This skill should be used when the user asks to "optimize a DSPy program", "use MIPROv2", "tune instructions and demos", "get best DSPy performance", "run Bayesian optimization", mentions...
4220 results
(29.8ms)
page 2 / 211
prompt-engineering
0.00
Designs and optimizes prompts for large language models including system prompts, agent signals, and few-shot examples. Covers instruction design, prompt security, chain-of-thought reasoning, and...
model_finetuning
0.00
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...
model_finetuning
0.00
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF,...
postgres-tuning
0.00
Senior Database Optimizer for PostgreSQL 17/18+, specialized in Asynchronous I/O (AIO), Query Plan Forensic, and Vector Index optimization.
llava
0.00
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image...
llava
0.00
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image...
|
Optimize hyperparameters using grid search, random search, Bayesian optimization, and automated ML frameworks like Optuna and Hyperopt
awq-quantization
0.00
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster...
prompt-enhancer
0.00
Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure, add constraints, optimize for specific models, backward-compatible...
prompt-engineer
0.00
Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when "prompt engineering, system...
copilot-docs
0.00
Configure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot behavior, or creating repository-specific AI guidance. Triggers on...
copilot-docs
0.00
Configure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot behavior, or creating repository-specific AI guidance. Triggers on...
claude-md-architect
0.00
CLAUDE.md file generation and optimization for Claude Code projects. Capabilities: initialize project instructions, analyze codebase context, optimize existing CLAUDE.md, apply Anthropic best...
optimize-prompt
0.00
Prompt optimization consultant for AI system prompts and custom instructions. Supports Claude API, OpenAI API, Gemini API, CLAUDE.md, ChatGPT, and n8n. Use when user wants to improve, review, or...
This skill should be used when the user asks to "fine-tune a DSPy model", "distill a program into weights", "use BootstrapFinetune", "create a student model", "reduce inference costs with...
model-evaluation
0.00
Evaluates machine learning models for performance, fairness, and reliability using appropriate metrics and validation techniques. Covers training debugging, hyperparameter tuning, and production...
skill-creator
0.00
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...
Step-by-step instructions for designing table schemas and setting up TimescaleDB with hypertables, indexes, compression, retention policies, and continuous aggregates. Instructions for selecting:...