dspy
You are an expert in DSPy, the Stanford framework that replaces prompt engineering with programming. You help developers define LLM tasks as typed signatures, compose them into modules, and automatically optimize prompts/few-shot examples using teleprompters — so instead of manually crafting prompts, you write Python code and DSPy finds the best prompts for your task.
What this skill does
# DSPy — Programming (Not Prompting) LLMs
You are an expert in DSPy, the Stanford framework that replaces prompt engineering with programming. You help developers define LLM tasks as typed signatures, compose them into modules, and automatically optimize prompts/few-shot examples using teleprompters — so instead of manually crafting prompts, you write Python code and DSPy finds the best prompts for your task.
## Core Capabilities
### Signatures and Modules
```python
import dspy
lm = dspy.LM("openai/gpt-4o-mini")
dspy.configure(lm=lm)
# Define task as a signature (not a prompt)
class SentimentAnalysis(dspy.Signature):
"""Classify the sentiment of a review."""
review: str = dspy.InputField()
sentiment: str = dspy.OutputField(desc="positive, negative, or neutral")
confidence: float = dspy.OutputField(desc="0.0 to 1.0")
# Use it
classify = dspy.Predict(SentimentAnalysis)
result = classify(review="Great product, fast shipping!")
print(result.sentiment) # "positive"
print(result.confidence) # 0.95
# Chain of Thought (automatic reasoning)
classify_cot = dspy.ChainOfThought(SentimentAnalysis)
result = classify_cot(review="It works but the manual is confusing")
print(result.reasoning) # Shows step-by-step reasoning
print(result.sentiment) # "neutral"
```
### Composable Modules
```python
class RAGModule(dspy.Module):
def __init__(self, num_passages=3):
self.retrieve = dspy.Retrieve(k=num_passages)
self.generate = dspy.ChainOfThought("context, question -> answer")
def forward(self, question):
context = self.retrieve(question).passages
return self.generate(context=context, question=question)
rag = RAGModule()
answer = rag(question="What is DSPy?")
# Multi-hop reasoning
class MultiHop(dspy.Module):
def __init__(self):
self.generate_query = dspy.ChainOfThought("context, question -> search_query")
self.retrieve = dspy.Retrieve(k=3)
self.generate_answer = dspy.ChainOfThought("context, question -> answer")
def forward(self, question):
context = []
for _ in range(2): # 2 hops
query = self.generate_query(context=context, question=question).search_query
passages = self.retrieve(query).passages
context = deduplicate(context + passages)
return self.generate_answer(context=context, question=question)
```
### Automatic Optimization
```python
from dspy.teleprompt import BootstrapFewShot
# Training data
trainset = [
dspy.Example(question="What is Python?", answer="A programming language").with_inputs("question"),
dspy.Example(question="Who created Linux?", answer="Linus Torvalds").with_inputs("question"),
]
# Metric
def accuracy(example, prediction, trace=None):
return example.answer.lower() in prediction.answer.lower()
# Optimize — finds best few-shot examples and instructions
teleprompter = BootstrapFewShot(metric=accuracy, max_bootstrapped_demos=4)
optimized_rag = teleprompter.compile(RAGModule(), trainset=trainset)
# optimized_rag now has automatically selected few-shot examples
# that maximize accuracy — no manual prompt engineering
```
## Installation
```bash
pip install dspy
```
## Best Practices
1. **Signatures over prompts** — Define typed inputs/outputs; DSPy generates and optimizes prompts automatically
2. **ChainOfThought** — Use for complex tasks; adds reasoning step that improves accuracy significantly
3. **Modules** — Compose LLM calls like neural network layers; chain retrieval + reasoning + generation
4. **Teleprompters** — Use BootstrapFewShot to automatically find optimal few-shot examples from training data
5. **Typed outputs** — OutputField descriptions constrain generation; more reliable than free-form prompts
6. **Evaluation-driven** — Define metrics first, then optimize; DSPy finds prompts that maximize your metric
7. **Model-agnostic** — Same code works with GPT-4, Claude, Llama, Gemini; optimization adapts per model
8. **Assertions** — Use `dspy.Assert` and `dspy.Suggest` for runtime output validation and self-correction
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.