Runner for local development environments including .NET and Python services.
Install
mkdir -p .claude/skills/run-gwergilius && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13235" && unzip -o skill.zip -d .claude/skills/run-gwergilius && rm skill.zipInstalls to .claude/skills/run-gwergilius
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Run the Blazor WASM app, .NET CLI console app, or Python Jupyter notebookKey capabilities
- →Run a Blazor WASM app dev server
- →Execute a .NET CLI console app
- →Start a Python Jupyter notebook server
- →Run commands in the background
- →Report access details for running applications
- →Parse arguments for application type
How it works
This skill launches specified development environments (Blazor WASM app, .NET CLI console app, or Python Jupyter notebook) in the background using Bash commands. It then reports the relevant access details to the user.
Inputs & outputs
When to use run
- →Running a Blazor app
- →Starting a Jupyter notebook
- →Executing .NET console apps
About this skill
Argument
$ARGUMENTS — one of: blazor, cli, python
Commands
| Argument | Command | Type |
|---|---|---|
blazor | dotnet run --project dotnet/BlazorChat | dev server — run in background |
cli | dotnet run --project dotnet/AnthropicApiClient | interactive console — run in background |
python | python/\.venv/Scripts/jupyter notebook python/001-requests.ipynb | notebook server — run in background |
All commands are executed from the repository root:
D:\OneDrive - Personal\OneDrive\Source\Trainings\AI\Claude with Anthropic API
Your task
- Parse
$ARGUMENTS(trim whitespace, lowercase). - If the value is not one of
blazor,cli,python:- Tell the user the valid options and stop. Do not run anything.
- Run the matching command using the Bash tool with
run_in_background: true. - Report back:
- blazor — the dev server URL (typically
https://localhost:5001) - cli — note that the app is interactive; the user should watch the terminal output for the prompt
- python — Jupyter opens in the browser automatically; the notebook URL will appear in the background output
- blazor — the dev server URL (typically
When not to use it
- →When the user needs to run applications not listed (Blazor, .NET CLI, Jupyter)
- →When the user needs to interact with the application directly through the skill
- →When the user needs to stop a running application
Limitations
- →The skill only supports 'blazor', 'cli', or 'python' arguments
- →The skill runs commands from a specific repository root
- →The skill does not provide direct interaction with the running applications
How it compares
This skill provides a unified interface to launch different development environments in the background, simplifying the startup process compared to executing each command manually.
Compared to similar skills
run side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| run (this skill) | 0 | 4mo | Review | Beginner |
| machine-learning-ops-ml-pipeline | 4 | 4mo | No flags | Advanced |
| uv | 3 | 5mo | Review | Beginner |
| vastai-core-workflow-b | 1 | 26d | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
machine-learning-ops-ml-pipeline
sickn33
Design and implement a complete ML pipeline for: $ARGUMENTS
uv
mitsuhiko
Use `uv` instead of pip/python/venv. Run scripts with `uv run script.py`, add deps with `uv add`, use inline script metadata for standalone scripts.
vastai-core-workflow-b
jeremylongshore
Execute Vast.ai secondary workflow: Core Workflow B. Use when implementing secondary use case, or complementing primary workflow. Trigger with phrases like "vastai secondary workflow", "secondary task with vastai".
mflux-dev-env
filipstrand
Set up and work in the mflux dev environment (arm64 expectation, uv, Makefile targets, lint/format/test).
hugging-face-jobs
patchy631
This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks. Should be invoked for tasks involving cloud compute, GPU workloads, or when users mention running jobs on Hugging Face infrastructure without local setup.
mlops-initialization
fmind
Guide to initialize a new MLOps project with standard tools (uv, git, VS Code) and best practices.