Loading...
Loading...
Found 19 Skills
DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and compilers
Switch AI providers or models without breaking things. Use when you want to switch from OpenAI to Anthropic, try a cheaper model, stop depending on one vendor, compare models side-by-side, a model update broke your outputs, you need vendor diversification, or you want to migrate to a local model. Covers DSPy model portability — provider config, re-optimization, model comparison, and multi-model pipelines.
This skill should be used when the user asks to "build a RAG pipeline", "create retrieval augmented generation", "use ColBERTv2 in DSPy", "set up a retriever in DSPy", mentions "RAG with DSPy", "context retrieval", "multi-hop RAG", or needs to build a DSPy system that retrieves external knowledge to answer questions with grounded, factual responses.
Measure and improve how well your AI works. Use when AI gives wrong answers, accuracy is bad, responses are unreliable, you need to test AI quality, evaluate your AI, write metrics, benchmark performance, optimize prompts, improve results, or systematically make your AI better. Covers DSPy evaluation, metrics, and optimization.
Generate synthetic training data when you don't have enough real examples. Use when you're starting from scratch with no data, need a proof of concept fast, have too few examples for optimization, can't use real customer data for privacy or compliance, need to fill gaps in edge cases, have unbalanced categories, added new categories, or changed your schema. Covers DSPy synthetic data generation, quality filtering, and bootstrapping from zero.
Fine-tune models on your data to maximize quality and cut costs. Use when prompt optimization hit a ceiling, you need domain specialization, you want cheaper models to match expensive ones, you heard "fine-tuning will make us AI-native", you have 500+ training examples, or you need to train on proprietary data. Covers DSPy BootstrapFinetune, BetterTogether, model distillation, and when to fine-tune vs optimize prompts.
Find every way users can break your AI before they do. Use when you need to red-team your AI, test for jailbreaks, find prompt injection vulnerabilities, run adversarial testing, do a safety audit before launch, prove your AI is safe for compliance, stress-test guardrails, or verify your AI holds up against adversarial users. Covers automated attack generation, iterative red-teaming with DSPy, and MIPROv2-optimized adversarial testing.
Break a failing complex AI task into reliable subtasks. Use when your AI works on simple inputs but fails on complex ones, extraction misses items in long documents, accuracy degrades as input grows, AI conflates multiple things at once, results are inconsistent across input types, you need to chunk long text for processing, or you want to split one unreliable AI step into multiple reliable ones.
Score, grade, or evaluate things using AI against a rubric. Use when grading essays, scoring code reviews, rating candidate responses, auditing support quality, evaluating compliance, building a quality rubric, running QA checks against criteria, assessing performance, rating content quality, or any task where you need numeric scores with justifications — not just categories.
Verify and validate AI output before it reaches users. Use when you need guardrails, output validation, safety checks, content filtering, fact-checking AI responses, catching hallucinations, preventing bad outputs, quality gates, or ensuring AI responses meet your standards before shipping them. Covers DSPy assertions, verification patterns, and generate-then-filter pipelines.
Stop your AI from making things up. Use when your AI hallucinates, fabricates facts, isn't grounded in real data, doesn't cite sources, makes unsupported claims, or you need to verify AI responses against source material. Covers citation enforcement, faithfulness verification, grounding via retrieval, and confidence thresholds.
Scaffold a new AI feature powered by DSPy. Use when adding AI to your app, starting a new AI project, building an AI-powered feature, setting up a DSPy program from scratch, or bootstrapping an LLM-powered backend.