OpenAgentSkill Registry Manifest
Skill: Convolutional KANs
Slug: antoniotepsich-convolutional-kans
Category: robotics-iot
Description: This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learnable non linear activations in each pixel.

Agent fit:
- Decision: 58/100 Prototype first
- Primary fit: Coding agents
- Role: Fallback candidate

Supply profile:
- Track: Coding and developer agents
- Scenario: Coding agents
- Applicable agents: Claude Code, CLI, Codex, Cursor, Jupyter Notebook
- Maintenance: 1y since push
- Risk: Needs review

Trust:
- Trust score: 80/100 Strong shortlist
- Audit: 70/100 Needs review

Attribution:
- Status: Community indexed
- Source: GitHub star discovery
- Creator: AntonioTepsich
- Claim URL: https://www.openagentskill.com/skills/antoniotepsich-convolutional-kans#claim-this-skill

Install:
npx skills add AntonioTepsich/Convolutional-KANs

URLs:
- Web: https://www.openagentskill.com/skills/antoniotepsich-convolutional-kans
- API: https://www.openagentskill.com/api/agent/skills/antoniotepsich-convolutional-kans
- Install API: https://www.openagentskill.com/api/skills/antoniotepsich-convolutional-kans/install
- Repository: https://github.com/AntonioTepsich/Convolutional-KANs