Compile declarative language model calls into self-improving pipelines.
npx skills add https://github.com/iani-kuli/harness_bro --skill dspy-iani-kuli
Please help me install this Agent Skill. Skill: dspy Source: https://github.com/iani-kuli/harness_bro/tree/main/.claude/skills/ported/dspy Command: npx skills add https://github.com/iani-kuli/harness_bro --skill dspy-iani-kuli
This Skill solves the fragility and manual effort of traditional prompt engineering by allowing you to program language model workflows declaratively and optimize them automatically using data-driven methods.
Use the dspy skill to optimize a chain of thought module for question answering using the provided training dataset.
High-intent search queries and answers about installing and using this skill.
Declarative programming automates prompt engineering by compiling language model calls into self-improving pipelines. You define tasks as input and output signatures, then use built-in teleprompters to optimize few-shot example selection based on training data.
Declarative programming for AI pipelines defines language model tasks as structural signatures rather than brittle prompt strings. This approach allows you to build modular, maintainable AI systems like RAG and agents that are portable across different language models.
You optimize few-shot examples for RAG applications by using built-in teleprompters to compile your modules. This data-driven method automatically selects examples to improve performance based on your specific training datasets.
Yes, you need training datasets to execute systematic performance optimization. The built-in teleprompters use your training data to compile declarative language model modules and automatically improve pipeline performance through data-driven methods.
Yes, declarative programming applies to building complex reasoning agents and modular AI systems. Defining tasks as structural signatures allows you to construct maintainable reasoning workflows that are portable across different language models.
projectedanxOptimize language model prompts and pipelines through declarative programming and data-driven compilation.
InverterNetworkProgram language models declaratively and optimize prompts automatically.
ovachieverDeclaratively program language models and automatically optimize prompts with DSPy.
liuerfireDesigns, optimizes and evaluates prompts for LLMs using techniques like chain-of-thought and few-shot learning.
