Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
This skill collection guides DSPy 3.2.x development from specification through optimization to deployment. It covers writing typed signatures and modules, building rich-feedback evaluation metrics, running GEPA optimization, handling contexts too large for a single prompt with RLM, and orchestrating the full seven-step workflow. It helps engineers who build, evaluate, and ship structured LLM programs.
WHO IT'S FOR
DSPy practitioners
building and shipping production LLM pipelines
AI evaluation engineers
designing rich-feedback metrics and evaluation harnesses
ML optimization engineers
optimizing DSPy programs with reflective evolutionary algorithms
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.