macromate-exact-fix
CommunityFixes nutrition data and model loading.
System Documentation
What problem does it solve?
MacroMate's nutrition predictor sometimes returns 0 kcal or misleading values because nutrition data is nested under nutrition_data and the model loader uses the wrong architecture, causing dependency on CLIP fallback. This skill provides targeted patches to correct the nutrition extractor, switch the model loader to EfficientNetV2-M, adjust preprocessing, and enable startup verification for reliable nutrition data.
Core Features & Use Cases
- Nutrition data corrected: read from nutrition_data and normalize calories, protein, carbohydrates, fat, fiber, sugar, vitamins, calcium, and iron.
- Model loading accuracy: load EfficientNetV2-M with 351 classes and 480x480 input, ensuring predictions are not delegated to CLIP.
- Startup validation: verify label_nutrition_mapping.json entries at startup and log known foods.
Quick Start
Apply the exact fixes to the MacroMate nutrition predictor to ensure correct nutrition extraction and proper EfficientNetV2-M model loading.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: macromate-exact-fix Download link: https://github.com/renish7606/MacroMate/archive/main.zip#macromate-exact-fix Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.