto-check passed

  • Run Fluent Autoclave

    Cai-aa/CAE-Agent-Hub

    Run, diagnose, reproduce, and validate ANSYS Fluent CFD simulations of forced-convection autoclaves using Fluent MCP or PyFluent.

    998 GitHub stars~984 tokensUpdated 8 days ago
    Auto-check passed

  • Abaqus Load

    Cai-aa/CAE-Agent-Hub

    Apply forces and pressures to structures. An agent skill from Cai-aa/CAE-Agent-Hub.

    998 GitHub stars~1.2k tokensUpdated 8 days ago
    Auto-check passed

Works with

Questions about Ansys Structural Workbench

What does Ansys Structural Workbench do?

Operate or inspect live ANSYS Workbench Mechanical structural simulations through the configured MCP, including model setup, materials, connections, loads, mesh, solve, convergence, validation, and…. Ansys Structural Workbench is an agent skill from Cai-aa/CAE-Agent-Hub. Operate or inspect live ANSYS Workbench Mechanical structural simulations through the configured MCP, including model setup, materials, connections, loads, mesh, solve, convergence, validation, and reporting.

When should I use Ansys Structural Workbench?

Ansys Structural Workbench fits situations like: A user asks Codex to create; validate a live Workbench structural analysis; theory-only questions; fluent/CFX operation.

How do I install Ansys Structural Workbench in Claude Code?

Run `npx skills add Cai-aa/CAE-Agent-Hub --skill ansys-structural-workbench -a claude-code`. Or copy the skill folder (Skill/Ansys/ansys-structural-workbench in Cai-aa/CAE-Agent-Hub) into .claude/skills/ansys-structural-workbench in your project. Claude Code loads it when a task matches its description.

How do I install Ansys Structural Workbench in Codex?

Run `npx skills add Cai-aa/CAE-Agent-Hub --skill ansys-structural-workbench -a codex`. Or copy the skill folder (Skill/Ansys/ansys-structural-workbench in Cai-aa/CAE-Agent-Hub) into .agents/skills/ansys-structural-workbench in your project. Codex loads it when a task matches its description.

Can I use Ansys Structural Workbench in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Cai-aa/CAE-Agent-Hub --skill ansys-structural-workbench -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ansys-structural-workbench, .gemini/skills/ansys-structural-workbench, .github/skills/ansys-structural-workbench and .opencode/skills/ansys-structural-workbench in your project.

What does Ansys Structural Workbench need to run?

SKILL.md names no scripts, command-line tools or credentials: Ansys Structural Workbench is instructions for the agent only. Our summary lists: Python 3.

Does Ansys Structural Workbench access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ansys Structural Workbench safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Ansys Structural Workbench use?

Ansys Structural Workbench is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ansys Structural Workbench use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.3k tokens, read only when the agent opens those files.

What are the alternatives to Ansys Structural Workbench?

Skills that share tags, products or a category with Ansys Structural Workbench: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ansys Structural Workbench?

Cai-aa (a GitHub user) maintains it in Cai-aa/CAE-Agent-Hub, which has 998 GitHub stars. The repository holds 57 skills in this directory. The repository was last updated on September 30, 2026.

Source: Cai-aa/CAE-Agent-Hub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.