Agent skill

Mviz

A chart & report builder for AI. An agent skill from matsonj/mviz.

No licenceAuto-check passedData & Analytics

Install Mviz

skills CLI

$ npx skills add matsonj/mviz --skill mviz -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install matsonj/mviz mviz --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "mviz" agent skill from https://github.com/matsonj/mviz/tree/main into .claude/skills/mviz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mviz", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add matsonj/mviz --skill mviz -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install matsonj/mviz mviz --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "mviz" agent skill from https://github.com/matsonj/mviz/tree/main into .agents/skills/mviz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mviz", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add matsonj/mviz --skill mviz -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install matsonj/mviz mviz --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "mviz" agent skill from https://github.com/matsonj/mviz/tree/main into .cursor/skills/mviz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mviz", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add matsonj/mviz --skill mviz -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install matsonj/mviz mviz --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "mviz" agent skill from https://github.com/matsonj/mviz/tree/main into .gemini/skills/mviz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mviz", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install matsonj/mviz mviz

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add matsonj/mviz --skill mviz -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "mviz" agent skill from https://github.com/matsonj/mviz/tree/main into .github/skills/mviz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mviz", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add matsonj/mviz --skill mviz -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install matsonj/mviz mviz --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "mviz" agent skill from https://github.com/matsonj/mviz/tree/main into .opencode/skills/mviz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mviz", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: mviz
GitHub stars: 226
Token cost: ~11k tokens
SKILL.md length: 3,621 words
Files: 10
Skills in repo: 1
Repo updated: May 28, 2026
First seen: Oct 7, 2026
Licence: None found

At a glance

A chart & report builder for AI. An agent skill from matsonj/mviz.

Works in 2 steps: A spec language — markdown with fenced… → A set of renderers that turn that spec…
The user asks to show
SKILL.md covers Setup, What This Skill Does, Picking a renderer and Visual Style (mdsinabox theme…, plus 8 more sections
Calls npx, duckdb and npm; reaches cdnjs.cloudflare.com and fonts.googleapis.com

What it does

Mviz is an agent skill from matsonj/mviz. A chart & report builder for AI. Use when the user asks to show, display, render, or visualize data as a chart (bar, line, pie, scatter, area, bubble, histogram, etc.), a table, KPI, big number, dashboard, report, sparkline, heatmap, sankey, funnel, calendar, waterfall, or any composed data visualization. Generates compact markdown specs that render either inline (via visualize:showwidget) or as standalone HTML files (via the mviz CLI).

Its SKILL.md is about 11k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files (for example `Best_practices.md`, `README.md` and `reference/chart-types.md`).

It sits in Data & Analytics, covering Data visualization, HTML artifacts and OKRs and executive reporting. It works with npm. The repository describes itself as: A chart & report builder designed for use by AI.

When your agent uses it

The user asks to show
Visualize data as a chart (bar
Any composed data visualization

Example prompts

“/mviz”

Requirements

Node.js

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

A spec language — markdown with fenced code blocks describing components (charts, KPIs, tables, notes, etc.). One markdown file (or a…
A set of renderers that turn that spec into HTML for different display contexts. Today there are two

What it can do on your machine

Read from SKILL.md and the folder at commit c65cd8a. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- npx
- duckdb
- npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- cdnjs.cloudflare.com
- fonts.googleapis.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mviz loads about 11k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 3,621 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~112
When it runs · the whole SKILL.md, loaded when a task matches: ~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 3,621 words (~10,907 tokens).

name: mviz

Outline of SKILL.md

mviz
Setup
What This Skill Does
Picking a renderer
Visual Style (mdsinabox theme — for the CLI renderer)
Renderer: mviz CLI (standalone HTML)
Single Chart (JSON)
Dashboard from Markdown
Dashboard from Folder
Iframe-embedded output (--embed)
16-Column Grid System
Side-by-Side Layout
Headings and Section Breaks
Default Sizes
Recommended Size Pairings
Example: Dense KPI Row
Example: Two Charts Side by Side
Supported Types
Table Formatting
Note Types
Specialized Chart Examples
Number Format Options
Auto-Detected Axis Formatting
Columnar Data Format
Axis Bounds (yMin/yMax)
Validation & Lint Rules
Lint Rules
Common Fixes
Troubleshooting
Warning Messages

Read the full SKILL.md on GitHub

Files

SKILL.md and 9 other files in the repository root of matsonj/mviz.

SKILL.md
Best_practices.md
DarkMode.png
LightMode.png
README.md
Sample Report.pdf
The Bo Nix Injury_ Quantifying the Damage.pdf
reference/chart-types.md
schema/mviz.schema.json
schema/mviz.v1.schema.json

Open the folder on GitHubat commit c65cd8a

Compare with similar skills

Mviz next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Mviz compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Mviz this skillmatsonj/mviz	226	—	~11k	Automated safety check: Pass	None	4 mo ago
Preact Developeroaustegard/claude-skills	150	—	~4.6k	Automated safety check: Pass	MIT	today
Data Viz Deckthatrebeccarae/claude-marketing	162	—	~1.8k	Automated safety check: Pass	MIT	4 mo ago
Creating Dashboardsancoleman/ai-design-components	526	—	~3.5k	Automated safety check: Pass	MIT	10 mo ago
D3 Visualizationbenchflow-ai/skillsbench	1.8k	—	~1.5k	Automated safety check: Pass	Apache-2.0	2 mo ago
SVG DashboardSCStelz/security-investigator	249	—	~5.7k	Automated safety check: Pass	MIT	yesterday

Similar skills

Preact Developer
oaustegard/claude-skills
Guides building standards-based Preact apps with native-first choices, HTM syntax, import maps and vendored ESM, from single-file demos to larger builds.
150 GitHub stars~4.6k tokensUpdated today
Frontend & DesignAuto-check passed
Data Viz Deck
thatrebeccarae/claude-marketing
Transform audit data, performance reports, and structured analyses into polished visual deliverables.
162 GitHub stars~1.8k tokensUpdated 4 mo ago
Documents & OfficeAuto-check passed
Creating Dashboards
ancoleman/ai-design-components
Creates comprehensive dashboard and analytics interfaces that combine data visualization, KPI cards, real-time updates, and interactive layouts.
526 GitHub stars~3.5k tokensUpdated 10 mo ago
Data & AnalyticsAuto-check passed
D3 Visualization
benchflow-ai/skillsbench
Build deterministic, verifiable data visualizations with D3.js (v6).
1.8k GitHub stars~1.5k tokensUpdated 2 mo ago
Data & AnalyticsAuto-check passed
SVG Dashboard
SCStelz/security-investigator
A skill your agent uses when asked to generate SVG data visualization dashboards from investigation data or skill reports.
249 GitHub stars~5.7k tokensUpdated yesterday
Data & AnalyticsAuto-check passed
Tufte
aref-vc/tufte-claude-skill
Apply Edward Tufte's principles to any data visualization, chart, dashboard, or infographic.
307 GitHub stars~1.3k tokensUpdated 3 mo ago
Data & AnalyticsAuto-check passed

Works with

Questions about Mviz

What does Mviz do?

A chart & report builder for AI. An agent skill from matsonj/mviz. Mviz is an agent skill from matsonj/mviz. A chart & report builder for AI.

When should I use Mviz?

Mviz fits situations like: the user asks to show; visualize data as a chart (bar; any composed data visualization.

How do I install Mviz in Claude Code?

Run `npx skills add matsonj/mviz --skill mviz -a claude-code`. Or copy the skill folder (the matsonj/mviz repository) into .claude/skills/mviz in your project. Claude Code loads it when a task matches its description.

How do I install Mviz in Codex?

Run `npx skills add matsonj/mviz --skill mviz -a codex`. Or copy the skill folder (the matsonj/mviz repository) into .agents/skills/mviz in your project. Codex loads it when a task matches its description.

Can I use Mviz in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add matsonj/mviz --skill mviz -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mviz, .gemini/skills/mviz, .github/skills/mviz and .opencode/skills/mviz in your project.

What does Mviz need to run?

Going by SKILL.md and its folder, Mviz needs the command-line tools its instructions call (npx, duckdb and npm). Our summary lists: Node.js.

Does Mviz access the network?

SKILL.md names 2 domains. In commands or code: cdnjs.cloudflare.com and fonts.googleapis.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Mviz safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Mviz use?

No licence was found for Mviz or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Mviz use?

About 11k tokens (SKILL.md is roughly 44k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mviz?

Skills that share tags, products or a category with Mviz: Preact Developer (oaustegard/claude-skills, 150 stars), Data Viz Deck (thatrebeccarae/claude-marketing, 162 stars), Creating Dashboards (ancoleman/ai-design-components, 526 stars) and D3 Visualization (benchflow-ai/skillsbench, 1.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mviz?

matsonj (a GitHub user) maintains it in matsonj/mviz, which has 226 GitHub stars. The repository was last updated on May 28, 2026.

Source: matsonj/mviz on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Mviz

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Compare with similar skills

Similar skills

Preact Developer

Data Viz Deck

Creating Dashboards

D3 Visualization

SVG Dashboard

Tufte

Related

Questions about Mviz