ai-stopping-hallucinations
No SKILL.md available for this skill.
View on GitHubMore from lebsral/dspy-programming-not-prompting-lms-skills
dspy-bootstrap-finetune
Use when you need maximum quality from a smaller/cheaper model — generates training data from a teacher model and fine-tunes a student model weights. Common scenarios - distilling GPT-4 quality into a cheaper model, generating training data from a strong teacher to fine-tune a weak student, reducing inference costs by replacing an expensive model with a fine-tuned small one, or building a production model that is fast and cheap. Related - ai-fine-tuning, ai-cutting-costs, dspy-better-together. Also used for dspy.BootstrapFinetune, model distillation with DSPy, teacher-student training, fine-tune small model from GPT-4 outputs, reduce API costs with fine-tuning, generate training data then fine-tune, cheap model same quality, distill large model into small model, fine-tune Llama from GPT-4, production model training, move from API to self-hosted model.
5dspy-mlflow
Use MLflow for DSPy tracing, experiment tracking, and model registry. Use when you want to set up MLflow, mlflow.dspy.autolog, MLflow Tracing, MLflow experiment tracking, MLflow model registry, or full ML lifecycle management. Also: 'mlflow setup', 'pip install mlflow', 'mlflow.set_experiment', 'mlflow UI', 'mlflow model versioning', 'mlflow OpenTelemetry', 'mlflow vs wandb', 'mlflow tracing DSPy', 'register DSPy model'.
4dspy-signatures
Use when you need to define the input/output contract for an LM call — choosing between inline and class-based signatures, adding type constraints, or using Pydantic models for structured outputs.
4dspy-miprov2
Use when you want the highest-quality prompt optimization DSPy offers — jointly optimizes instructions and few-shot demos, with auto='light'/'medium'/'heavy' presets. Common scenarios: you want the best possible accuracy from prompt optimization, jointly tuning instructions and few-shot demonstrations, using auto presets for different compute budgets, or when COPRO or BootstrapFewShot alone aren't reaching your accuracy target. Related: ai-improving-accuracy, dspy-copro, dspy-bootstrap-few-shot. Also: \"dspy.MIPROv2\", \"best DSPy optimizer\", \"highest quality optimization\", \"auto='light' medium heavy\", \"joint instruction and demo optimization\", \"most powerful prompt optimizer\", \"MIPROv2 vs COPRO vs BootstrapFewShot\", \"which optimizer should I use\", \"state of the art prompt optimization\", \"when to use MIPROv2\", \"optimize both instructions and examples\", \"heavy optimization for production\", \"best optimizer for accuracy\".
4ai-rewriting-text
Rewrite text to match a different tone, reading level, or audience using AI. Use when rewriting content in a different tone, simplifying legal language, adapting text for a different audience, converting technical docs to plain English, making formal text casual, adjusting reading level, matching brand voice in existing content, paraphrasing for clarity, converting jargon-heavy text to simple language, tone transformation, style transfer for text, rewriting marketing copy, making content more accessible, executive summary from technical report.
2