init-physics-intern

Crea un espacio de trabajo de investigación PhysicsIntern en la carpeta actual. Ejecútalo solo cuando el usuario lo invoque explícitamente para configurar una nueva investigación de física/matemáticas…

npx skills add https://github.com/huggingface/physics-intern-codex-plugin --skill init-physics-intern

This is a purely mechanical bootstrap. Do exactly the following and nothing more — do not read, copy, render, or create any files yourself, and do not narrate steps:

  1. First, print this line verbatim to the user:

    ⏳ Initializing the PhysicsIntern workspace. This needs one permission approval — the script writes .codex/ and runs git init, which the sandbox keeps read-only by default. Please approve it when prompted.

  2. Then run the bundled init script, with no arguments, using the shell tool — a single command:

    bash "${PLUGIN_ROOT}/scripts/plugin-init.sh"
    

    The script renders the workspace, scaffolds the directories, and makes the first git commit — it does the entire job in one command. It writes to .codex/ and runs git init/git commit, which the workspace-write sandbox blocks, so Codex will ask for approval — that is expected; approve it. Do not fall back to doing the work by hand if it is denied — just re-run the same script with approval.

  3. Read the script's final RESULT: line, then:

    • If it contains RESULT: initialized, print the following message verbatim and then stop — add nothing else, no file lists, no extra suggestions:

      ✅ PhysicsIntern workspace initialized. Two steps to begin:

      1. Edit problem.md — fill in the problem setup and main question.
      2. Exit and restart Codex in this folder (accept the project-trust prompt on first launch), then run $survey.
    • If it contains RESULT: already-initialized, tell the user this folder already contains a PhysicsIntern workspace and was left untouched, and stop.

    • If there is no RESULT: line, show the script's output to the user and stop.

Más skills de huggingface

sync-models
huggingface
Sincroniza la configuración de modelos de chat-ui con el router de HuggingFace: añade descripciones para modelos nuevos, marca los que tienen capacidad de razonamiento, habilita artefactos para modelos con 32B+…
custom-blocks
huggingface
Use when the user has written (or wants to write) a `ModularPipelineBlocks` subclass in a local Python file and needs to package it into a Hub-uploadable…
self-review
huggingface
Use before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the `@claude` CI (checks the diff against…
hf-cloud-sagemaker-production-defaults
huggingface
Crear un endpoint de SageMaker (en tiempo real o asíncrono) con autoescalado, alarmas de CloudWatch y etiquetado habilitado por defecto. Usa esta habilidad siempre que estés a punto de crear un…
hf-cloud-serving-image-selection
huggingface
Selecciona el contenedor de servicio adecuado para una implementación de modelo SageMaker y encuentra su URI de imagen actual. Usa esta habilidad cada vez que estés a punto de implementar un modelo en un…
Hugging Face Cli
huggingface
Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.
Hugging Face Datasets
huggingface
Crear y gestionar conjuntos de datos en Hugging Face Hub. Permite inicializar repositorios, definir configuraciones/indicaciones del sistema, transmitir actualizaciones de filas y realizar consultas/transformaciones de conjuntos de datos basadas en SQL. Diseñado para funcionar junto con el servidor HF MCP para flujos de trabajo integrales de conjuntos de datos.
Hugging Face Evaluation
huggingface
Agregar y gestionar resultados de evaluación en tarjetas de modelo de Hugging Face. Permite extraer tablas de evaluación del contenido README, importar puntuaciones desde la API de Artificial Analysis y ejecutar evaluaciones de modelo personalizadas con vLLM/lighteval. Funciona con el formato de metadatos model-index.