Torchcode Pytorch Interview Practice
reason-machines/trending-skills/skills/torchcode-pytorch-interview-practiceby reason-machines2384a003145aNo license83 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 3 months ago
LeetCode-style PyTorch interview practice environment with auto-grading for implementing softmax, attention, GPT-2 and more from scratch.
Add to a SourceWeft workspace
- Open the skill in your dashboard and add it to a workspace.
- Enable it for the chats that should use it.
This skill is instructions only: it ships no scripts to execute.
Add to SourceWeftYou will be asked to sign in first, then taken straight to this skill.
Ask your agent to install it
Paste this prompt into Claude Code, Codex, Cursor or another agent that can run commands — or into SourceWeft chat. The agent reads this skill's install guide, shows you its source, license and scripts, and installs it with the SourceWeft CLI once you agree.
Read https://sourceweft.com/skills/gh-reason-machines-trending-skills-torchcode-pytorch-interview-practice/install.md and install the skill it describes. Before installing, show me its source, license and whether it ships scripts, and wait for my OK. Ask me before changing anything else on my machine.Install it yourself from a terminal
For Claude Code, Codex, Cursor and other local agents. The SourceWeft CLI fetches the skill from its source repository at the commit scanned here, and verifies every file against the hashes recorded when the skill was scanned. If anything differs, nothing is written.
npx @sourceweft/cli skills install @reason-machines/torchcode-pytorch-interview-practiceAdd --agent claude-code, codex, cursor or universal to choose which agent gets it (Claude Code by default).
Upstream installer — not verified by SourceWeft
The open-source skills installer fetches the same pinned commit, but does not check the files against the hashes SourceWeft recorded.
npx skills add https://github.com/reason-machines/trending-skills/tree/2384a003145a59276aa204b10c47262aab65a3c9/skills/torchcode-pytorch-interview-practiceSource and attribution
Source:reason-machines/trending-skillsinskills/torchcode-pytorch-interview-practiceat commit2384a00
License: No license
Content belongs to its original authors. SourceWeft indexes it from a public repository.
More from reason-machines/trending-skills
Yourvpndead Vpn Detection
reason-machines
Documents an Android app that detects VPN clients and probes localhost SOCKS5 and Clash API ports for leaks.
X Mentor Skill Nuwa
reason-machines
Guides X (Twitter) content strategy: tweet and thread writing, hook review, growth tactics and account diagnostics.
Wildworld Dataset
reason-machines
Describes the WildWorld action-conditioned ARPG world-modeling dataset and shows anticipated loading, filtering and benchmark code.
Understand Anything Knowledge Graph
reason-machines
Builds an interactive knowledge graph of a codebase and lets users explore, search and question it visually.
Webphysics Avbd Engine
reason-machines
Guides integration of the experimental WebGPU AVBD rigid-body and soft-body physics engine into browser projects.
Ui Ux Pro Max Skill
reason-machines
Generates UI/UX design systems — page patterns, styles, color palettes, typography and checklists — from a product description.
More in Learning & Education
Jupyter Notebook
openai
Scaffolds and edits Jupyter notebooks for experiments or tutorials using bundled templates and a helper script.
Eli5
anthropics
Explains a topic in very simple terms using an HTML artifact with large pictures and few words.
Wiki Onboarding
microsoft
Generates four audience-tailored codebase onboarding guides: contributor, staff engineer, executive, and product manager.
Azuresql Db Faq
microsoft
Answers questions about what the Azure SQL Database container (Private Preview) supports and why it differs from the cloud service.
Teach
mattpocock
Teaches a user a topic over multiple sessions, producing HTML lessons, reference sheets and learning records in a workspace.
Scaffold Exercises
mattpocock
Scaffolds course exercise directory structures with problem, solution, and explainer folders plus readme stubs that pass linting.