Program language models declaratively with automated prompt optimization in DSPy.
npx skills add https://github.com/gztcode/my-skills --skill dspy-gztcode
Please help me install this Agent Skill. Skill: dspy Source: https://github.com/gztcode/my-skills/tree/main/dspy Command: npx skills add https://github.com/gztcode/my-skills --skill dspy-gztcode
This Skill streamlines the development of AI systems by providing systematic approaches to programming and optimizing LMs declaratively.
Use the dspy skill to create a question answering module for the provided text, with the expected output being a summary of the text.
import dspy
lm = dspy.Claude(model="claude-sonnet-4-5-20250929")
dspy.settings.configure(lm=lm)
class QA(dspy.Signature):
question = dspy.InputField()
answer = dspy.OutputField(desc="summary of the provided text")
qa = dspy.Predict(QA)
response = qa(question="Summarize the text.")
print(response.answer)
High-intent search queries and answers about installing and using this skill.
Automate prompt optimization by programming LLMs declaratively, which shifts focus from manual prompting to data-driven methods that systematically improve model performance.
Declarative programming for modular AI builds maintainable and portable pipelines by defining what the model should achieve rather than writing manual prompt instructions.
Yes, the framework is compatible with Anthropic Claude, OpenAI, and local models, allowing you to configure your preferred LM for modular AI pipelines and agents.
Build a RAG system by defining declarative LM modules for information retrieval and answer generation, leveraging automated optimization to refine model outputs.
Yes, local models are supported alongside OpenAI and Anthropic Claude, enabling automated prompt optimization and modular AI programming across different environments.
Shifting to declarative LM programming eliminates manual prompt tuning by using data-driven optimization, resulting in more maintainable and systematically improved AI pipelines.
anilcan-karaAutomate declarative LM programming and self-improvement workflows with DSPy.
ContextJet-aiEvaluate RAG pipelines using context precision, recall, faithfulness, and answer relevance.
SriRamkunamsettyAutomate AI pipeline construction with declarative LM programming and prompt optimization.
nimeshgurungDesign and optimize LLM prompts with RAG and agent workflows.