Dspy
DSPy is a Python framework from Stanford NLP that replaces hand-written prompts with code: you declare LLM tasks as typed signatures, compose them into modules, and let optimizers (BootstrapFewShot, MIPROv2, GEPA) tune the prompts and few-shot examples against your metric. Use when the user asks about DSPy, signatures, ChainOfThought, ReAct, teleprompters or optimizers, or wants to stop hand-tuning prompts.
Install
npx skills add TerminalSkills/skills --skill dspygit clone --depth 1 https://github.com/TerminalSkills/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/dspy ~/.claude/skills/dspyPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# DSPy — Programming (Not Prompting) LLMs
## Overview
DSPy lets you describe what an LLM step takes in and returns (a signature), pick how it should run (`Predict`, `ChainOfThought`, `ReAct`), compose steps in a `dspy.Module`, and then optimize the whole program with a metric and a few examples. Models are called through LiteLLM-style identifiers such as `openai/gpt-4o-mini` or `gemini/gemini-2.5-flash`, so the same code moves between providers. This skill covers the current 3.x API; code written for 2.x (`dspy.Assert`, `dspy.Suggest`, `dspy.OpenAI(...)`, `dspy.settings.configure`) needs porting.
## Instructions
### Install and configure
```bash
pip install -U dspy
export OPENAI_API_KEY=... # or the key of whichever provider you use
```
```python
import dspy
dspy.configure(lm=dspy.LM("openai/gpt-4o-mini")) # global default
```
Use `with dspy.context(lm=other_lm):` to override the model for one call.
### Signatures and predictors
A signature is either a string (`"question -> answer"`) or a class with typed fields. Use `Literal[...]` or other Python types to constrain outputs. Predictors: `dspy.Predict`, `dspy.ChainOfThought` (adds a `reasoning` output field), `dspy.ReAct` (tool-using agent), `dspy.ProgramOfThought`.
### ModulesDetails
- Skill name
dspy- Repository
- TerminalSkills/skills
- Path
skills/dspy/SKILL.md- License
- Apache-2.0
- Repo updated
- 8 November 2026
FAQ
What does the Dspy skill do?
DSPy is a Python framework from Stanford NLP that replaces hand-written prompts with code: you declare LLM tasks as typed signatures, compose them into modules, and let optimizers (BootstrapFewShot, MIPROv2, GEPA) tune the prompts and few-shot examples against your metric. Use when the user asks about DSPy, signatures, ChainOfThought, ReAct, teleprompters or optimizers, or wants to stop hand-tuning prompts.
How do I install the Dspy skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add TerminalSkills/skills --skill dspy. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Dspy popular?
It lives in TerminalSkills/skills, which has 213 GitHub stars and 34 forks.
Related skills
3dsmax Rendering
213TerminalSkills/skills
Scripts and configures production rendering in Autodesk 3ds Max with the V-Ray and Corona renderers: output size and files, render elements, denoising, light mix, batch and command-line rendering, and network rendering. Use when a user asks to set up a production render, render several cameras in one batch, render from the command line or on a render farm, add render passes for compositing, or cut render time for archviz and product shots.
3dsmax Scripting
213TerminalSkills/skills
Covers scripting Autodesk 3ds Max, the 3D modeling and rendering application, with MAXScript and Python (pymxs): scene manipulation, object creation, material assignment, camera and light setup, batch operations, and file I/O. Use when tasks involve automating repetitive 3ds Max workflows, batch processing scenes, running scripts headless with 3dsmaxbatch, creating custom tools, or scripting scene setup for archviz, product visualization, or VFX.
3proxy
213TerminalSkills/skills
3proxy is a small open-source proxy server that runs HTTP/HTTPS, SOCKS4/5, SNI and TCP/UDP port-mapping proxies from one config file. Use when a user asks to set up an HTTP or SOCKS5 proxy, add proxy users and passwords, write 3proxy access rules, chain or rotate upstream (parent) proxies, limit bandwidth, connections or monthly traffic per user, run 3proxy in Docker, or fix a 3proxy.cfg that will not start.
Dvc
213TerminalSkills/skills
DVC (Data Version Control) tracks large datasets and models next to Git, builds reproducible ML pipelines and compares experiments. Use when the user says "version my dataset", "dvc add", "dvc repro", "track ML experiments", "push data to S3 or GCS" or wants to reproduce a model from a Git commit.
Dify
213TerminalSkills/skills
Dify is an open-source platform for building LLM apps such as chatbots, agents, workflows and RAG knowledge bases, and it exposes every published app as a REST API. Use when a user asks to self-host Dify with Docker Compose, configure Dify environment variables, call a Dify app or workflow API, upload documents to a Dify knowledge base, export or import a Dify DSL file, run a Dify app from the terminal with difyctl, or upgrade and back up a Dify instance.
E2b
213TerminalSkills/skills
E2B is a cloud platform that gives AI agents secure, isolated sandboxes — ephemeral Linux VMs with a filesystem, package managers, and internet access — to run AI-generated code safely. Use when a user wants an agent to execute Python or JavaScript, install packages, read/write files, or run a long process without risking the host machine, or wants to wire code execution into a LangChain, CrewAI, or custom agent loop.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.