NeVibeCode · repository · 23 items
dspy-skills: a set by omidzamani
The omidzamani/dspy-skills repository on GitHub: 23 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.
About the repository
- GitHub
- omidzamani/dspy-skills
- Stars
- ★ 125
- License
- MIT
- Source updated
- 2026-06-23
- In the catalog since
- 2026-10-26
skill-perfection skill skill-perfection is a Claude Code skill that audits and patches skill markdown files against official documentation in one pass. It supports preparing an agent skill for release.
CX Codex +1
★ 125repo stars
dspy-simba-optimizer skill The dspy-simba-optimizer skill guides SIMBA optimization for DSPy programs, using numeric scores to refine prompts and demonstrations. Use it when you can measure task quality with a metric.
CX Codex +1
★ 125repo stars
dspy-signature-designer skill dspy-signature-designer turns a task description into a typed DSPy signature with declared inputs and outputs. Useful when model replies must fit a fixed schema.
CX Codex +1
★ 125repo stars
dspy-reasoning-modules skill dspy-reasoning-modules guides configuration of DSPy 3.2.1 reasoning modules including RLM, ProgramOfThought, CodeAct, and Parallel. Useful for sandboxed code and long documents.
CX Codex +1
★ 125repo stars
dspy-react-agent-builder skill The dspy-react-agent-builder skill guides you through building DSPy ReAct agents that call tools to handle multi-step tasks. Use it for workflows involving retrieval, calculations, or answers based on external data.
CX Codex +1
★ 125repo stars
dspy-rag-pipeline skill dspy-rag-pipeline builds retrieval-augmented generation pipelines powered by ColBERTv2 that can be systematically optimized. Use when questions require searching across your own document corpus and grounding answers in retrieved facts.
CX Codex +1
★ 125repo stars
dspy-production-deployment skill dspy-production-deployment prepares DSPy 3.2.1 pipelines for production by configuring safe caching, state-only JSON persistence, async calls, and output streaming.
CX Codex +1
★ 125repo stars
dspy-output-refinement-constraints skill The dspy-output-refinement-constraints skill shows how to validate DSPy outputs, refine them with dspy.Refine, and choose among candidates with dspy.BestOfN. Use it when generated results must meet format or content rules.
CX Codex +1
★ 125repo stars
dspy-optimizer-selection skill dspy-optimizer-selection helps you pick a DSPy optimizer that fits your data and budget, from LabeledFewShot up to GEPA and BetterTogether. Useful when you don't know where to start compiling.
CX Codex +1
★ 125repo stars
dspy-optimize-anything skill dspy-optimize-anything guides AI agents through GEPA reflective evolutionary search for code, prompts, configs, and text artifacts using diagnostic feedback.
CX Codex +1
★ 125repo stars
dspy-miprov2-optimizer skill The dspy-miprov2-optimizer skill guides MIPROv2 optimization of DSPy programs, searching for instruction and few-shot demo combinations with Bayesian optimization. Use it to tune a program against training data.
CX Codex +1
★ 125repo stars
dspy-mcp-tool-integration skill dspy-mcp-tool-integration — a skill that walks through wiring an MCP server into DSPy: turning its tools into dspy.Tool and calling them from an async agent.
CX Codex +1
★ 125repo stars
dspy-haystack-integration skill dspy-haystack-integration optimizes Haystack pipeline prompts using DSPy few-shot compilers. Connects Haystack retrievers into DSPy modules for data-driven prompt tuning.
CX Codex +1
★ 125repo stars
dspy-gepa-reflective skill dspy-gepa-reflective is a Claude Code skill for reflective GEPA optimization of agent systems. It targets ReAct workflows that use execution traces and text feedback.
CX Codex +1
★ 125repo stars
dspy-finetune-bootstrap skill dspy-finetune-bootstrap turns a working DSPy program into fine-tuned weights for a smaller model, cutting inference cost and speeding up responses.
CX Codex +1
★ 125repo stars
dspy-evaluation-suite skill dspy-evaluation-suite is a Claude Code skill that tests and benchmarks DSPy modules against evaluation datasets with parallel execution and custom scoring.
CX Codex +1
★ 125repo stars
dspy-embedding-retrieval skill dspy-embedding-retrieval is a skill for semantic retrieval over an application-owned text corpus with DSPy embeddings and optional FAISS, for retrieval and RAG.
CX Codex +1
★ 125repo stars
dspy-debugging-observability skill dspy-debugging-observability — a skill for debugging and monitoring DSPy programs: call history, MLflow tracing, and custom callbacks that track cost and errors.
CX Codex +1
★ 125repo stars
dspy-custom-module-design skill dspy-custom-module-design is a Claude Code skill for building custom DSPy modules and extending dspy.Module. It comes into play when a project needs reusable components, module state, or serialization.
CX Codex +1
★ 125repo stars
dspy-bootstrap-fewshot skill dspy-bootstrap-fewshot is a Claude Code skill that builds few-shot demonstrations for DSPy programs with a teacher model, for 10–50 labeled examples when manual selection gets tedious.
CX Codex +1
★ 125repo stars
dspy-better-together skill dspy-better-together — a skill that walks you through chaining DSPy prompt and weight optimizers, scoring intermediate programs and keeping the best one.
CX Codex +1
★ 125repo stars
dspy-advanced-module-composition skill dspy-advanced-module-composition composes complex DSPy programs using module ensembling, MultiChainComparison, sequential pipelines, and fallbacks. Useful for multi-step reasoning architectures.
CX Codex +1
★ 125repo stars
dspy-adapters-multimodal skill The dspy-adapters-multimodal skill guides DSPy adapter choices for structured responses, function calls, and image, audio, or document inputs. Use it when building DSPy-based AI applications.
CX Codex +1
★ 125repo stars