Individual skill
dspy-programming
Program language models instead of prompting them — DSPy signatures, modules, and optimizers that tune prompts automatically.
skills/dspy-programming/SKILL.md
Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 8, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 56
- Repository last updated
- Oct 10, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-agents Repository topic
- ai-agents-automation Repository topic
- ai-skills Repository topic
- awesome Repository topic
- awesome-list Repository topic
- chatgpt Repository topic
- claude-skills Repository topic
- meta-ai Repository topic
- muse-ai Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 6,496 bytes
Read excerpt
## Overview
DSPy replaces hand-written prompts with programs: you declare what each step
should do via signatures (input/output field specs, e.g., `question -> answer`),
compose steps into modules (ChainOfThought, ReAct, multi-hop pipelines), and let
optimizers (teleprompters) automatically find effective prompts and few-shot
examples using a metric you define. The core philosophy: prompting is an
optimization problem, so treat it like one — write the objective and the
structure, and let the compiler search the prompt space.
This inverts the usual workflow. Instead of iterating on prompt wording by vibes,
you iterate on the metric and the module decomposition, then run an optimizer
(like MIPRO or BootstrapFewShot) that generates, tests, and refines
demonstrations. The result is prompts that are found empirically rather than