Agent skill

Nx Modeling

Create or edit native Siemens NX parts through the existing NXMCP tools, including sketch/extrude workflows, result checks, and recovery from stale references or uncertain execution.

MITAuto-check passedAgent Workflows

Install Nx Modeling

skills CLI

$ npx skills add DreamEnding/NX_MCP --skill nx-modeling -a claude-code

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

GitHub CLI

$ gh skill install DreamEnding/NX_MCP nx-modeling --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/DreamEnding/NX_MCP.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nx-modeling .claude/skills/nx-modeling && 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/

Paste into Claude Code

Install the "nx-modeling" agent skill from https://github.com/DreamEnding/NX_MCP/tree/master/skills/nx-modeling into .claude/skills/nx-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nx-modeling", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/DreamEnding/NX_MCP/tree/master/skills/nx-modeling

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add DreamEnding/NX_MCP --skill nx-modeling -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install DreamEnding/NX_MCP nx-modeling --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DreamEnding/NX_MCP.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/nx-modeling .agents/skills/nx-modeling && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "nx-modeling" agent skill from https://github.com/DreamEnding/NX_MCP/tree/master/skills/nx-modeling into .agents/skills/nx-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nx-modeling", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add DreamEnding/NX_MCP --skill nx-modeling -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install DreamEnding/NX_MCP nx-modeling --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DreamEnding/NX_MCP.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/nx-modeling .cursor/skills/nx-modeling && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "nx-modeling" agent skill from https://github.com/DreamEnding/NX_MCP/tree/master/skills/nx-modeling into .cursor/skills/nx-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nx-modeling", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/DreamEnding/NX_MCP.git --path skills/nx-modeling

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add DreamEnding/NX_MCP --skill nx-modeling -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install DreamEnding/NX_MCP nx-modeling --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DreamEnding/NX_MCP.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/nx-modeling .gemini/skills/nx-modeling && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "nx-modeling" agent skill from https://github.com/DreamEnding/NX_MCP/tree/master/skills/nx-modeling into .gemini/skills/nx-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nx-modeling", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install DreamEnding/NX_MCP nx-modeling

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add DreamEnding/NX_MCP --skill nx-modeling -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/DreamEnding/NX_MCP.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/nx-modeling .github/skills/nx-modeling && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "nx-modeling" agent skill from https://github.com/DreamEnding/NX_MCP/tree/master/skills/nx-modeling into .github/skills/nx-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nx-modeling", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add DreamEnding/NX_MCP --skill nx-modeling -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install DreamEnding/NX_MCP nx-modeling --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DreamEnding/NX_MCP.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/nx-modeling .opencode/skills/nx-modeling && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "nx-modeling" agent skill from https://github.com/DreamEnding/NX_MCP/tree/master/skills/nx-modeling into .opencode/skills/nx-modeling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "nx-modeling", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: nx-modeling
GitHub stars: 112
Token cost: ~1.2k tokens
SKILL.md length: 622 words
Files: 1
Skills in repo: 1
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Create or edit native Siemens NX parts through the existing NXMCP tools, including sketch/extrude workflows, result checks, and recovery from stale references or uncertain execution.

Works in 4 steps: Discover the server's actual tool list… → Establish the target part, requested… → Use paths relative to the configured… → …
Tasks that involve MCP servers
SKILL.md covers Before changing a part, Modeling workflow and Recovery and stopping conditions
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Nx Modeling is an agent skill from DreamEnding/NX_MCP. Create or edit native Siemens NX parts through the existing NXMCP tools, including sketch/extrude workflows, result checks, and recovery from stale references or uncertain execution. Not for arbitrary Journal execution or CAD-to-USD conversion.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. The repository describes itself as: MCP server for Siemens NX (UG) — AI agents control NX GUI via 47+ tools. The licence is MIT.

When your agent uses it

Tasks that involve MCP servers

Example prompts

“/nx-modeling”

Workflow steps

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

Discover the server's actual tool list and input/output schemas. Do not invent
Establish the target part, requested changes, units, and expected result.
Use paths relative to the configured NX_MCP_WORKSPACE. For a new part, choose
Confirm that a mutation is within the user's requested task. Do not enable

What it can do on your machine

Read from SKILL.md and the folder at commit e08cdf6. 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
No scripts in the folder and no shell commands in SKILL.md.
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

Nx Modeling loads about 1.2k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 622 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~64
When it runs · the whole SKILL.md, loaded when a task matches: ~1.2k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from DreamEnding/NX_MCP at commit e08cdf6, republished under its MIT licence (© DreamEnding). 622 words, ~1,196 tokens.

Download SKILL.mdSave it as .claude/skills/nx-modeling/SKILL.md (or your agent's skills folder).

name: nx-modeling
description: Create or edit native Siemens NX parts through the existing NX_MCP tools, including sketch/extrude workflows, result checks, and recovery from stale references or uncertain execution. Not for arbitrary Journal execution or CAD-to-USD conversion.

NX Modeling

Use the discovered default NX_MCP tools to complete the user's modeling task. A tool returning successfully is not, by itself, proof of the intended model.

Before changing a part

Discover the server's actual tool list and input/output schemas. Do not invent tools or assume experimental tools are available. Call nx_status; if the bridge is unavailable, report the missing prerequisite rather than attempting a direct NXOpen attach. Read the setup and validation guide only when setup or acceptance is requested.
Establish the target part, requested changes, units, and expected result. Read nx_status.units: mm or inch is the active work part's native length unit. Sketch coordinates and extrusion distances use that unit. Convert the user's dimensions into it before modeling. If units are null or absent on an older bridge, obtain them from verified context or ask before using numbers.
Use paths relative to the configured NX_MCP_WORKSPACE. For a new part, choose a fresh path and pass units explicitly. A disposable acceptance run requires no active part; ordinary editing may use the user's explicitly selected part. Do not close an unrelated part or overwrite files to make a workflow proceed.
Confirm that a mutation is within the user's requested task. Do not enable experimental or Journal flags to work around a missing capability. For current support and evidence, read the capability matrix.

Modeling workflow

Use explicit object IDs returned by tools, not guessed names. Query the relevant objects before editing and retain the current part identity. If the active part changes unexpectedly, stop and establish which part the user wants to modify.

For example, to create a 20 x 10 x 12.5 mm rectangular solid in a new part:

nx_create_part(path=<fresh relative .prt path>, units="mm") and record the part ID.
nx_list_bodies to establish the baseline body count.
nx_create_sketch(plane="XY") and capture its object.id as sketch_id.
nx_sketch_rectangle(sketch_id, corner1={x: 0, y: 0}, corner2={x: 20, y: 10}).
nx_finish_sketch(sketch_id) before nx_extrude(sketch_id, distance=12.5).
Query bodies/features and verify the expected new body and feature. These queries check model structure, not exact dimensional metrology.
Save or export STEP only as requested. Check the returned export path and, if filesystem access is available, verify a newly created nonempty file. Report any verification that could not be performed rather than claiming it passed.

Do not copy the acceptance runner's undo/cleanup into an ordinary modeling task: that runner deliberately exports the solid, then undoes it before saving the .prt. Saving normally should retain the user's intended model. Save and close operate on the work part, not its entire assembly tree; nx_close_part saves by default, so always choose its save argument deliberately when closing is requested.

Show full SKILL.md (178 more words)Show less

Recovery and stopping conditions

On validation errors, correct the inputs; do not repeat an unchanged request.
After undo or failed-mutation rollback, discard cached object references, including nx_status.active_part.id. Call nx_status and query fresh object IDs before continuing. IDs are session references, not persistent asset identities.
For details.execution_state="unknown" (including uncertain timeout or disconnect), do not automatically replay a mutation. Reconnect if necessary, inspect the active part and relevant objects, then reconcile the observed state with the requested result. If queries cannot resolve the uncertainty, ask for inspection rather than guessing that the operation failed.
not_started alone is not permission to retry: only a documented retryable failure whose cause has been resolved can be reissued. Never loop on errors.
On NX_ROLLBACK_FAILED, stop writes. Read the recovery contract. Discard-close/reopen only an owned disposable part or with explicit permission to discard unsaved work. Restarting a bridge does not repair an uncertain model.

Finish with the part/artifact paths, checks actually performed, and any remaining uncertainty. Keep bridge tokens and descriptors out of reports. Batch acceptance is not evidence of a responsive interactive NX GUI.

Files

Just SKILL.md in skills/nx-modeling of DreamEnding/NX_MCP.

Open the folder on GitHubat commit e08cdf6

Compare with similar skills

Nx Modeling 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.

Nx Modeling compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Nx Modeling this skillDreamEnding/NX_MCP	112	—	~1.2k	Automated safety check: Pass	MIT	yesterday
MCP Server Builderanthropics/skills	180k	63 repos	~2.3k	Automated safety check: Pass	Apache-2.0	yesterday
MCP Server BuildershareAI-lab/learn-claude-code	78k	4 repos	~1.2k	Automated safety check: Pass	MIT	13 days ago
MCP Integration for Pluginsanthropics/claude-plugins-official	38k	11 repos	~3.1k	Automated safety check: Pass	Apache-2.0	today
Microsoft Skill CreatorMicrosoftDocs/mcp	1.9k	3 repos	~2.1k	Automated safety check: Pass	CC-BY-4.0	3 days ago
Crush Configurationcharmbracelet/crush	29k	—	~3.7k	Automated safety check: Pass	Custom licence	today

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 63 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 4 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
Microsoft Skill Creator
MicrosoftDocs/mcp
Official
Create agent skills for Microsoft technologies using official documentation.
1.9k GitHub starsUsed in 3 repos~2.1k tokens
Agent WorkflowsAuto-check passed
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
29k GitHub stars~3.7k tokensUpdated today
Agent WorkflowsAuto-check passed
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
26k GitHub stars~4.1k tokensUpdated today
Agent WorkflowsAuto-check passed

Questions about Nx Modeling

What does Nx Modeling do?

Create or edit native Siemens NX parts through the existing NXMCP tools, including sketch/extrude workflows, result checks, and recovery from stale references or uncertain execution. Nx Modeling is an agent skill from DreamEnding/NX_MCP. Create or edit native Siemens NX parts through the existing NXMCP tools, including sketch/extrude workflows, result checks, and recovery from stale references or uncertain execution.

When should I use Nx Modeling?

Nx Modeling fits situations like: tasks that involve MCP servers.

How do I install Nx Modeling in Claude Code?

Run `npx skills add DreamEnding/NX_MCP --skill nx-modeling -a claude-code`. Or copy the skill folder (skills/nx-modeling in DreamEnding/NX_MCP) into .claude/skills/nx-modeling in your project. Claude Code loads it when a task matches its description.

How do I install Nx Modeling in Codex?

Run `npx skills add DreamEnding/NX_MCP --skill nx-modeling -a codex`. Or copy the skill folder (skills/nx-modeling in DreamEnding/NX_MCP) into .agents/skills/nx-modeling in your project. Codex loads it when a task matches its description.

Can I use Nx Modeling 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 DreamEnding/NX_MCP --skill nx-modeling -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nx-modeling, .gemini/skills/nx-modeling, .github/skills/nx-modeling and .opencode/skills/nx-modeling in your project.

What does Nx Modeling need to run?

SKILL.md names no scripts, command-line tools or credentials: Nx Modeling is instructions for the agent only.

Does Nx Modeling 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 Nx Modeling 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. Review the folder before installing.

What licence does Nx Modeling use?

Nx Modeling 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 Nx Modeling use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Nx Modeling?

Skills that share tags, products or a category with Nx Modeling: 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 Microsoft Skill Creator (MicrosoftDocs/mcp, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nx Modeling?

DreamEnding (a GitHub user) maintains it in DreamEnding/NX_MCP, which has 112 GitHub stars. The repository was last updated on October 10, 2026.

Source: DreamEnding/NX_MCP on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Nx Modeling

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

NX Modeling

Before changing a part

Modeling workflow

Recovery and stopping conditions

Files

Compare with similar skills

Similar skills

MCP Server Builder

MCP Server Builder

MCP Integration for Plugins

Microsoft Skill Creator

Crush Configuration

Context Mode Output Sandbox

Related

Questions about Nx Modeling