Agent skill

Data Viz Deck

by thatrebeccarae in thatrebeccarae/claude-marketing

Transform audit data, performance reports, and structured analyses into polished visual deliverables.

MITAuto-check passedDocuments & Office

Install Data Viz Deck

skills CLI
$ npx skills add thatrebeccarae/claude-marketing --skill data-viz-deck -a claude-code

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

GitHub CLI
$ gh skill install thatrebeccarae/claude-marketing data-viz-deck --agent claude-code

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

Manual copy
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/data-viz-deck .claude/skills/data-viz-deck && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

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

Facts

Skill name
data-viz-deck
GitHub stars
162
Token cost
~1.8k tokens
SKILL.md length
588 words
Files
4
Skills in repo
55
Repo updated
First seen
Licence
MIT

At a glance

Transform audit data, performance reports, and structured analyses into polished visual deliverables.

  • Works in 7 steps: PPTX Deck (Primary) → Interactive HTML Dashboard → Visual Markdown Report → …
  • The user has analysis data and needs a visual deliverable
  • SKILL.md covers Install, When to Use This Skill, Output Formats and Workflow, plus 1 more section
  • Calls git and pip

What it does

Data Viz Deck is an agent skill from thatrebeccarae/claude-marketing. Transform audit data, performance reports, and structured analyses into polished visual deliverables. Generates presentation decks (PPTX), interactive HTML dashboards, or styled markdown reports with charts. Includes a customizable design system with forest green accent and warm cream backgrounds. Use when the user has analysis data and needs a visual deliverable.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `EXAMPLES.md` and `REFERENCE.md`).

It sits in Documents & Office, covering PowerPoint presentations, Data visualization and HTML artifacts. It works with Microsoft PowerPoint and pandas. The repository describes itself as: A full marketing department for Claude Code. Skill packs for Klaviyo, Shopify, GA4, Looker Studio, paid media, and more. Audit, optimize, and report using natural language. The licence is MIT.

When your agent uses it

  • The user has analysis data and needs a visual deliverable
  • Tasks that involve PowerPoint presentations
  • Tasks that involve Data visualization

Example prompts

  • “/data-viz-deck”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. PPTX Deck (Primary)
  2. Interactive HTML Dashboard
  3. Visual Markdown Report
  4. Identify the Data Source
  5. Select Chart Types
  6. Apply the Design System
  7. Generate the Deliverable

What it can do on your machine

Read from SKILL.md and the folder at commit a8a63ec. 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:

    • git
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git and pip, which can reach the network depending on how they are called.

    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

Data Viz Deck loads about 1.8k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 588 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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

The full file from thatrebeccarae/claude-marketing at commit a8a63ec, republished under its MIT licence (© thatrebeccarae). 588 words, ~1,837 tokens.

Download SKILL.mdSave it as .claude/skills/data-viz-deck/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
data-viz-deck
description
Transform audit data, performance reports, and structured analyses into polished visual deliverables. Generates presentation decks (PPTX), interactive HTML dashboards, or styled markdown reports with charts. Includes a customizable design system with forest green accent and warm cream backgrounds. Use when the user has analysis data and needs a visual deliverable.
license
MIT
origin
custom
author
Rebecca Rae Barton
author_url
https://github.com/thatrebeccarae
metadata.version
1.0.0
metadata.category
reporting
metadata.domain
data-visualization
metadata.updated
2026-03-18
metadata.tested
2026-03-18
metadata.tested_with
Claude Code v2.1

Data Visualization & Deck Builder

Transform structured data and analysis into polished visual deliverables: presentation decks, interactive dashboards, and visual reports.

Install

bash
git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/data-viz-deck ~/.claude/skills/

When to Use This Skill

  • User has completed an audit or analysis and wants a visual deliverable
  • User says "make a deck," "create a presentation," "build a dashboard," "visualize this"
  • User wants to turn a markdown report into client-ready slides
  • User needs charts, tables, or visual summaries from performance data

Output Formats

1. PPTX Deck (Primary)

Native PowerPoint with editable charts, styled tables, and professional layouts. Best for client handoffs and presentations.

Requires: python-pptx (installed), pandas (installed)

2. Interactive HTML Dashboard

Single-file HTML with plotly.js charts (loaded via CDN), filterable tables, and responsive layout. Best for sharing interactive reports.

Requires: jinja2 (installed), pandas (installed). Plotly.js loaded via CDN at runtime.

3. Visual Markdown Report

Enhanced markdown with embedded chart images (requires matplotlib: pip install matplotlib). Best for vault reports and documentation.

Workflow

Step 1: Identify the Data Source

Read the source file (audit markdown, CSV, JSON, or database query results). Parse the key metrics, tables, and findings into a pandas DataFrame or structured dict.

Step 2: Select Chart Types
Data PatternChart TypeWhen to Use
Categories with valuesBar chart (horizontal)Revenue by category
Categories + benchmarkBar chart with reference linePerformance vs benchmark
Parts of a wholeDoughnut/Pie chartRevenue concentration, channel mix
Values over timeLine chartTrend data, period-over-period
Two variablesScatter plotCorrelation analysis
Performance scoringHeatmap tableColor-coded metrics (green/amber/red)
Before/after or gapsWaterfall chartRevenue opportunity sizing
Ranked itemsHorizontal barTop 10 sorted
FunnelsFunnel chartDelivered > opened > clicked > converted
Status overviewScorecard/KPI tilesExecutive summary metrics
Step 3: Apply the Design System

All deliverables use a configurable design system. Override the color tokens and font choices to match your brand.

Color Palette
python
COLORS = {
    # Brand accent -- change to your brand color
    "accent":      "#3D7A5C",  # Forest green
    "accent_light":"#6AB88A",  # Light green

    # Chart series (ordered for visual distinction)
    "series": ["#3D7A5C", "#6AB88A", "#8B7EC8", "#D4845A", "#C9A84C", "#C75B6F", "#93C9A8", "#8B949E"],

    # Semantic
    "good":        "#2E8B57",  # Green -- above benchmark
    "warning":     "#D97706",  # Amber -- watch
    "critical":    "#C0392B",  # Red -- action needed
    "neutral":     "#8B949E",  # Slate -- no judgment

    # Dark mode (title slides, section dividers)
    "bg_deep":     "#141414",
    "bg_surface":  "#1E1E1E",
    "text_bright": "#F0F3F6",
    "text_secondary_dark": "#9CA3AF",

    # Light mode (content slides -- the default)
    "bg_light":    "#FAF7F2",  # Warm cream, NOT white
    "bg_surface_light": "#F2EDE6",
    "text_primary":"#0F0E0E",
    "text_secondary": "#57606A",
    "text_muted":  "#8B949E",
}

Color rules:

  • Light mode (#FAF7F2 warm cream) is default for all content slides. NOT white.
  • Dark mode (#141414) only for: title slides, section dividers, closing slides.
  • Accent color used sparingly: top-performing bars, key metrics, accent callouts.
  • Semantic colors (green/amber/red) only for status indicators, never decoration.
Show full SKILL.md (241 more words)Show less
Typography (PPTX)
python
FONTS = {
    "title":    "Switzer",        # Slide titles -- Light (300), 28-36pt, NOT bold
    "subtitle": "Switzer",        # Subtitles -- Regular (400), 18-22pt
    "body":     "Switzer",        # Body text -- Regular (400), 12-14pt
    "data":     "Cartograph CF",  # Numbers, tables -- Regular/Bold, 11-12pt
    "kpi":      "Cartograph CF",  # KPI big numbers -- Bold (700), 44-60pt
    "label":    "Cartograph CF",  # ALL CAPS labels -- Regular, 9-10pt, +tracking
}
# Fallbacks: Switzer -> Inter -> system-ui | Cartograph CF -> Consolas -> monospace

Critical typography rules:

  1. Headlines use Light weight, NOT Bold. Light at large sizes = confident, premium.
  2. Monospace font for ALL numeric/data content. KPIs, table numbers, labels, footers.
  3. Negative tracking on headlines. -0.03em to -0.04em.
  4. Positive tracking on ALL CAPS labels. +0.08em to +0.1em.
Slide Layouts

Every deck follows this structure:

1. Title Slide         -- Report name, date (dark mode)
2. Executive Summary   -- 3-5 KPI tiles + key findings bullets
3. Scorecard           -- Color-coded performance overview table
4. Deep Dive slides    -- One per major finding (chart + insight + recommendation)
5. Opportunity Sizing  -- Waterfall or bar chart of revenue opportunities
6. Recommendations     -- Prioritized table (Quick Wins / Strategic / Maintenance)
7. Appendix            -- Full data tables
Slide Dimensions (python-pptx)
Width:  13.333"
Height: 7.5"
Aspect: 16:9
Step 4: Generate the Deliverable

Follow the code patterns in REFERENCE.md for the chosen output format.

Key Principles

  1. One insight per slide. Never cram multiple findings onto one slide. Each deep-dive slide has: chart (left 60%), insight + recommendation (right 40%).

  2. Lead with the number. Every slide title should contain the key metric: "Post-Purchase RPR at $0.07 -- 14x Below Benchmark" not "Post-Purchase Flow Analysis."

  3. Benchmark everything. Never show a metric without context. Show the benchmark, the gap, and what closing the gap is worth.

  4. Color = meaning. Green means good/above benchmark. Amber means watch. Red means action needed. Never use color decoratively in data slides.

  5. Simplify chart data. Max 6-8 items per chart. Aggregate the tail into "Other."

  6. Executive summary is the deck. If someone only reads slide 2, they should understand the full story.

  7. Never estimate when actuals exist. If the data has exact values, compute precise totals.

  8. No white backgrounds. Always warm cream #FAF7F2 for light content.

  9. No bold headlines. Light weight for all hero/section titles.

For complete code templates and reference, see REFERENCE.md.

© thatrebeccarae, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files in skills/data-viz-deck of thatrebeccarae/claude-marketing.

  • SKILL.md
  • EXAMPLES.md
  • LICENSE
  • REFERENCE.md

Open the folder on GitHubat commit a8a63ec

Compare with similar skills

Data Viz Deck 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.

Data Viz Deck compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Data Viz Deck this skillthatrebeccarae/claude-marketing162—~1.8kAutomated safety check: PassMIT
Ky Markdown RebuilderKyrieCheungYep/ky-markdown-rebuilder117—~5.7kAutomated safety check: PassNone
PPT as CodeRussell-cell/PPT-as-code191—~11kAutomated safety check: PassMIT
Markdown HTML Orchestratoralirezarezvani/claude-skills28k—~2.7kAutomated safety check: PassMIT
Report With HTMLdaymade/claude-code-skills1.4k—~11kAutomated safety check: PassMIT
Baoyu DesignDejavuMoe/Smoji1141 repos~2.7kAutomated safety check: PassMIT

Similar skills

  • Ky Markdown Rebuilder

    KyrieCheungYep/ky-markdown-rebuilder

    Rebuild visual documents into reliable Markdown by combining text extraction with page or screenshot alignment.

    117 GitHub stars~5.7k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed
  • PPT as Code

    Russell-cell/PPT-as-code

    Plans and builds HTML-based web presentations through staged quick, basic or advanced workflows, with optional visualization planning, motion, a workbench and PPTX export handoff.

    191 GitHub stars~11k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Markdown HTML Orchestrator

    alirezarezvani/claude-skills

    A skill your agent uses when a user wants to convert any markdown file in their Claude project into a single-file, lightly-interactive HTML — long-form documents (specs, plans, RFCs, reports…

    28k GitHub stars~2.7k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Report With HTML

    daymade/claude-code-skills

    Produces the reader-facing HTML artifact — report, dashboard, architecture view, data browser, or review workbench — evidence-backed, browser-verified.

    1.4k GitHub stars~11k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Baoyu Design

    DejavuMoe/Smoji

    Create polished design artifacts as self-contained HTML: UI mockups, interactive prototypes, wireframes, landing pages, dashboards, app screens, mobile apps, slide decks (a.k.a.

    114 GitHub starsUsed in 1 repo~2.7k tokens
    Frontend & DesignAuto-check passed
  • Superloopy Slides

    beefiker/superloopy

    Creates zero-dependency, animation-rich HTML slide decks that run in the browser, with style presets, PowerPoint conversion and PDF export, proven by a real-browser render.

    111 GitHub starsUsed in 1 repo~8.8k tokens
    Documents & OfficeAuto-check passed

More from thatrebeccarae/claude-marketing

All 55 skills in this repo
  • Google Analytics

    thatrebeccarae/claude-marketing

    Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements.

    162 GitHub starsUsed in 4 repos~1.3k tokens
    Auto-check: notes
  • Content Creator

    thatrebeccarae/claude-marketing

    Comprehensive content marketing toolkit with brand voice analysis, SEO optimization scripts, content frameworks, social media strategy, and content calendar planning.

    162 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Klaviyo Analyst

    thatrebeccarae/claude-marketing

    Klaviyo marketing operations and analyst expertise. An agent skill from thatrebeccarae/claude-marketing.

    162 GitHub stars~5k tokensUpdated 4 mo ago
    Auto-check: notes
  • Klaviyo Developer

    thatrebeccarae/claude-marketing

    Klaviyo API and developer integration expertise. An agent skill from thatrebeccarae/claude-marketing.

    162 GitHub stars~4.9k tokensUpdated 4 mo ago
    Auto-check: notes
  • Looker Studio

    thatrebeccarae/claude-marketing

    Looker Studio (formerly Google Data Studio) expertise. An agent skill from thatrebeccarae/claude-marketing.

    162 GitHub stars~3.6k tokensUpdated 4 mo ago
    Auto-check: notes
  • Shopify

    thatrebeccarae/claude-marketing

    Shopify e-commerce platform marketing expertise. An agent skill from thatrebeccarae/claude-marketing.

    162 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check: notes

Questions about Data Viz Deck

What does Data Viz Deck do?

Transform audit data, performance reports, and structured analyses into polished visual deliverables. Data Viz Deck is an agent skill from thatrebeccarae/claude-marketing. Transform audit data, performance reports, and structured analyses into polished visual deliverables.

When should I use Data Viz Deck?

Data Viz Deck fits situations like: the user has analysis data and needs a visual deliverable; tasks that involve PowerPoint presentations; tasks that involve Data visualization.

How do I install Data Viz Deck in Claude Code?

Run `npx skills add thatrebeccarae/claude-marketing --skill data-viz-deck -a claude-code`. Or copy the skill folder (skills/data-viz-deck in thatrebeccarae/claude-marketing) into .claude/skills/data-viz-deck in your project. Claude Code loads it when a task matches its description.

How do I install Data Viz Deck in Codex?

Run `npx skills add thatrebeccarae/claude-marketing --skill data-viz-deck -a codex`. Or copy the skill folder (skills/data-viz-deck in thatrebeccarae/claude-marketing) into .agents/skills/data-viz-deck in your project. Codex loads it when a task matches its description.

Can I use Data Viz Deck 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 thatrebeccarae/claude-marketing --skill data-viz-deck -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/data-viz-deck, .gemini/skills/data-viz-deck, .github/skills/data-viz-deck and .opencode/skills/data-viz-deck in your project.

What does Data Viz Deck need to run?

Going by SKILL.md and its folder, Data Viz Deck needs the command-line tools its instructions call (git and pip). Our summary lists: Python 3.

Does Data Viz Deck access the network?

SKILL.md contains no URLs. Its commands use git and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Data Viz Deck 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 Data Viz Deck use?

Data Viz Deck is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Data Viz Deck use?

About 1.8k tokens (SKILL.md is roughly 7.3k 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 Data Viz Deck?

Skills that share tags, products or a category with Data Viz Deck: Ky Markdown Rebuilder (KyrieCheungYep/ky-markdown-rebuilder, 117 stars), PPT as Code (Russell-cell/PPT-as-code, 191 stars), Markdown HTML Orchestrator (alirezarezvani/claude-skills, 28k stars) and Report With HTML (daymade/claude-code-skills, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Data Viz Deck?

thatrebeccarae (a GitHub user) maintains it in thatrebeccarae/claude-marketing, which has 162 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on May 14, 2026.

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