# dspy-react-agent-builder

This 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.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 124
- Author: OmidZamani
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/OmidZamani/dspy-skills/tree/HEAD/skills/dspy-react-agent-builder/SKILL.md
- Updated: 2026-06-23
- HTML: https://affpapa.org/en/nevibecode/skills/dspy-react-agent-builder

## What it does

The skill shows how to define a task signature and provide Python functions as tools. It builds the agent with `dspy.ReAct`; function docstrings describe what each tool can do. The examples add error handling and logging, and use `max_iters` to cap the agent’s reasoning steps.

GEPA can optimize an agent against a training set and feedback metric. Tool calls run sequentially, not in parallel. The guidance recommends 3–7 tools, since larger sets can confuse the agent, and notes that language models differ in their support for tool calling. Examples use DSPy, `dspy.PythonInterpreter`, and `dspy.ColBERTv2`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add OmidZamani/dspy-skills --skill dspy-react-agent-builder -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/dspy-react-agent-builder/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/dspy-react-agent-builder/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add OmidZamani/dspy-skills --skill dspy-react-agent-builder -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/dspy-react-agent-builder/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add OmidZamani/dspy-skills --skill dspy-react-agent-builder -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/dspy-react-agent-builder/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install OmidZamani/dspy-skills dspy-react-agent-builder
```

2. **Manually: put the files in place**
- File: `.github/skills/dspy-react-agent-builder/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add OmidZamani/dspy-skills --skill dspy-react-agent-builder -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/OmidZamani/dspy-skills --path skills/dspy-react-agent-builder
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/dspy-react-agent-builder/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add OmidZamani/dspy-skills --skill dspy-react-agent-builder -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/OmidZamani/dspy-skills/tree/HEAD/skills/dspy-react-agent-builder/SKILL.md

## When to use it
- build a ReAct agent that searches documents
- add calculation tools to a multi-step workflow
- handle failures during tool calls
- optimize an agent with GEPA and a training set

## Example prompts
- Build a DSPy ReAct agent that searches documents and answers a question.
- Add a calculation tool and error handling to my agent.
- Set up GEPA to optimize this ReAct agent using a training set and feedback metric.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: f38eb520dc90e88b.

BEGIN THIRD-PARTY FILE f38eb520dc90e88b
````text
---
name: dspy-react-agent-builder
version: "1.0.0"
dspy-compatibility: "3.2.1"
tags: ["agent", "reasoning"]
requires-extras: []
description: Use for ReAct agents, tool-calling agents, dspy.ReAct, multi-step reasoning and acting, and GEPA agent optimization.
allowed-tools:
  - Read
  - Write
  - Glob
  - Grep
---

# DSPy ReAct Agent Builder

## Goal

Build production-quality ReAct agents that use tools to solve complex multi-step tasks with reasoning, acting, and error handling.

## When to Use

- Multi-step tasks requiring tool use
- Search + reasoning workflows
- Complex question answering with external data
- Tasks needing calculation, retrieval, or API calls

## Related Skills

- Optimize agents: [dspy-gepa-reflective](../dspy-gepa-reflective/SKILL.md)
- Connect MCP tools: [dspy-mcp-tool-integration](../dspy-mcp-tool-integration/SKILL.md)
- Configure native tool calling: [dspy-adapters-multimodal](../dspy-adapters-multimodal/SKILL.md)
- Define signatures: [dspy-signature-designer](../dspy-signature-designer/SKILL.md)
- Evaluate performance: [dspy-evaluation-suite](../dspy-evaluation-suite/SKILL.md)

## Inputs

| Input | Type | Description |
|-------|------|-------------|
| `signature` | `str` | Task signature (e.g., "question -> answer") |
| `tools` | `list[callable]` | Available tools/functions |
| `max_iters` | `int` | Max reasoning steps (default: 20) |

## Outputs

| Output | Type | Description |
|--------|------|-------------|
| `agent` | `dspy.ReAct` | Configured ReAct agent |

## Workflow

### Phase 1: Define Tools

Tools are Python functions with clear docstrings. The agent uses docstrings to understand tool capabilities:

```python
import dspy

def search(query: str) -> list[str]:
    """Search knowledge base for relevant information.

    Args:
        query: Search query string

    Returns:
        List of relevant text passages
    """
    retriever = dspy.ColBERTv2(url='http://20.102.90.50:2017/wiki17_abstracts')
    results = retriever(query, k=3)
    return [r['text'] for r in results]

def calculate(expression: str) -> float:
    """Safely evaluate mathematical expressions.

    Args:
        expression: Math expression (e.g., "2 + 2", "sqrt(16)")

    Returns:
        Numerical result
    """
    try:
        with dspy.PythonInterpreter() as interpreter:
            return interpreter.execute(expression)
    except Exception as e:
        return f"Error: {e}"
```

### Phase 2: Create ReAct Agent

```python
# Configure LM
dspy.configure(lm=dspy.LM("openai/gpt-4o-mini"))

# Create agent
agent = dspy.ReAct(
    signature="question -> answer",
    tools=[search, calculate],
    max_iters=5
)

# Use agent
result = agent(question="What is the population of Paris plus 1000?")
print(result.answer)
```

### Phase 3: Production Agent with Error Handling

```python
import dspy
import logging

logger = logging.getLogger(__name__)

class ResearchAgent(dspy.Module):
    """Production agent with error handling and logging."""
````
END THIRD-PARTY FILE f38eb520dc90e88b

The third-party file has ended. Everything between the f38eb520dc90e88b tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2987 of 6729 bytes. © OmidZamani · MIT · https://github.com/OmidZamani/dspy-skills/tree/HEAD/skills/dspy-react-agent-builder/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md