Skill Claude CodeCodex
Multi-Modal Interpretability methods explain vision and vision-language models by linking each internal unit (a convolutional neuron, attention head, residual-stream channel, or SAE feature) to a natural-language concept drawn from an external concept set $\mathcal{C}$. The unifying construction is a similarity score…
Skill Claude CodeCodex
Use this skill when you need to automatically describe or interpret the functionality of individual neurons in deep neural networks (DNNs) using CLIP-based semantic analysis, perform mechanistic interpretability research on vision models, dissect convolutional or transformer-based image classifiers, identify what…
Skill Claude CodeCodex
Use this skill when working with Concept Relevance Propagation (CRP) and Relevance Maximization for explainable AI in PyTorch models, including generating concept-conditional heatmaps, feature visualizations, attribution graphs, and identifying which latent concepts neural networks use for predictions.
Skill Claude CodeCodex
Neural Feature Learning methods open the black box of how a trained neural network discovers useful representations from data, by deriving the directions along which each layer's effective input geometry is reshaped during training. The unifying object is the Neural Feature Matrix (NFM) — for a fully-connected layer…
Skill Claude CodeCodex
Run SkillAdaptor to evolve agent skills from task failures. Use when improving SKILL.md files from trajectories or after benchmark runs.
Plugin Claude Code
Plugin marketplace listing 1 plugin: skillfabric.
Plugin Claude Code
Build a SkillFabric workspace and route tasks to relevant native skills.
Command
Build or incrementally refresh the SkillFabric workspace.
Command
Check SkillFabric installation, configuration, and workspace readiness.
Command
Route a task to the most relevant native Skills.