菜单
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
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when code loads or uses duckspatial (library(duckspatial), duckspatial::), performing spatial joins or areal interpolation on large vector datasets in R, or needing faster spatial operations than sf
Use when creating, editing, or validating R package skills (library(pkg), pkg::), or gathering R package documentation (CRAN, pkgdown, vignettes) to generate a skill
Use when code loads or uses btw (library(btw), btw::), providing R session context to LLMs, registering tools for ellmer chat, or copying R object descriptions to clipboard
Use when code loads or uses collapse (library(collapse), collapse::), performing fast grouped or weighted statistics in R, or seeking faster alternatives to dplyr aggregation
Use when code loads or uses mapgl (library(mapgl), mapgl::), calls maplibre()/mapboxgl()/add_*_layer()/maplibre_proxy(), builds interactive WebGL maps in R, displays PMTiles on a map, or creates story maps / scrollytelling in R Shiny
Use when code loads ellmer, btw, mcptools, ragnar, or vitals, building LLM-powered R applications, implementing RAG workflows, or choosing between R AI packages (meta-skill for ellmer/btw/mcptools/ragnar/vitals)
| name | r-ellmer |
| description | 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 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
Read references/API.md before writing code.
references/API.md - Complete function referencereferences/getting-started.md - Core workflow and chat patternsreferences/tool-calling.md - Tool registration and function calling# 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
| 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 |
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
See references/ for:
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