This skill should be used when the user asks to "evaluate a DSPy program", "test my DSPy module", "measure performance", "create evaluation metrics", "use answer_exact_match or SemanticF1",...
1598 results
(13.9ms)
page 5 / 80
problem-solver
0.00
Step-by-step problem solving with detailed explanations. Uses structured approach (Identify, Plan, Execute, Verify) for math, physics, chemistry, and CS problems. Can provide hints before...
create-project
0.00
Bootstraps production-ready AlgoKit projects for Algorand dApps and smart contracts. Use when initializing new Algorand smart contract projects, setting up development environments from scratch,...
This skill should be used when the user asks to "bootstrap few-shot examples", "generate demonstrations", "use BootstrapFewShot", "optimize with limited data", "create training demos...
speckit-02-clarify
0.00
Identify underspecified areas and ask targeted clarification questions
Creates FHIR R4 Questionnaires with official LOINC codes. NEVER suggest codes from memory - ALWAYS use provided scripts to search LOINC database.
codex-ask
0.00
Ask OpenAI Codex questions about code to understand implementations, architecture, patterns, and debugging. Use when the user asks how code works, where something is implemented, what patterns are...
skill-selector
0.00
Self-driven skill selection system that uses internal curiosity asking (self-questioning) to analyze user requests, infer context from available information, and automatically recommend the most...
rag-agent-builder
0.00
Build Retrieval-Augmented Generation (RAG) applications that combine LLM capabilities with external knowledge sources. Covers vector databases, embeddings, retrieval strategies, and response...
dspy-simba-optimizer
0.00
This skill should be used when the user asks to "optimize with SIMBA", "use Bayesian optimization", "optimize agents with custom feedback", mentions "SIMBA optimizer", "mini-batch optimization",...
This skill should be used when the user asks to "create a ReAct agent", "build an agent with tools", "implement tool-calling agent", "use dspy.ReAct", mentions "agent with tools", "reasoning and...
aeo-optimization
0.00
AI Engine Optimization - semantic triples, page templates, content clusters for AI citations
grpo-rl-training
0.00
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
grpo-rl-training
0.00
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
synalinks
0.00
Build neuro-symbolic LLM applications with Synalinks framework. Use when working with DataModel, Program, Generator, Module, training LLM pipelines, in-context learning, structured output, JSON...
gemini-ask
0.00
Ask Google Gemini questions about code to understand implementations, architecture, patterns, and debugging. Use when the user asks how code works, where something is implemented, what patterns...
rag-implementation
0.00
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or...
guidance
0.00
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained...
guidance
0.00
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained...
rag-implementation
0.00
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or...