DSPy vs SkillOpt
Program — don't prompt — your language models. Compile declarative pipelines into optimized prompts. — versus — Microsoft's text-space optimizer that trains a frozen agent's skill document like weights — rollouts, bounded edits, validation-gated updates — and ships a compact best_skill.md.
Both optimize the text a frozen model runs on against a metric; DSPy compiles prompts for declarative pipelines, SkillOpt trains one deployable skill document for an agent harness.
| DSPy | SkillOpt | |
|---|---|---|
| Stars | 39k | 18k |
| Forks | 3.4k | 1.7k |
| Language | Python | Python |
| License | MIT | MIT |
| Last activity | 3 days ago | 5 days ago |
| Topics | orchestration, rag | skills, training |
| Curated connections | 4 | 4 |
DSPy — the curator's take
Program — don't prompt — your language models. Compile declarative pipelines into optimized prompts.
SkillOpt — the curator's take
Use it when you have a task with a scorer and want a skill that measurably improves on it — an edit lands only if the held-out score rises, and deployment adds zero model calls. Not a passive learner: you need data, a benchmark and an optimizer-model budget; the nightly SkillOpt-Sleep mode is the bridge to everyday Claude Code/Codex sessions. No metric? An in-use skill learner fits better.