dspy-skills MCP — Use Cases, Install & Live Demo

Why use it

Key features

DSPy signatures / modules / predictors encoded as patterns
Teleprompter (BootstrapFewShot, MIPRO) usage guidance
Evaluation + metric design
RAG pipeline scaffolds with DSPy retrievers
Opinionated integration with common LLM providers

Live Demo

What it looks like in practice

dspy-skill.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "dspy-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/OmidZamani/dspy-skills",
        "~/.claude/skills/dspy-skills"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "dspy-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/OmidZamani/dspy-skills",
        "~/.claude/skills/dspy-skills"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "dspy-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/OmidZamani/dspy-skills",
        "~/.claude/skills/dspy-skills"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "dspy-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/OmidZamani/dspy-skills",
        "~/.claude/skills/dspy-skills"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "dspy-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/OmidZamani/dspy-skills",
        "~/.claude/skills/dspy-skills"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "dspy-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/OmidZamani/dspy-skills",
          "~/.claude/skills/dspy-skills"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add dspy-skill -- git clone https://github.com/OmidZamani/dspy-skills ~/.claude/skills/dspy-skills

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use dspy-skills

How to build your first DSPy program and optimize it

👤 ML engineers and applied researchers ⏱ ~90 min advanced

When to use: You have a task where prompt quality matters and want a systematic way to improve it.

Prerequisites

Python 3.10+ with dspy-ai installed — pip install dspy-ai
Skill cloned — git clone https://github.com/OmidZamani/dspy-skills ~/.claude/skills/dspy-skills

Flow

Define the signature

Task: classify support tickets into {billing, technical, account}. Give me a DSPy signature and a simple Predict module.✓ Copied

→ Signature + module code
Write an eval

Add an evaluation set of 50 labeled examples and an accuracy metric.✓ Copied

→ Eval harness with metric callable
Optimize

Run BootstrapFewShot to compile the module against the eval set.✓ Copied

→ Compiled predictor + improved score

Outcome: A DSPy-optimized predictor that beats a hand-written prompt, with reproducible code.

Pitfalls

Eval too small — optimizer overfits — Minimum 100–200 examples; hold out a true test set
Metric doesn't capture what you care about — Spend on metric design before on model choice

Combine with: filesystem

Build a RAG pipeline with DSPy

👤 Engineers building retrieval-augmented systems ⏱ ~120 min advanced

When to use: You want modular, optimizable RAG rather than a hand-wired chain.

Flow

Define the modules

Create a DSPy RAG pipeline: RetrieveThenRead with ColBERTv2 or a local retriever.✓ Copied

→ Modular pipeline with separate retrieval and generation
Optimize end-to-end

Write an eval on our QA set and run MIPRO to improve.✓ Copied

→ Compiled pipeline with score delta

Outcome: A RAG pipeline you can improve by changing the eval, not by rewriting prompts.

Pitfalls

Retriever quality caps end-to-end quality — Evaluate retrieval separately (recall@k) before optimizing generation

Combine with: local-rag

Combinations

Pair with other MCPs for X10 leverage

dspy-skill + local-rag

Plug a local retriever into DSPy's RAG modules

Swap the ColBERT retriever for a local-rag MCP as the retrieval source.✓ Copied

dspy-skill + filesystem

Organize DSPy programs, evals, and artifacts in a repo

Lay out a DSPy project with programs/, evals/, and artifacts/ directories.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
signature-design	task spec	Start of any DSPy program	0
module-authoring	signatures + flow	After signatures	0
teleprompter-optimization	module + eval	After eval is ready	LLM tokens during optimization
evaluation-harness	task data	Before optimizing	0

Cost & Limits

What this costs to run

API quota: LLM tokens dominate during optimization runs
Tokens per call: Can be high — optimizations may invoke the LLM hundreds of times
Monetary: depends on provider
Tip: Use cheap models during teleprompter runs, upgrade only for final evaluation

Security

Permissions, secrets, blast radius

Credential storage: LLM provider keys in env vars

Data egress: LLM provider endpoints

Troubleshooting

Common errors and fixes

Teleprompter seems to make things worse

Check metric correctness; use a held-out set; widen the example pool.

Optimization eats your budget

Cap max_bootstrapped_demos and use cheaper models during search.

Alternatives

dspy-skills vs others

Alternative	When to use it instead	Tradeoff
prompt-architect-skill	You want prompt-level craft, not DSPy's programmatic approach	Hand-crafted vs optimized

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills