interrupt
73ScientiaCapital/unsloth-mcp-server
Command Claude Code
Interrupt Protocol — snapshot current work and pivot to urgent task.
2 5mo ago A 11 tokens
original Apache-2.0
pr
74ScientiaCapital/unsloth-mcp-server
Command Claude Code
Clean PR workflow — branch, build, simplify, review, submit.
2 5mo ago A 14 tokens
original Apache-2.0
review
75ScientiaCapital/unsloth-mcp-server
Command Claude Code
Quick code review of recent changes.
2 5mo ago A 6 tokens
original Apache-2.0
ship
76ScientiaCapital/unsloth-mcp-server
Command Claude Code
Stage, commit, push. One command.
2 5mo ago A 9 tokens
original Apache-2.0
simplify
77ScientiaCapital/unsloth-mcp-server
Command Claude Code
Simplify recent code — reduce complexity, improve readability.
2 5mo ago A 11 tokens
original Apache-2.0
status
78ScientiaCapital/unsloth-mcp-server
Command Claude Code
Project health snapshot — git, deps, tests, CLAUDE.md.
2 5mo ago A 14 tokens
original Apache-2.0
ScientiaCapital/unsloth-mcp-server
Skill Claude CodeCodex
Self-learning workflow system that tracks what works best for your use cases. Records experiment results, suggests optimizations, creates custom templates, and builds a personal knowledge base. Use to learn from experience and optimize your LLM workflows over time.
2 5mo ago A 51 tokens
original Apache-2.0
ScientiaCapital/unsloth-mcp-server
Skill Claude CodeCodex
Create, clean, and optimize datasets for LLM fine-tuning. Covers formats (Alpaca, ShareGPT, ChatML), synthetic data generation, quality assessment, and augmentation. Use when preparing data for training.
2 5mo ago A 48 tokens
original Apache-2.0
ScientiaCapital/unsloth-mcp-server
Skill Claude CodeCodex
Export and deploy fine-tuned models to production. Covers GGUF/Ollama, vLLM, HuggingFace Hub, Docker, quantization, and platform selection. Use after fine-tuning when you need to deploy models efficiently.
2 5mo ago B 52 tokens
original Apache-2.0
superbpe
82ScientiaCapital/unsloth-mcp-server
Skill Claude CodeCodex
Train and use SuperBPE tokenizers for 20-33% token reduction across any project. Covers training, optimization, validation, and integration with any LLM framework. Use when you need efficient tokenization, want to reduce API costs, or maximize context windows.
2 5mo ago A 58 tokens
original Apache-2.0
ScientiaCapital/unsloth-mcp-server
Skill Claude CodeCodex
Advanced techniques for optimizing LLM fine-tuning. Covers learning rates, LoRA configuration, batch sizes, gradient strategies, hyperparameter tuning, and monitoring. Use when fine-tuning models for best performance.
2 5mo ago A 45 tokens
original Apache-2.0
ScientiaCapital/unsloth-mcp-server
Skill Claude CodeCodex
Fine-tune LLMs 2x faster with 80% less memory using Unsloth. Use when the user wants to fine-tune models like Llama, Mistral, Phi, or Gemma. Handles model loading, LoRA configuration, training, and model export.
2 5mo ago A 66 tokens
original Apache-2.0
ScientiaCapital/unsloth-mcp-server
Skill Claude CodeCodex
Work with the Unsloth MCP Server codebase. Use when maintaining, extending, or debugging this specific MCP server implementation. Provides architecture knowledge, code patterns, and development workflows.
2 5mo ago C 43 tokens
original Apache-2.0
ScientiaCapital/unsloth-mcp-server
Skill Claude CodeCodex
Analyze, compare, and work with tokenizers using Unsloth tools. Compare different tokenizers, analyze token efficiency, and integrate with Unsloth models. For SuperBPE training, see the 'superbpe' skill.
2 5mo ago A 53 tokens
original Apache-2.0
ScientiaCapital/unsloth-mcp-server
Instructions file
Instructions for ScientiaCapital/unsloth-mcp-server, covering unsloth mcp server, critical rules, what this project is, current status and key files.
2 5mo ago A 378 tokens
original Apache-2.0