Dspy Adapters Multimodal
Use for DSPy adapter selection, JSONAdapter, XMLAdapter, ChatAdapter, native function calling, structured outputs, and multimodal inputs like dspy.Image or dspy.Audio.
Install
/plugin marketplace add OmidZamani/dspy-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add OmidZamani/dspy-skills --skill dspy-adapters-multimodalgit clone --depth 1 https://github.com/OmidZamani/dspy-skills.git /tmp/dspy-skills
mkdir -p ~/.claude/skills
cp -r /tmp/dspy-skills/skills/dspy-adapters-multimodal ~/.claude/skills/dspy-adapters-multimodalPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# DSPy Adapters and Multimodal I/O
## Goal
Choose an adapter deliberately and model image, audio, and file inputs with DSPy's typed primitives.
## Adapter Selection
| Adapter | Use it for |
|---------|------------|
| `dspy.ChatAdapter()` | Default, human-readable field markers, broad model compatibility |
| `dspy.JSONAdapter()` | Structured JSON output and native function calling where supported |
| `dspy.XMLAdapter()` | XML-tagged fields when XML is easier for the target LM to follow |
| `dspy.TwoStepAdapter()` | A separate extraction pass when parsing needs extra help |
Configure globally or for a limited scope:
```python
import dspy
dspy.configure(
lm=dspy.LM("openai/gpt-4o-mini"),
adapter=dspy.JSONAdapter(),
)
with dspy.context(adapter=dspy.XMLAdapter()):
result = dspy.Predict("question -> answer")(question="What is DSPy?")
```
## Native Function Calling
`JSONAdapter` enables native function calling by default. `ChatAdapter` keeps text parsing by default. Override either behavior explicitly:
```python
chat_native = dspy.ChatAdapter(use_native_function_calling=True)
json_manual = dspy.JSONAdapter(use_native_function_calling=False)
```
DSPy falls back to manual parsing when the configured LM does not support native function calling.
## Image InputsDetails
- Skill name
dspy-adapters-multimodal- Repository
- OmidZamani/dspy-skills
- Path
skills/dspy-adapters-multimodal/SKILL.md- License
- MIT
- Repo updated
- 23 June 2026
- Listed in
- heilcheng/awesome-agent-skills
FAQ
What does the Dspy Adapters Multimodal skill do?
Use for DSPy adapter selection, JSONAdapter, XMLAdapter, ChatAdapter, native function calling, structured outputs, and multimodal inputs like dspy.Image or dspy.Audio.
How do I install the Dspy Adapters Multimodal 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 Adapters Multimodal 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
Dspy Advanced Module Composition
125OmidZamani/dspy-skills
Use for composing DSPy modules with Ensemble, MultiChainComparison, ensemble voting, sequential pipelines, and multi-program workflows.
Dspy Better Together
125OmidZamani/dspy-skills
Use for BetterTogether, prompt plus weight optimization, fine-tuning sequences, and strategy chains like p -> w -> p.
Dspy Bootstrap Fewshot
125OmidZamani/dspy-skills
Use for BootstrapFewShot, bootstrapped demonstrations, teacher-model demos, and low-data DSPy prompt optimization.
Notebooklm Video Research
79BayramAnnakov/notebooklm-youtube-skill
Automate NotebookLM notebook creation from YouTube videos. Given a YouTube video URL, extract information about people featured in the video, research them online, create a new NotebookLM notebook with the video and research as sources, and generate an audio overview. Uses screenshot-first automation to reliably target UI elements.
Klik Remotion Method
97t3knobox/klik-anim-skill-creation
The Klik production method — takes a user from prompt to COMPLETE animated video (motion graphics + typography) in Remotion. Runs a fixed discovery questioning sequence into a single source of truth, then a visual storyboard the user approves as PIXELS, then a frozen execution plan built on Opus. Trigger whenever the user asks to produce a full video — "make a promo/launch/brand video", "create an animated video for X", "turn this script into a video" — or when a project contains *_animation_SSOT.md / *_storyboard.html / *_execution_plan.md / PROGRESS.md artifacts (at the root or in a klik/ pl
Video Storyboard Generator
76OYYH-Apple/video-storyboard-generator
视频分镜脚本生成器,支持头脑风暴、用户偏好记忆、15秒镜头规则、角色提示词生成、音效/BGM建议。用于生成带运镜指导、画面设计、旁白、角色描述的完整分镜脚本。支持极简版(内容描述)和专业版(详细运镜)。适用:教程、书籍介绍、评论、剧情、产品介绍、数据报告。当用户说"做分镜"、"分镜脚本"、"视频分镜"时使用。
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.