Skip to content
Back to skills

Self Nn Torch

ASecurity

General SOP for common requests related to self, nn, torch.

  • 666 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 2, 2026
ai-agents

Security analysis

A100/100

Scanned September 2, 2026

npx -y skills add majiayu000/claude-skill-registry --skill self-nn-torch --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Self Nn Torch?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Self Nn Torch
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majiayu000-self-nn-torch/badge)](https://www.skillsdirectory.com/skills/majiayu000-self-nn-torch)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
id: "589bbb5c-34e3-4f93-a5a9-9ba395734d97"
name: "self / nn / torch"
description: "General SOP for common requests related to self, nn, torch."
version: "0.1.0"
tags:
  - "self"
  - "nn"
  - "torch"
triggers:
  - "Use when the user asks for a process or checklist."
  - "Use when you want to reuse a previously mentioned method/SOP."
examples:
  - input: "Break this into best-practice, executable steps."
---

# self / nn / torch

General SOP for common requests related to self, nn, torch.

## Prompt

Follow this SOP (replace specifics with placeholders like <PROJECT>/<ENV>/<VERSION>):
1) Ex
2) reshape
3) 1×1Conv(Low-dimentional Projection
4) 并行的(1×1 Conv和1×1 DW-Conv
5) 元素级相加
6) 1×1Conv
7) GELU
8) 1×1Conv(High-dimensional Projection
9) Fx + 当前输出
10) Fx

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.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.