██████╗
██╔══██╗
██████╔╝
██╔══██╗
██║  ██║
╚═╝  ╚═╝

██████╗  █████╗ ████████╗ █████╗ ██████╗  █████╗ ███████╗██╗  ██╗
██╔══██╗██╔══██╗╚══██╔══╝██╔══██╗██╔══██╗██╔══██╗██╔════╝██║  ██║
██║  ██║███████║   ██║   ███████║██║  ██║███████║███████╗███████║
██║  ██║██╔══██║   ██║   ██╔══██║██║  ██║██╔══██║╚════██║██╔══██║
██████╔╝██║  ██║   ██║   ██║  ██║██████╔╝██║  ██║███████║██║  ██║
╚═════╝ ╚═╝  ╚═╝   ╚═╝   ╚═╝  ╚═╝╚═════╝ ╚═╝  ╚═╝╚══════╝╚═╝  ╚═╝

⚡ R DataDash

Skills that help an agent teach and build R dashboards, with the SQL and Power BI links around them, for students and lecturers.

Validate skills License: MIT Agent skills Format Tooling

Table of contents:

Skills
How they fit together
Install
Usage
Optional agent profiles
Validate
Layout
Status and limits

Important

Principle: Every dashboard number must trace back to data the learner can inspect, and the agent explains the why, not only the code.

The skills cover Shiny, bs4Dash and Quarto dashboards, data preparation, database links, statistics, chart design and Power BI modelling. They are grounded in the official Shiny, Quarto, DBI and Microsoft Learn documentation, plus MIT-licensed community material credited below, and follow the open Agent Skills format. They work in Claude Code, Codex, Cursor, Copilot, OpenCode, or any SKILL.md-compatible agent.

🧩 Skills

Skill	Purpose
`powerbi-model-and-dax`	Governs Power BI data models and DAX measures: star schema, relationships, date tables, storage modes, row-level security, and readable, fast DAX with variables and time intelligence.
`r-dashboard-design`	Governs how a dashboard looks and performs: choosing a chart, arranging the page, colour and accessibility, labelling, and speed habits for R and Power BI dashboards.
`r-data-prep`	Governs getting data ready for a dashboard in R: reading CSV, Excel and JSON, calling web APIs, scraping tables, cleaning, date handling, and the extract-transform-load script shape.
`r-datadash`	Router and shared guardrails for building, explaining and checking data dashboards with R, plus the SQL and Power BI links around them, aimed at students and lecturers.
`r-dplyr-wrangling`	Governs reshaping a data frame in R with dplyr before it feeds a dashboard: select and rename columns, filter rows (including missing values), make or recode columns with mutate and case_when, group and summarise, count, and work within groups.
`r-quarto-dashboards`	Governs how to build and fix Quarto dashboards with R: the dashboard format, rows, columns, pages, tabsets, cards, sidebars, value boxes, and the optional Shiny server mode.
`r-shiny-dashboards`	Governs how to build and fix Shiny and bs4Dash dashboards in R: file layout, global setup, ui and server split, reactivity, value boxes, tabs, charts and static assets.
`r-sql-bridge`	Governs connecting R to a SQL database and handing data on to Power BI: DBI connections, safe credentials, reading and writing tables, parameterised queries, and choosing SQLite or PostgreSQL for teaching.
`r-stats-foundations`	Governs the statistics behind dashboards in R: mean, median, mode, variance, standard deviation, skewness, correlation, hypothesis tests and simple linear regression, and how to explain a result in plain words.

🗺️ How they fit together

flowchart TD
    R["⚡ r-datadash<br/>routes and enforces the shared habits"]
    R --> A["📥 r-data-prep<br/>load, clean, API, scrape"]
    R --> W["🔧 r-dplyr-wrangling<br/>select, filter, recode, summarise"]
    R --> B["🖥️ r-shiny-dashboards / r-quarto-dashboards<br/>build the dashboard"]
    R --> C["🎨 r-dashboard-design<br/>chart, layout, speed"]

Usually: data prep, then dplyr wrangling, then statistics (r-stats-foundations), then a dashboard tool, then design. r-sql-bridge and powerbi-model-and-dax join when a database or Power BI is involved.

📦 Install

Tip

Install the router skill plus every sibling skill it links to; routers reference siblings by relative path.

Claude Code plugin (installs the skills and any agent profiles together):

/plugin marketplace add KinwiseNZ-DevOps/r-datadash
/plugin install r-datadash@r-datadash-marketplace

ChatGPT desktop plugin (local, skills and bundled hooks):

This repo has a portable plugin.json manifest and a repo marketplace at .agents/plugins/marketplace.json. Open this repo as a trusted project and restart ChatGPT desktop, then install R DataDash from the Plugins Directory. Review and trust bundled hook scripts before they run.

Or copy or symlink the skills/ subfolders you want into your agent's skills directory:

Agent	Where skills live
Claude Code	`~/.claude/skills/` or a project's `.claude/skills/`
Codex · Cursor · Copilot · OpenCode · Windsurf	the agent's own SKILL.md discovery path

To install supplied Claude Code, GitHub Copilot or Codex profiles into a project, run python scripts/install_agents.py --host claude-code --target PATH. Each repo supplies one main workflow agent and may supply one helper per host. Other hosts receive the skills only. If no profile files are supplied for that host, it makes no changes.

🚀 Usage

Tip

You never need to memorise skill names. Just describe the problem in plain words; the router picks the right skill automatically. But if you want short, reliable phrases that always work, use these:

The flow (this is all most people need):

1. "Build me a Shiny dashboard from this CSV"     → Routes to the right skill and checks the result
2. "Explain what this test result means"    → Routes to the right skill and checks the result
3. "Review this dashboard for clarity"     → Routes to the right skill and checks the result

Short phrases that trigger each skill:

Just say…	What you get	Skill used
`Why is my chart frozen?`	Finds the cause and fixes it with a check	r-shiny-dashboards

Note

Skills also trigger on their own when your request matches. In Claude Code you can also invoke one explicitly with /<skill-name>, but the plain phrases above are shorter and work across every agent.

Optional agent profiles

This section applies only when agent definitions were supplied during setup. One main agent handles the repo's workflows through named modes, and an optional helper handles one distinct task. Profiles live under resources/agents/<host>/. Other hosts receive the skills only. If no agents were supplied, remove this section and let the skills run directly.

✅ Validate

python scripts/skills_tool.py check

Checks: frontmatter, name/folder match, description length and trigger, body under 500 lines, every relative link resolves (including README.md and AGENTS.md), agent profile naming with no more than two profiles per host and exactly one -workflow main agent, agent skills: entries that exist and no skills/<name>/SKILL.md paths in agent bodies, plugin manifests (.claude-plugin/plugin.json and marketplace.json: required fields, licence matches LICENSE, agents lists every Claude Code profile, no top-level agents/ folder), at least 3 eval cases per skill, catalogue freshness, no project-specific terms from reference-content/strip-terms.txt, and no em or en dashes in file names or in any text outside reference-content/. After the starter skill is deleted it also rejects leftover placeholders and setup-only paths that are tracked by Git or not ignored. Stdlib only, no dependencies.

🗂️ Layout

Repository layout

skills/<name>/SKILL.md      one folder per skill (+ references/ where needed)
.claude-plugin/             plugin.json and marketplace.json (Claude Code plugin)
evals/cases.jsonl           3+ behavioural cases per skill
resources/agents/             optional host profiles copied by installer
scripts/install_agents.py     copy optional agent profiles into a project
scripts/skills_tool.py      validate, regenerate catalogue (stdlib only)
.github/workflows/          CI runs `skills_tool.py check` (free on public repos)
AGENTS.md                   agent-facing rules for this repo
SETUP.md                    local checklist; ignored and kept off GitHub
reference-content/          private source material; ignored and kept off GitHub
templates/                  local skill scaffolding; ignored and kept off GitHub

📌 Status and limits

Note

Draft as of 18 October 2026: the skills are untested against live classroom use, and no skill covers Python or Tableau.

Power BI and PostgreSQL guidance is condensed from the MIT-licensed awesome-copilot collection.

Licensed under MIT (see LICENSE).

⚡ Built on the Agent Skills open format · grounded in Shiny, Quarto and Microsoft Learn