Guia os usuários na criação de Skills para Agentes no Claude Code.
Esta skill (pytorch/skill-writer) foi projetada para orientar desenvolvedores e usuários na criação de Skills para Agentes no Claude Code. Ela é especialmente útil quando o usuário deseja criar, escrever, autorar ou projetar uma nova Skill, ou precisa de ajuda com arquivos SKILL.md, frontmatter ou a estrutura geral de uma Skill. A skill fornece assistência passo a passo, desde a definição do nome e descrição até a formatação correta do frontmatter YAML e a organização do conteúdo markdown. Ela suporta o ecossistema Claude Code e pode ser usada em conjunto com outras ferramentas de desenvolvimento de agentes. O funcionamento baseia-se na análise da intenção do usuário e na geração de um esqueleto de SKILL.md com as seções obrigatórias e recomendações de boas práticas.
npx skills add https://github.com/pytorch/pytorch/tree/main/skills/skill-writerGuia os usuários na criação de Skills para Agentes no Claude Code. Use quando o usuário desejar criar, escrever, autorar ou projetar uma nova Skill, ou precisar de ajuda com arquivos SKILL.md, frontmatter ou estrutura de Skills.
This repo contains 8 individual skills — each has its own dedicated page.
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
Debug AOTInductor (AOTI) errors and crashes. Use when encountering AOTI segfaults, device mismatch errors, constant loading failures, or runtime errors from aot_compile, aot_load, aoti_compile_and_package, or aoti_load_package.
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.
Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstrings in PyTorch code.
Write Metal/MPS kernels for PyTorch operators. Use when adding MPS device support to operators, implementing Metal shaders, or porting CUDA kernels to Apple Silicon. Covers native_functions.yaml dispatch, host-side operators, and Metal kernel implementation.
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
Migrate a file to use stricter Pyrefly type checking with annotations required for all functions, classes, and attributes.
Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.
ElevenLabs text-to-speech with mac-style say UX.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
Capture and automate macOS UI with the Peekaboo CLI.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".