Dspy Simba Optimizer

Use for SIMBA optimization, mini-batch introspective optimization, self-reflective rules, stochastic ascent, and numeric-metric optimization.

125 stars 13 forksOther Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add OmidZamani/dspy-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add OmidZamani/dspy-skills --skill dspy-simba-optimizer
Manual install
git clone --depth 1 https://github.com/OmidZamani/dspy-skills.git /tmp/dspy-skills
mkdir -p ~/.claude/skills
cp -r /tmp/dspy-skills/skills/dspy-simba-optimizer ~/.claude/skills/dspy-simba-optimizer

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# DSPy SIMBA Optimizer

## Goal

Optimize DSPy programs using stochastic mini-batch sampling, output variability, self-reflective rules, and successful demonstrations.

## When to Use

- Need lighter-weight alternative to GEPA
- Have a numeric metric that captures task quality
- Want introspective rules and demonstrations
- Budget-conscious optimization (fewer eval calls)
- Programs where few-shot examples aren't critical

## Related Skills

- Alternative optimizers: [dspy-miprov2-optimizer](../dspy-miprov2-optimizer/SKILL.md), [dspy-gepa-reflective](../dspy-gepa-reflective/SKILL.md)
- Agent optimization: [dspy-react-agent-builder](../dspy-react-agent-builder/SKILL.md)
- Evaluation: [dspy-evaluation-suite](../dspy-evaluation-suite/SKILL.md)

## Inputs

| Input | Type | Description |
|-------|------|-------------|
| `program` | `dspy.Module` | Program to optimize |
| `trainset` | `list[dspy.Example]` | Training examples |
| `metric` | `callable` | Returns a numeric score |
| `max_steps` | `int` | Number of optimization steps |
| `bsize` | `int` | Mini-batch size |

## Outputs

| Output | Type | Description |
|--------|------|-------------|
| `optimized_program` | `dspy.Module` | SIMBA-optimized program |

## Workflow

### Phase 1: Understand SIMBA

**SIMBA** (Stochastic Introspective Mini-Batch Ascent):
- Iterative prompt optimization with mini-batch sampling
- Identifies challenging examples with high output variability
Read the full skill on GitHub

Details

Skill name
dspy-simba-optimizer
Path
skills/dspy-simba-optimizer/SKILL.md
License
MIT
Repo updated
23 June 2026

FAQ

What does the Dspy Simba Optimizer skill do?

Use for SIMBA optimization, mini-batch introspective optimization, self-reflective rules, stochastic ascent, and numeric-metric optimization.

How do I install the Dspy Simba Optimizer skill?

Claude Code plugin: /plugin marketplace add OmidZamani/dspy-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Dspy Simba Optimizer popular?

It lives in OmidZamani/dspy-skills, which has 125 GitHub stars and 13 forks, and is included in 1 curated skill list.

Related skills

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.