vizier

v0.3.1

Chart-form selection and critique grounded in reader questions, honest comparison, and documented patterns.

CodexClaude Code2 Skills1 MCP serverstdio

By Marc LavalleeLicense: MIT0 GitHub starsUpdated last month

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 3 skill or MCP entries
Source updated: Sep 8, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install vizier for Codex and Claude Code

Installs for the current user

codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add vizier@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/lavallee/vizier

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

vizier/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/chart-critique/SKILL.md
├── skills/chart-design/SKILL.md
└── .mcp.json

Included Skills2

chart-critiqueskills/chart-critique/SKILL.md

Judge a chart that already exists. Invoke FIRST — before any other charting or visualization skill — when asked to review, critique, audit, assess, or improve a chart, graph, plot, figure, or dashboard, whether it's a source file, a screenshot, or a published graphic, and when asked whether a chart is misleading or whether it's the right chart. Checks the artifact structurally with no keys, answers the form's documented reading checklist against it, and adds corpus-backed judgment with prior-art citation when an LLM key is available.

chart-designskills/chart-design/SKILL.md

ALWAYS use this before creating, designing, choosing, or recommending ANY chart, graph, plot, figure, or dashboard — in any library or medium (d3, Vega, matplotlib, plotly, Recharts, Observable, hand-written SVG), and whenever someone asks what chart to use or how to show some data. Use it even when another visualization or design skill is available — this one runs FIRST and decides *what* to build, then hands off. It picks the form from the reader's question against 43 documented chart forms and their when-not-to-use lists, runs the honesty checks a newsroom applies before publishing (fair comparison, denominator, counter-reading, benchmark), and names the anti-patterns for the form you land on. Skipping it means deciding the chart from habit.

MCP servers1

vizierstdio

command: ${CLAUDE_PLUGIN_ROOT}/bin/vizier-mcp

Plugin manifests2

.codex-plugin/plugin.json

{
  "name": "vizier",
  "version": "0.3.1",
  "description": "Chart-form selection and critique grounded in reader questions, honest comparison, and documented patterns.",
  "author": {
    "name": "Marc Lavallee"
  },
  "homepage": "https://lavallee.github.io/vizier/",
  "repository": "https://github.com/lavallee/vizier",
  "license": "MIT",
  "keywords": [
    "dataviz",
    "charts",
    "data-visualization",
    "journalism",
    "critique",
    "accessibility",
    "codex"
  ],
  "skills": "./skills/",
  "mcpServers": "./.mcp.json",
  "interface": {
    "displayName": "vizier — chart judgment",
    "shortDescription": "Choose and critique charts with evidence",
    "longDescription": "Choose chart forms from the reader's question, run newsroom-style honesty checks, and critique finished graphics against a documented pattern library.",
    "developerName": "Marc Lavallee",
    "category": "Productivity",
    "capabilities": [
      "Interactive",
      "Read"
    ],
    "websiteURL": "https://lavallee.github.io/vizier/",
    "defaultPrompt": [
      "Use Vizier to choose a chart for this question.",
      "Use Vizier to critique this chart for misleading choices.",
      "Use Vizier to check this chart's comparison and denominator."
    ]
  }
}

.claude-plugin/plugin.json

{
  "name": "vizier",
  "displayName": "vizier — chart judgment",
  "version": "0.3.1",
  "description": "Steers agents toward good data visualization: pick the chart form from the reader's question rather than from habit, answer the honesty checks a newsroom would ask, and critique a finished chart against 43 documented forms and a corpus of critical writing.",
  "author": {
    "name": "Marc Lavallee"
  },
  "homepage": "https://lavallee.github.io/vizier/",
  "repository": "https://github.com/lavallee/vizier",
  "license": "MIT",
  "keywords": [
    "dataviz",
    "charts",
    "data-visualization",
    "journalism",
    "critique",
    "accessibility"
  ]
}

Browse the “dataviz” tag →

html-report

by Jaison Erick

Turn finished analysis results into a self-contained interactive HTML report: charts, cohort heatmaps, sortable tables and stat tiles, all inline in one file that opens by double-click with no network. Carries no brand of its own — it derives a theme from a brand color, or lifts one verbatim out of a report it built earlier.

CodexClaude CodeAgent Plugins1 Skill

1Updated last month

splash

by Remy Dumas

Splash: Visual journalism for every newsroom — a skill pack a newsroom installs and drives from its own AI assistant. Entry point: the splash skill.

Claude Code16 Skills

0Updated 4 weeks ago

ui-craft

by TheMizeGuy

Consolidated UI engineering team plugin: design, review, improvement and performance optimization for any UI surface (web, iOS, Android, desktop), with deep TypeScript/React/Tailwind v4 coverage plus Apple and Android review overlays. Ten specialists (architect, visual reviewer, anti-slop auditor, accessibility, motion, responsive, perf engineer, TypeScript engineer, verifier, team lead), each dispatched on the model the session chooses. Four user-invoked skills: design-ui (new UI from scratch), review-ui (adaptive specialist review with delta reporting against a review ledger), improve-ui (full team pass plus prioritized fix plan), optimize-ui (Core Web Vitals audit). Backed by a fully self-contained reference library: 60 files across 12 domains covering the substance floor (what a surface must have, measured), copy placement and volume, app shells and content layout, fluid and intrinsic sizing, breakpoints versus container queries, zoom and adaptive postures, task flows and journeys, forms and error recovery, navigation and information architecture, states and feedback, WCAG 2.2, OKLCH and APCA color, fluid typography, motion, Tailwind v4, shadcn, component and state architecture, Core Web Vitals, TypeScript 6/7 typing with the TS7 type gate, chart palettes, density and economy, and a 150-plus-tell anti-AI catalogue. Produces severity-tagged findings (CRITICAL/HIGH/MEDIUM/LOW/TASTE) with evidence citations, confidence classes and concrete remediation, against one canonical finding template. Ships a labeled regression corpus (40 fixtures, thirteen of them clean controls) with a recall- and precision-gated scoring harness, a deterministic tell scanner with its own corpus selftest, a label contract against the catalogue, a dogfood gate and a reference-integrity check, a CI gate producing GREEN/YELLOW/RED verdict artifacts with a 38-case selftest, and a review ledger for run-over-run delta reports. Read-only by default; the orchestrator applies findings only on explicit user approval.

Claude Code3 Skills

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[vizier on Agent Plugins Marketplace](https://pluginsmp.com/plugins/vizier)