r-expert
Core R programming skill for all R code, package development, and data science workflows. Use when writing R functions, building packages, using tidyverse (dplyr, ggplot2, purrr), creating Shiny apps, working with R Markdown/Quarto, or doing data analysis—e.g., "write an R function", "refactor this R code", "create a Shiny dashboard", "set up package tests", "debug R errors".
89
86%
Does it follow best practices?
Impact
92%
1.55xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the key criteria. It provides specific concrete actions, includes natural trigger terms R users would actually say, explicitly states both what the skill does and when to use it, and has clear R-specific terminology that distinguishes it from other programming or data science skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'writing R functions', 'building packages', 'using tidyverse (dplyr, ggplot2, purrr)', 'creating Shiny apps', 'working with R Markdown/Quarto', 'doing data analysis'. Also includes specific examples like 'refactor this R code', 'create a Shiny dashboard', 'set up package tests', 'debug R errors'. | 3 / 3 |
Completeness | Clearly answers both what ('Core R programming skill for all R code, package development, and data science workflows') AND when with explicit 'Use when...' clause followed by specific trigger scenarios and example phrases users might say. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'R function', 'R code', 'tidyverse', 'dplyr', 'ggplot2', 'purrr', 'Shiny', 'R Markdown', 'Quarto', 'data analysis', 'package tests', 'debug R errors'. These are terms R users naturally use when seeking help. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on R programming with distinct triggers like 'R function', 'R code', 'tidyverse', 'Shiny', 'R Markdown'. The R-specific terminology makes it unlikely to conflict with Python, JavaScript, or general data science skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable R guidance with executable code examples and good progressive disclosure through complementary skills. However, it suffers from repetitive emphatic language that wastes tokens and lacks explicit validation checkpoints in the workflow. The Context7 integration is well-documented but over-emphasized at the cost of conciseness.
Suggestions
Remove repetitive phrases like 'No exceptions', 'Every time', and 'YOU MUST' - state requirements once clearly instead of repeating warnings
Add explicit validation steps to the Core Workflow, such as 'Run devtools::check() after code changes' or 'Verify output dimensions match expectations'
Consolidate the Context7 messaging into a single clear instruction rather than repeating its importance in multiple sections
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Contains some unnecessary repetition ('No exceptions', 'Every time' appears 6+ times) and over-explains the importance of Context7. The core content is useful but could be tightened by removing redundant warnings. | 2 / 3 |
Actionability | Provides fully executable code examples for data pipelines, file operations, and package structure. The patterns are copy-paste ready with specific package::function() syntax and clear directory layouts. | 3 / 3 |
Workflow Clarity | The 4-step core workflow is present but lacks validation checkpoints. No explicit verification steps between stages, and no error recovery guidance for when Context7 lookups fail or code doesn't work as expected. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, appropriate use of complementary skill references, and a single-level-deep reference to r-context7-mappings.md. Content is appropriately split between overview and detailed references. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jjjermiah/dotagents
- Commit
b74de5e
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.