self / torch / import
SOP for PyTorch setup involving specific input splitting logic and standard library imports.
npx skills add ECNU-ICALK/AutoSkill --skill self-torch-import --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# self / torch / import SOP for PyTorch setup involving specific input splitting logic and standard library imports. ## Prompt Follow this SOP (replace specifics with placeholders like <PROJECT>/<ENV>/<VERSION>): 1) 将 4输入分开，构建新的相同模态结合的2输入，2分支 2) import math 3) import logging 4) from functools import partial 5) from collections import OrderedDict 6) from copy import deepcopy 7) import torch 8) import torch.nn as nn 9) import torch.nn.functional as F 10) from timm.models.layers import to_2tuple For each step, include: action, checks, and failure rollback/fallback plan. Output format: for each step number, provide status/result and what to do next. ## Triggers - Use when the user asks for a process or checklist. - Use when you want to reuse a previously mentioned method/SOP. ## Examples ### Example 1 Input: Break this into best-practice, executable steps.
- Prompt
- Triggers
- Examples
- Example 1
What does the self / torch / import skill do?
SOP for PyTorch setup involving specific input splitting logic and standard library imports.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill self-torch-import --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.