AutoSkill self / torch / import

SOP for PyTorch setup involving specific input splitting logic and standard library imports.

install

source · Clone the upstream repo

git clone https://github.com/ECNU-ICALK/AutoSkill

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/ECNU-ICALK/AutoSkill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/SkillBank/ConvSkill/chinese_gpt4_8_GLM4.7/self-torch-import" ~/.claude/skills/ecnu-icalk-autoskill-self-torch-import && rm -rf "$T"

manifest: SkillBank/ConvSkill/chinese_gpt4_8_GLM4.7/self-torch-import/SKILL.md

source content

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>):

将 4输入分开，构建新的相同模态结合的2输入，2分支
import math
import logging
from functools import partial
from collections import OrderedDict
from copy import deepcopy
import torch
import torch.nn as nn
import torch.nn.functional as F
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.