init-physics-intern

Estruture um espaço de trabalho de pesquisa PhysicsIntern na pasta atual. Execute apenas quando o usuário o invocar explicitamente para configurar uma nova pesquisa de física/matemática…

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.

Mais skills de huggingface

sync-models
huggingface
Sincronize a configuração de modelos do chat-ui com o roteador HuggingFace — adicione descrições para novos modelos, sinalize os capazes de raciocínio, habilite artefatos para modelos com 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
Crie um endpoint SageMaker (em tempo real ou assíncrono) com auto scaling, alarmes do CloudWatch e marcação habilitados por padrão. Use esta habilidade sempre que for criar um…
hf-cloud-serving-image-selection
huggingface
Escolha o contêiner de serviço correto para uma implantação de modelo SageMaker e encontre o URI da imagem atual. Use esta habilidade sempre que for implantar um modelo em um…
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
Criar e gerenciar datasets no Hugging Face Hub. Suporta inicialização de repositórios, definição de configurações/prompts de sistema, atualização de linhas em streaming e consulta/transformação de datasets baseada em SQL. Projetado para funcionar junto ao servidor MCP do HF para fluxos de trabalho abrangentes com datasets.
Hugging Face Evaluation
huggingface
Adicionar e gerenciar resultados de avaliação em model cards do Hugging Face. Suporta extração de tabelas de avaliação do conteúdo do README, importação de pontuações da API Artificial Analysis e execução de avaliações personalizadas de modelos com vLLM/lighteval. Funciona com o formato de metadados model-index.