implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
hypogenic
Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against observational data, or conducting systematic hypothesis exploration for research discovery in domains like deception detection, AI content detection, mental health analysis, or other empirical research tasks.
knowledge-distillation
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
training-llms-megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
prompt-enhancer
Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure, add constraints, optimize for specific models, backward-compatible rewrites. Actions: improve, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, prompt optimization, token efficiency, LLM prompt, AI prompt, clarity, structure, system prompt, user prompt, few-shot, chain-of-thought, instruction tuning, prompt compression, token reduction, prompt rewrite, semantic preservation. Use when: improving unclear prompts, reducing token consumption, optimizing LLM outputs, restructuring verbose requests, creating system prompts, enhancing prompt clarity.
data-engineering
Data engineering, machine learning, AI, and MLOps. From data pipelines to production ML systems and LLM applications.
llm-doc-gen
LLM-powered documentation generation for narrative architecture docs, tutorials, and developer guides. Uses AI consultation to create contextual, human-readable documentation from code analysis and spec data.
llm-integration
Expert skill for integrating local Large Language Models using llama.cpp and Ollama. Covers secure model loading, inference optimization, prompt handling, and protection against LLM-specific vulnerabilities including prompt injection, model theft, and denial of service attacks.
small-council
Consult the Small Council - a multi-LLM deliberation system that gathers independent answers from multiple frontier AI models, has them anonymously rank each other's responses, then synthesizes a consensus answer. Use for complex coding questions, architectural decisions, code reviews, debugging challenges, or when you want multiple expert perspectives. Trigger when user mentions "small council", "ask the council", "consult the council", or wants multi-model deliberation on code.
vllm-deployment
|
distributed-claude-receiver
You are a remote Claude instance running on a VPS. Receive messages via chat.sh wrapper, maintain persistent context, use Z.ai GLM backend via Doppler.
prompt-engineering
Designs and optimizes prompts for large language models to achieve better, more consistent outputs. Trigger keywords: prompt, LLM, GPT, Claude, prompt engineering, AI prompts, few-shot, chain of thought.
bloom_integrity_verification
>
subcodex
|
funsloth-train
Generate Unsloth training notebooks and scripts. Use when the user wants to create a training notebook, configure fine-tuning parameters, or set up SFT/DPO/GRPO training.
llm-cli
Process textual and multimedia files with various LLM providers using the llm CLI. Supports both non-interactive and interactive modes with model selection, config persistence, and file input handling.
Convex Agents Usage Tracking
Tracks LLM token consumption and usage metrics for billing, monitoring, and optimization. Use this to log token usage, calculate costs, generate invoices, and understand which agents or users consume the most resources.
Convex Agents Debugging
Troubleshoots agent behavior, logs LLM interactions, and inspects database state. Use this when responses are unexpected, to understand context the LLM receives, or to diagnose data issues.
Page 1 of 2 · 29 results