How do I install the R Ellmer skill?

Run npx skillmds@latest add arthurgailes/r-ellmer in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is R Ellmer safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with R Ellmer?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is R Ellmer free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published R Ellmer?

arthurgailes (@arthurgailes) published this skill. Their other Agent Skills are listed on their SkillMD profile.

R Ellmer by arthurgailes — Agent Skill

Name: R Ellmer
Author: arthurgailes

File contents

ellmer: R Interface to Large Language Models

Overview

ellmer is the hub of the R AI stack. Provides unified interface to 20+ LLM providers (OpenAI, Claude, Ollama, etc.) with stateful chat sessions, tool calling, and token tracking.

Install: install.packages("ellmer")

API keys: Set OPENAI_API_KEY or ANTHROPIC_API_KEY in .Renviron

References

Read references/API.md before writing code.

references/API.md - Complete function reference
references/getting-started.md - Core workflow and chat patterns
references/tool-calling.md - Tool registration and function calling

When to Use

Chat with any LLM from R
Create custom chatbots with domain knowledge
Extract structured data from unstructured text
Need multi-provider support (switch between OpenAI/Claude/Ollama)
Build LLM-powered R applications

When NOT to Use

Single one-off HTTP request (use httr2)
Need streaming with custom callbacks
Non-chat ML workflows (use tidymodels)

Quick Reference

# Create chat
chat <- chat_openai(model = "gpt-4o")
chat <- chat_claude(model = "claude-sonnet-4")
chat <- chat_ollama(model = "llama3.2")  # Local

# Chat (stateful - history preserved)
chat$chat("Explain this error")
chat$chat("How do I fix it?")  # Remembers context

# Fresh conversation
chat <- chat_openai()  # New = no history

# Track costs
token_usage()

# Tool calling
chat$set_tools(btw_tools())  # See r-btw skill

Common Mistakes

Issue	Solution
Forgot API key	Set in `.Renviron`, restart R
Ollama connection error	Run `ollama serve` first
Conversation too long/expensive	Start fresh chat for new topics
Expecting accuracy	LLMs for prototyping, not critical work
Using chat for single request	Just use httr2 for one-off calls

Use Cases

Custom chatbots: Preload with documentation, package info, educational materials

Structured data extraction: Sentiment analysis, geocoding, recipe parsing, document indexing

Programming assistance: Code modernization, documentation lookup, explanation, security analysis

Other: Alt text generation, statistical reasoning, brand style guide enforcement

Advanced

See references/ for:

API.md: Complete function reference (all providers, models, methods)
getting-started.md: Core vocabulary, tokens, system prompts
tool-calling.md: Tool/function calling patterns

Integration

With btw (context tools): See r-btw skill With ragnar (RAG): See r-ragnar skill With vitals (evaluation): See r-vitals skill Cross-package patterns: See r-ai meta-skill

---name: r-ellmerdescription: Use when code loads or uses ellmer (library(ellmer), chat_openai, chat_claude, chat_ollama), chatting with LLMs from R, building chatbots, or extracting structured data from text with LLMs---# ellmer: R Interface to Large Language Models## Overview**ellmer is the hub of the R AI stack.** Provides unified interface to 20+ LLM providers (OpenAI, Claude, Ollama, etc.) with stateful chat sessions, tool calling, and token tracking.**Install:** `install.packages("ellmer")`**API keys:** Set `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` in `.Renviron`## ReferencesRead `references/API.md` before writing code.- `references/API.md` - Complete function reference- `references/getting-started.md` - Core workflow and chat patterns- `references/tool-calling.md` - Tool registration and function calling## When to Use- Chat with any LLM from R- Create custom chatbots with domain knowledge- Extract structured data from unstructured text- Need multi-provider support (switch between OpenAI/Claude/Ollama)- Build LLM-powered R applications## When NOT to Use- Single one-off HTTP request (use httr2)- Need streaming with custom callbacks- Non-chat ML workflows (use tidymodels)## Quick Reference```r# Create chatchat <- chat_openai(model = "gpt-4o")chat <- chat_claude(model = "claude-sonnet-4")chat <- chat_ollama(model = "llama3.2") # Local# Chat (stateful - history preserved)chat$chat("Explain this error")chat$chat("How do I fix it?") # Remembers context# Fresh conversationchat <- chat_openai() # New = no history# Track coststoken_usage()# Tool callingchat$set_tools(btw_tools()) # See r-btw skill```## Common Mistakes| Issue | Solution ||-------|----------|| Forgot API key | Set in `.Renviron`, restart R || Ollama connection error | Run `ollama serve` first || Conversation too long/expensive | Start fresh chat for new topics || Expecting accuracy | LLMs for prototyping, not critical work || Using chat for single request | Just use httr2 for one-off calls |## Use Cases**Custom chatbots:** Preload with documentation, package info, educational materials**Structured data extraction:** Sentiment analysis, geocoding, recipe parsing, document indexing**Programming assistance:** Code modernization, documentation lookup, explanation, security analysis**Other:** Alt text generation, statistical reasoning, brand style guide enforcement## AdvancedSee `references/` for:- **API.md**: Complete function reference (all providers, models, methods)- **getting-started.md**: Core vocabulary, tokens, system prompts- **tool-calling.md**: Tool/function calling patterns## Integration**With btw (context tools):** See r-btw skill**With ragnar (RAG):** See r-ragnar skill**With vitals (evaluation):** See r-vitals skill**Cross-package patterns:** See r-ai meta-skill

Frequently asked questions

R Ellmer