Updated 3mo ago
by OmidZamani
dspy-skills
Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically
124 GitHub stars (124)
+1 in 20 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | +1 |
| Sep 30 | 0 |
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | −1 |
| Oct 11 | 0 |
| Oct 12 | +1 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 23 skills (23 skills found in its SKILL.md files)
- 13 forks (13 forks)
- 3mo ago last update (Last updated 3mo ago)
Install
Skills CLI
npx skills add OmidZamani/dspy-skills
Asks which skills and agents to install. Just one: npx skills add OmidZamani/dspy-skills --skill skill-perfection — add -g for every project.
Claude Code
git clone https://github.com/OmidZamani/dspy-skillscp -r "dspy-skills/.claude/skills-skill-perfection" ~/.claude/skills/
Copies the skill-perfection skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add OmidZamani/dspy-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
skill-perfection
Use this skill when you need to QA audit and fix a plugin skill file. Provides a methodology for verifying skill content against official documentation, fixing issues in-place, and producing verification reports.
.claude/skills-skill-perfection/SKILL.md on GitHub (opens in a new tab) -
dspy-adapters-multimodal
Use for DSPy adapter selection, JSONAdapter, XMLAdapter, ChatAdapter, native function calling, structured outputs, and multimodal inputs like dspy.Image or dspy.Audio.
skills/dspy-adapters-multimodal/SKILL.md on GitHub (opens in a new tab) -
dspy-advanced-module-composition
Use for composing DSPy modules with Ensemble, MultiChainComparison, ensemble voting, sequential pipelines, and multi-program workflows.
skills/dspy-advanced-module-composition/SKILL.md on GitHub (opens in a new tab) -
dspy-better-together
Use for BetterTogether, prompt plus weight optimization, fine-tuning sequences, and strategy chains like p -> w -> p.
skills/dspy-better-together/SKILL.md on GitHub (opens in a new tab) -
dspy-bootstrap-fewshot
Use for BootstrapFewShot, bootstrapped demonstrations, teacher-model demos, and low-data DSPy prompt optimization.
skills/dspy-bootstrap-fewshot/SKILL.md on GitHub (opens in a new tab) -
dspy-custom-module-design
Use for creating custom DSPy modules, extending dspy.Module, reusable components, stateful modules, serialization, and module testing.
skills/dspy-custom-module-design/SKILL.md on GitHub (opens in a new tab) -
dspy-debugging-observability
Use for debugging DSPy programs, inspect_history, tracing LLM calls, custom callbacks, observability, monitoring, and cost tracking.
skills/dspy-debugging-observability/SKILL.md on GitHub (opens in a new tab) -
dspy-embedding-retrieval
Use for DSPy retrieval with dspy.Embedder, dspy.Embeddings, FAISS indexes, semantic search, and local or hosted embedding models.
skills/dspy-embedding-retrieval/SKILL.md on GitHub (opens in a new tab) -
dspy-evaluation-suite
Use for evaluating DSPy programs with Evaluate, answer_exact_match, SemanticF1, custom metrics, baselines, and program comparisons.
skills/dspy-evaluation-suite/SKILL.md on GitHub (opens in a new tab) -
dspy-finetune-bootstrap
Use for BootstrapFinetune, fine-tuning DSPy models, teacher-student distillation, weight optimization, and lower-cost deployment.
skills/dspy-finetune-bootstrap/SKILL.md on GitHub (opens in a new tab) -
dspy-gepa-reflective
Use for GEPA reflective optimization, ReAct agent optimization, feedback metrics, LLM reflection, and execution trajectories.
skills/dspy-gepa-reflective/SKILL.md on GitHub (opens in a new tab) -
dspy-haystack-integration
Use for integrating DSPy with Haystack, optimizing Haystack prompts, improving retrieval pipelines, and extracting DSPy prompts.
skills/dspy-haystack-integration/SKILL.md on GitHub (opens in a new tab) -
dspy-mcp-tool-integration
Use for MCP tools with DSPy, Model Context Protocol servers, dspy.Tool.from_mcp_tool, and ReAct agents over MCP-compatible tools.
skills/dspy-mcp-tool-integration/SKILL.md on GitHub (opens in a new tab) -
dspy-miprov2-optimizer
Use for MIPROv2, Bayesian optimization, instruction and demo tuning, and high-performance DSPy program optimization.
skills/dspy-miprov2-optimizer/SKILL.md on GitHub (opens in a new tab) -
dspy-optimize-anything
Use for GEPA optimize_anything on text artifacts such as code, prompts, agent architectures, configs, and non-DSPy optimization targets.
skills/dspy-optimize-anything/SKILL.md on GitHub (opens in a new tab) -
dspy-optimizer-selection
Use to choose or compare DSPy optimizers including LabeledFewShot, BootstrapFewShot, MIPROv2, SIMBA, GEPA, BootstrapFinetune, Ensemble, and BetterTogether.
skills/dspy-optimizer-selection/SKILL.md on GitHub (opens in a new tab) -
dspy-output-refinement-constraints
Use for dspy.Refine, dspy.BestOfN, output constraints, validation, reward functions, and iterative output refinement.
skills/dspy-output-refinement-constraints/SKILL.md on GitHub (opens in a new tab) -
dspy-production-deployment
Use for deploying DSPy with save/load, configure_cache, restrict_pickle, track_usage, async execution, streaming, and production runtime controls.
skills/dspy-production-deployment/SKILL.md on GitHub (opens in a new tab) -
dspy-rag-pipeline
Use for RAG pipelines, retrieval augmented generation, ColBERTv2, context retrieval, multi-hop RAG, and grounded DSPy answers.
skills/dspy-rag-pipeline/SKILL.md on GitHub (opens in a new tab) -
dspy-react-agent-builder
Use for ReAct agents, tool-calling agents, dspy.ReAct, multi-step reasoning and acting, and GEPA agent optimization.
skills/dspy-react-agent-builder/SKILL.md on GitHub (opens in a new tab) -
dspy-reasoning-modules
Use for DSPy reasoning modules including RLM, ProgramOfThought, CodeAct, Parallel, sandboxed execution, and long-context workflows.
skills/dspy-reasoning-modules/SKILL.md on GitHub (opens in a new tab) -
dspy-signature-designer
Use for DSPy signatures, InputField, OutputField, typed inputs and outputs, signature classes, and Pydantic-style structured schemas.
skills/dspy-signature-designer/SKILL.md on GitHub (opens in a new tab) -
dspy-simba-optimizer
Use for SIMBA optimization, mini-batch introspective optimization, self-reflective rules, stochastic ascent, and numeric-metric optimization.
skills/dspy-simba-optimizer/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.