Agent skill

Dspy

Optimize and build programmatic prompt systems with Stanford DSPy.

MITAuto-check passedAI & LLM Engineering

Install Dspy

skills CLI

$ npx skills add magnus919/agent-skills --skill dspy -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install magnus919/agent-skills dspy --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/dspy .claude/skills/dspy && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "dspy" agent skill from https://github.com/magnus919/agent-skills/tree/main/dspy into .claude/skills/dspy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dspy", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/magnus919/agent-skills/tree/main/dspy

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add magnus919/agent-skills --skill dspy -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install magnus919/agent-skills dspy --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/dspy .agents/skills/dspy && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "dspy" agent skill from https://github.com/magnus919/agent-skills/tree/main/dspy into .agents/skills/dspy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dspy", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add magnus919/agent-skills --skill dspy -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install magnus919/agent-skills dspy --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/dspy .cursor/skills/dspy && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "dspy" agent skill from https://github.com/magnus919/agent-skills/tree/main/dspy into .cursor/skills/dspy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dspy", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/magnus919/agent-skills.git --path dspy

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add magnus919/agent-skills --skill dspy -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install magnus919/agent-skills dspy --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/dspy .gemini/skills/dspy && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "dspy" agent skill from https://github.com/magnus919/agent-skills/tree/main/dspy into .gemini/skills/dspy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dspy", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install magnus919/agent-skills dspy

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add magnus919/agent-skills --skill dspy -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/dspy .github/skills/dspy && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "dspy" agent skill from https://github.com/magnus919/agent-skills/tree/main/dspy into .github/skills/dspy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dspy", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add magnus919/agent-skills --skill dspy -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install magnus919/agent-skills dspy --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/dspy .opencode/skills/dspy && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "dspy" agent skill from https://github.com/magnus919/agent-skills/tree/main/dspy into .opencode/skills/dspy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dspy", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: dspy
GitHub stars: 115
Token cost: ~2k tokens
SKILL.md length: 696 words
Files: 16 (incl. scripts, references)
Skills in repo: 131
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Optimize and build programmatic prompt systems with Stanford DSPy.

Works in 6 steps: DSPy is a compiler, not a chain… → Signatures define the task. Input/output… → Modules are program components.… → …
Doing programmatic prompt optimization
SKILL.md covers Core Paradigm, Core Principles, Where to Start and Quick Reference, plus 6 more sections
Runs Python scripts from its folder

What it does

Dspy is an agent skill from magnus919/agent-skills. Optimize and build programmatic prompt systems with Stanford DSPy. Signatures, modules (Predict, ChainOfThought, ReAct), optimizer/teleprompter selection, compilation, caching, evaluation. Use when doing programmatic prompt optimization or building compiled prompt programs. Do not use this skill for unrelated requests; route to the nearest named specialist.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 19 other files, including scripts and reference files (for example `README.md`, `evals/evals.json` and `references/agent-patterns.md`).

It sits in AI & LLM Engineering, covering Prompt engineering and Caching. It works with React and Python. The repository describes itself as: Curated collection of AI agent skills for Hermes and other agent frameworks. The licence is MIT.

When your agent uses it

Doing programmatic prompt optimization
Building compiled prompt programs
Unrelated requests
Route to the nearest named specialist

Example prompts

“/dspy”

Requirements

Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

DSPy is a compiler, not a chain framework. You define the program structure with Python control flow and typed signatures. The compiler…
Signatures define the task. Input/output field pairs with optional descriptions are the task definition. The syntax is input1, input2 ->…
Modules are program components. dspy.Predict (direct), dspy.ChainOfThought (reasoning), dspy.ReAct (tool-use), and custom dspy.Module…
Optimizers tune prompts, not weights. A dozen optimizers (teleprompters) tune instructions, few-shot demos, or both. Selection depends on…
Compile once, serve many. Compilation is expensive ($3-$300+). The output is a portable artifact via program.save(path). Inference is cheap.
Cache aggressively. DSPy caches all LM calls by default. Set DSPY_CACHEDIR for the current client. Disable with dspy.LM(..., cache=False).

What it can do on your machine

Read from SKILL.md and the folder at commit 22b4723. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dspy loads about 2k tokens when it runs, and up to ~7.3k if it reads all its reference files. Until then it costs about 91 tokens; SKILL.md has 696 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~91
When it runs · the whole SKILL.md, loaded when a task matches: ~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~7.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from magnus919/agent-skills at commit 22b4723, republished under its MIT licence (© magnus919). 696 words, ~1,966 tokens.

Download SKILL.mdSave it as .claude/skills/dspy/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.

name: dspy
description: Optimize and build programmatic prompt systems with Stanford DSPy. Signatures, modules (Predict, ChainOfThought, ReAct), optimizer/teleprompter selection, compilation, caching, evaluation. Use when doing programmatic prompt optimization or building compiled prompt programs. Do not use this skill for unrelated requests; route to the nearest named specialist.
license: MIT
metadata.author: Magnus Hedemark
metadata.version: 1.1.0
metadata.source: https://dspy.ai

DSPy Expert Skill

DSPy is a compiler for prompt programs, not a chain or RAG framework. You write Python programs with typed signatures and DSPy optimizes the prompts automatically.

⚠️ DSPy is NOT a chain framework. It does not use prompt | model | parser. It does not have LCEL. DSPy operates at a different layer: you define a program with Python control flow and typed signatures, then the compiler optimizes the prompts against a metric. If you reach for DSPy expecting LangChain-style composition, you are reaching for the wrong tool.

Think of it as PyTorch for LMs — you define the architecture, the compiler tunes the weights (prompts).

Core Paradigm

Read this first. It is the most important thing to understand about DSPy.

python

import dspy

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

# 2. Define a signature (input/output schema)
class QASignature(dspy.Signature):
    """Answer questions concisely."""
    question: str = dspy.InputField()
    answer: str = dspy.OutputField()

# 3. Build a program using modules
qa = dspy.ChainOfThought(QASignature)

# 4. Compile against a metric
optimizer = dspy.MIPROv2(metric=dspy.answer_exact_match)
compiled_qa = optimizer.compile(qa, trainset=trainset, num_trials=25)

# 5. Use the compiled program (portable artifact)
answer = compiled_qa(question="What is DSPy?").answer

Core Principles

DSPy is a compiler, not a chain framework. You define the program structure with Python control flow and typed signatures. The compiler optimizes the prompts. This is fundamentally different from LangChain's explicit prompt composition.
Signatures define the task. Input/output field pairs with optional descriptions are the task definition. The syntax is input1, input2 -> output1, output2.
Modules are program components. dspy.Predict (direct), dspy.ChainOfThought (reasoning), dspy.ReAct (tool-use), and custom dspy.Module subclasses. Compose them with Python control flow (if/for/while).
Optimizers tune prompts, not weights. A dozen optimizers (teleprompters) tune instructions, few-shot demos, or both. Selection depends on bottleneck and budget. See the optimizer cheat sheet.
Compile once, serve many. Compilation is expensive ($3-$300+). The output is a portable artifact via program.save(path). Inference is cheap.
Cache aggressively. DSPy caches all LM calls by default. Set DSPY_CACHEDIR for the current client. Disable with dspy.LM(..., cache=False).

Where to Start

You already have...	Start here
Nothing — exploring DSPy	Understand the paradigm (read this page first), then build a simple Predict program
A working prompt you want to optimize	Port to a DSPy Signature, add ChainOfThought, compile with BootstrapFewShot
A multi-step pipeline	Build as a custom dspy.Module with Python control flow, compile with MIPROv2
An agent/tool-use task	Use dspy.ReAct with tools, compile with GEPA or AvatarOptimizer
Comparing frameworks	See the Framework Routing Guide

Quick Reference

Task	Approach	Reference
Basic prediction	`dspy.Predict(signature)`	`references/core-modules.md`
With reasoning	`dspy.ChainOfThought(signature)`	`references/core-modules.md`
With tools	`dspy.ReAct(tools=tools)`	`references/agent-patterns.md`
Custom program	`class MyProgram(dspy.Module)`	`references/program-patterns.md`
Quick optimization	`dspy.BootstrapFewShot(metric)`	`references/optimizer-guide.md`
Full optimization	`dspy.MIPROv2(metric, auto="medium")`	`references/optimizer-guide.md`
Evaluation	`dspy.Evaluate(metric=fn, devset=examples)`	`references/evaluation.md`
Save/load	`program.save(path)` / `program.load(path)`	`references/compilation-guide.md`
Retrieval	`dspy.Retrieve(k=5)`	`references/program-patterns.md`

Show full SKILL.md (311 more words)Show less

Framework Routing Guide

Scenario	Reach for	Why
Prompt optimization / compiled programs	DSPy	Only framework that auto-optimizes prompts against a metric
Documents to query / RAG	LlamaIndex	Data ingestion and retrieval are first-class primitives
Chain/agent composition	LangChain	LCEL is the cleanest pipe-based composition model
State-machine multi-agent	LangGraph	Graph topology, subgraphs, human-in-the-loop
Search pipelines	Haystack	Pipeline model is more mature for search workloads
Role-based teams	CrewAI	Higher-level agent abstraction

Reference Files

Reference	Load when	File
Core Modules	Building with Predict, ChainOfThought, ReAct	`references/core-modules.md`
Optimizer Guide	Choosing and configuring an optimizer	`references/optimizer-guide.md`
Program Patterns	RAG, classification, multi-step, tool-use	`references/program-patterns.md`
Evaluation	Metrics, evaluation loop, dataset creation	`references/evaluation.md`
Compilation Guide	Caching, cost management, save/load	`references/compilation-guide.md`
Agent Patterns	ReAct agent, tool-use, AvatarOptimizer	`references/agent-patterns.md`
FAQ & Troubleshooting	Common errors and fixes	`references/faq-and-troubleshooting.md`
Validation Audit	Research validation of all API claims	`references/validation-audit.md`
Worked RAG Example	Full RAG compilation with expected output	`references/example-rag-compilation.md`

Template Files

Template	When to use	File
Classification	Text classification with BootstrapFewShot	`templates/classification.py`
RAG Program	RAG with ColBERT retrieval and ChainOfThought	`templates/rag-program.py`
Multi-Step Reasoning	Multi-step program with tool-use	`templates/multi-step.py`

Scripts

Script	Purpose	File
check-setup	Verify DSPy installation and configuration	`scripts/check-setup.py`

Troubleshooting

Symptom	Likely cause	Fix	Reference
Compilation too slow	Too many candidates/threads	Reduce `num_candidates` or use `auto="light"`	`references/optimizer-guide.md`
Compilation too expensive	No caching	Enable DSPY_CACHEDIR	`references/compilation-guide.md`
Context too long	Too many demos	Reduce `max_bootstrapped_demos` and `max_labeled_demos`	`references/faq-and-troubleshooting.md`
Low quality after compile	Wrong optimizer for bottleneck	Check cheat sheet: instructions vs demos vs weights	`references/optimizer-guide.md`
Program is not improving	Metric not discriminating	Use a metric that returns float, not bool	`references/evaluation.md`
Sub-module not updating	_compiled flag set	Set `module._compiled = False` before recompiling	`references/compilation-guide.md`

When NOT to Use DSPy

Simple single-prompt application — raw API calls are simpler
Need pre-built application modules (PDF Q&A, text-to-SQL) — use LlamaIndex or LangChain
One-shot task with no optimization budget — DSPy's compiler overhead won't amortize
Real-time latency-critical — compilation happens at development time but adds no inference overhead

Files

SKILL.md and 15 other files (scripts, references) in dspy of magnus919/agent-skills.

SKILL.md
README.md
evals/evals.json
references/agent-patterns.md
references/compilation-guide.md
references/core-modules.md
references/evaluation.md
references/example-rag-compilation.md
references/faq-and-troubleshooting.md
references/optimizer-guide.md
references/program-patterns.md
references/validation-audit.md
scripts/check-setup.py
templates/classification.py
templates/multi-step.py
templates/rag-program.py

Open the folder on GitHubat commit 22b4723

Compare with similar skills

Dspy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dspy compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Dspy this skillmagnus919/agent-skills	115	—	~2k	Automated safety check: Pass	MIT	today
Claude Cookbooks Reference2025Emma/vibe-coding-cn	23k	1 repos	~2.2k	Automated safety check: Pass	MIT	9 mo ago
Prompt Engineering Patternswshobson/agents	40k	—	~1.3k	Automated safety check: Pass	MIT	5 days ago
Opikcomet-ml/opik-mcp	220	—	~2.1k	Automated safety check: Pass	Apache-2.0	2 days ago
Flowfile AI Subsystem GuideEdwardvaneechoud/Flowfile	385	—	~9.1k	Automated safety check: Notes	MIT	today
Guidance Constrained GenerationOrchestra-Research/AI-Research-SKILLs	13k	5 repos	~3.6k	Automated safety check: Pass	MIT	3 mo ago

Similar skills

Claude Cookbooks Reference
2025Emma/vibe-coding-cn
Reference of Claude API examples and guides covering tool use, vision, RAG, classification, summarization, text-to-SQL, prompt caching and agent patterns.
23k GitHub starsUsed in 1 repo~2.2k tokens
AI & LLM EngineeringAuto-check passed
Prompt Engineering Patterns
wshobson/agents
Reference for designing and tuning production LLM prompts: few-shot examples, chain-of-thought, structured outputs, templates and system prompts.
40k GitHub stars~1.3k tokensUpdated 5 days ago
AI & LLM EngineeringAuto-check passed
Opik
comet-ml/opik-mcp
Reference for the Opik SDK — tracing, span types, framework integrations, threads, and the prompt library (Python, TypeScript, REST).
220 GitHub stars~2.1k tokensUpdated 2 days ago
AI & LLM EngineeringAuto-check passed
Flowfile AI Subsystem Guide
Edwardvaneechoud/Flowfile
Maps the /ai/ subsystem of flowfile_core, its three agent tiers, litellm seam, BYOK keys and rate limits, and sets rules for extending or debugging it safely.
385 GitHub stars~9.1k tokensUpdated today
AI & LLM EngineeringAuto-check: notes
Guidance Constrained Generation
Orchestra-Research/AI-Research-SKILLs
Constrains language model output with regex, selections and grammars using the Guidance library, so JSON, XML, code or formatted fields come out valid.
13k GitHub starsUsed in 5 repos~3.6k tokens
AI & LLM EngineeringAuto-check passed
Lintlang Audit
hermes-labs-ai/lintlang
Audit a named AI agent config, system prompt, tool-definition or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI, on request.
140 GitHub stars~1.8k tokensUpdated today
AI & LLM EngineeringAuto-check passed

Questions about Dspy

What does Dspy do?

Optimize and build programmatic prompt systems with Stanford DSPy. Dspy is an agent skill from magnus919/agent-skills. Optimize and build programmatic prompt systems with Stanford DSPy.

When should I use Dspy?

Dspy fits situations like: doing programmatic prompt optimization; building compiled prompt programs; unrelated requests; route to the nearest named specialist.

How do I install Dspy in Claude Code?

Run `npx skills add magnus919/agent-skills --skill dspy -a claude-code`. Or copy the skill folder (dspy in magnus919/agent-skills) into .claude/skills/dspy in your project. Claude Code loads it when a task matches its description.

How do I install Dspy in Codex?

Run `npx skills add magnus919/agent-skills --skill dspy -a codex`. Or copy the skill folder (dspy in magnus919/agent-skills) into .agents/skills/dspy in your project. Codex loads it when a task matches its description.

Can I use Dspy in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add magnus919/agent-skills --skill dspy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dspy, .gemini/skills/dspy, .github/skills/dspy and .opencode/skills/dspy in your project.

What does Dspy need to run?

Going by SKILL.md and its folder, Dspy needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Dspy access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Dspy safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Dspy use?

Dspy is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dspy use?

About 2k tokens (SKILL.md is roughly 7.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.3k tokens, read only when the agent opens those files.

What are the alternatives to Dspy?

Skills that share tags, products or a category with Dspy: Claude Cookbooks Reference (2025Emma/vibe-coding-cn, 23k stars), Prompt Engineering Patterns (wshobson/agents, 40k stars), Opik (comet-ml/opik-mcp, 220 stars) and Flowfile AI Subsystem Guide (Edwardvaneechoud/Flowfile, 385 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dspy?

magnus919 (a GitHub user) maintains it in magnus919/agent-skills, which has 115 GitHub stars. The repository holds 131 skills in this directory. The repository was last updated on October 10, 2026.

Source: magnus919/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Dspy

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

DSPy Expert Skill

Core Paradigm

Core Principles

Where to Start

Quick Reference

Framework Routing Guide

Reference Files

Template Files

Scripts

Troubleshooting

When NOT to Use DSPy

Files

Compare with similar skills

Similar skills

More from magnus919/agent-skills

Related

Questions about Dspy