PE

An expert assistant for adding and debugging artificial dendrites in PyTorch neural networks using the PerforatedAI library.

Install

mkdir -p .claude/skills/perforatedai && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19304" && unzip -o skill.zip -d .claude/skills/perforatedai && rm skill.zip

Installs to .claude/skills/perforatedai

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Expert in PerforatedAI library for adding artificial dendrites to PyTorch neural networks. Triggers: 'Perforate my model' (start interactive setup), 'debug my perforated model' (debug/optimize existing integration). Also use when: debugging dendrite training, configuring PAI settings, troubleshooting dendrite issues, working with PAINeuronModule or PAIDendriteModule. For analyzing completed training results, use the perforatedai-analyze skill.
447 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • Add artificial dendrites to PyTorch models
  • Configure dendrite training settings
  • Debug existing PerforatedAI integrations
  • Analyze model architecture for PAI compatibility

How it works

The skill analyzes existing PyTorch training scripts to inject dendrite modules and configuration calls, or debugs existing implementations.

Inputs & outputs

You give it
PyTorch training script path
You get back
Integrated dendrite code or debug report

When to use perforatedai

  • Add artificial dendrites to a PyTorch model
  • Debug existing PerforatedAI integration
  • Configure dendrite training settings

About perforatedai

Guides users through the setup of PerforatedAI in PyTorch models. It helps configure training modules, analyze implementation, and troubleshoot dendrite integration issues.

Expert in PerforatedAI library for adding artificial dendrites to PyTorch neural networks. Triggers: 'Perforate my model' (start interactive setup), 'debug my perforated model' (debug/optimize existing integration). Also use when: debugging dendrite training, configuring PAI settings, troubleshootin

When not to use it

  • When the user does not have a working baseline training script

Prerequisites

perforatedai pip packageperforatedbp pip package

Limitations

  • Requires manual installation of required pip packages
  • Does not run user training scripts directly

How it compares

It automates the integration of dendritic computation into standard PyTorch layers instead of manual layer modification.

Compared to similar skills

perforatedai side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
perforatedai (this skill)01moReviewAdvanced
langsmith-observability48moReviewIntermediate
mflux-debugging33moNo flagsAdvanced
debug-distributed16moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry