Official agent skill

Visual Design

by aws-samples in aws-samples/sample-strands-agent-with-agentcore

Use this skill any time the user needs a visual output as an image or PDF — charts, diagrams, posters, infographics, abstract artwork, or any visual design.

OfficialMITAuto-check passedMedia & Creative

Install Visual Design

skills CLI
$ npx skills add aws-samples/sample-strands-agent-with-agentcore --skill visual-design -a claude-code

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

GitHub CLI
$ gh skill install aws-samples/sample-strands-agent-with-agentcore visual-design --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/aws-samples/sample-strands-agent-with-agentcore.git skills-src && mkdir -p .claude/skills && cp -r skills-src/chatbot-app/agentcore/skills/visual-design .claude/skills/visual-design && 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
visual-design
GitHub stars
194
Token cost
~1.5k tokens
SKILL.md length
612 words
Files
4
Skills in repo
24
Repo updated
First seen
Licence
MIT

At a glance

Use this skill any time the user needs a visual output as an image or PDF — charts, diagrams, posters, infographics, abstract artwork, or any visual design.

  • Works in 5 steps: Identify data structure and choose… → Select color palette (see Design Ideas… → Preserve requested labels, units,… → …
  • : data visualization requests
  • SKILL.md covers Quick Reference, Available Tools, Available Libraries and Design Workflow, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Visual Design is an agent skill from aws-samples/sample-strands-agent-with-agentcore, published by the product's own GitHub organization. Use this skill any time the user needs a visual output as an image or PDF — charts, diagrams, posters, infographics, abstract artwork, or any visual design. Trigger for: data visualization requests, poster/flyer creation, infographic design, abstract or artistic visuals, architecture/flow diagrams, or any request mentioning 'chart', 'graph', 'poster', 'infographic', 'design', 'visual', or referencing .png/.pdf image output.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `canvas-design.md`, `diagram-design.md` and `library-reference.md`).

It sits in Media & Creative, covering UI design, Data visualization and Infographics. It works with Python and Matplotlib. The repository describes itself as: Reference architecture for agentic AI chatbots with Strands Agents and Amazon Bedrock AgentCore. The licence is MIT.

When your agent uses it

  • : data visualization requests
  • Poster/flyer creation
  • Infographic design
  • Artistic visuals

Example prompts

  • “poster”
  • “infographic”
  • “design”
  • “/visual-design”

Requirements

  • Python 3

Workflow steps

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

  1. Identify data structure and choose appropriate chart type
  2. Select color palette (see Design Ideas below)
  3. Preserve requested labels, units, colors, dimensions, and explicit axis limits in the code. Verify these against the generated output.
  4. Write code with plt.savefig(filename, dpi=300, bbox_inches='tight')
  5. Review the generated chart and confirm the saved file matches the requested format and filename

What it can do on your machine

Read from SKILL.md and the folder at commit 6dd9d13. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Visual Design loads about 1.5k tokens when it runs. Until then it costs about 110 tokens; SKILL.md has 612 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~110
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 aws-samples/sample-strands-agent-with-agentcore at commit 6dd9d13, republished under its MIT licence (© aws-samples). 612 words, ~1,459 tokens.

Download SKILL.mdSave it as .claude/skills/visual-design/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
visual-design
description
Use this skill any time the user needs a visual output as an image or PDF — charts, diagrams, posters, infographics, abstract artwork, or any visual design. Trigger for: data visualization requests, poster/flyer creation, infographic design, abstract or artistic visuals, architecture/flow diagrams, or any request mentioning 'chart', 'graph', 'poster', 'infographic', 'design', 'visual', or referencing .png/.pdf image output.

Visual Design

Quick Reference

TaskToolGuide
Data chart or graphgenerate_chartRead SKILL.md Design Ideas
Poster / infographic / artcreate_visual_designRead canvas-design.md
Architecture / flow diagramExcalidraw skillUse create_excalidraw_diagram for an editable in-app result. Use image generation only when a raster or print deliverable is requested.

Available Tools

generate_chart

Data visualization. Executes matplotlib/plotly code to produce chart PNGs.

  • python_code (str, required): Chart generation Python code
  • output_filename (str, required): .png filename
create_visual_design

Visual design creation: posters, infographics, artwork, diagrams. Uses reportlab, Pillow, svgwrite, or any available library.

  • python_code (str, required): Design generation Python code
  • output_filename (str, required): .png or .pdf filename

Available Libraries

PurposeLibrariesOutputNotes
Data chartsmatplotlib, plotly, bokehPNGBest for charts
PDF designreportlab, fpdfPDFFull control
Image designPillow + fonttoolsPNGBest for PNG designs
Vector graphicssvgwrite → svglib + renderPDFSVG → PDFSVG→PNG NOT supported (no renderPM)
Image processingWand (ImageMagick), opencv-pythonPNGCheck availability first

IMPORTANT: For PNG output, use Pillow or matplotlib. Do NOT use svgwrite→renderPM (rlPyCairo is unavailable).

Design Workflow

Data Charts (generate_chart)
  1. Identify data structure and choose appropriate chart type
  2. Select color palette (see Design Ideas below)
  3. Preserve requested labels, units, colors, dimensions, and explicit axis limits in the code. Verify these against the generated output.
  4. Write code with plt.savefig(filename, dpi=300, bbox_inches='tight')
  5. Review the generated chart and confirm the saved file matches the requested format and filename
Visual Design (create_visual_design)
  1. Establish design concept/philosophy (internally)
  2. Follow the process in canvas-design.md
  3. Select appropriate library and write code
  4. Save: reportlab canvas.save(), Pillow image.save(), matplotlib plt.savefig()
  5. Review output and refine

Design Ideas

Color Palettes
ThemePrimaryAccentBackground
Midnight Executive1E2761408EC60D1B2A
Forest & Moss2C5F2D97BC621A1A1A
Coral EnergyF96167F9E7952F3C7E
Ocean Gradient065A821B9AAA021B29
Charcoal Minimal36454FE8E8E81C1C1E
Cherry Bold990011FCF6F5150E11
Sage Calm84B59F69A2972D3A2D
Warm TerracottaB85042E7E8D12A1F1C
Typography

Prefer thin/light fonts. Minimize text in designs.

ElementSizeStyle
Main title48-72ptBold or Thin
Subtext14-18ptLight
Labels/captions8-12ptRegular, muted

Text-to-Canvas Balance (IMPORTANT):

  • Text size must be proportional to the overall canvas and surrounding design elements
  • Common mistake: text that is too small relative to the canvas, making it unreadable at normal viewing distance
  • Rule of thumb: if you need to zoom in to read it, it's too small
  • Titles should command attention — when in doubt, go larger
  • Labels/captions should be clearly legible, not decorative afterthoughts
  • Test: mentally shrink the output to 50% — all text should still be readable
Show full SKILL.md (195 more words)Show less
Spacing & Composition
  • Generous margins (minimum 10% of canvas)
  • Consistent spacing between elements
  • No overlapping; all elements within canvas bounds
  • Visual hierarchy: convey importance via size, color, position
Avoid
  • Elements flush to canvas edges (insufficient margins)
  • Overlapping elements
  • Too many colors (stick to 3-4)
  • Excessive text — visual elements are the focus
  • Default matplotlib styles without customization

Code Requirements

  • Code must save a file to disk
  • Use the exact output_filename provided
  • PNG: dpi=300 or higher recommended
  • PDF: A4 or Letter size recommended
  • For Korean text: configure appropriate fonts

QA

Assume there are problems and look for them.

  1. Review the generated image/PDF
  2. Check for overlapping elements, clipped text, insufficient margins
  3. Verify sufficient color contrast
  4. If issues found, fix the code and regenerate
  5. If a check fails, correct and verify it. Do not regenerate an already valid output solely to perform a fix cycle.

UI Guidance (from tools-config)

Tool Selection:

  • generate_chart: Data charts/graphs (matplotlib, plotly, bokeh) → PNG
  • create_visual_design: Posters, infographics, artwork, flow diagrams (reportlab, Pillow, svgwrite) → PNG or PDF

Code Requirements:

  • Charts: plt.savefig(filename, dpi=300, bbox_inches='tight')
  • PDF designs: canvas.save() (reportlab) or equivalent
  • Image designs: image.save(filename) (Pillow)
  • PNG: dpi=300+ recommended
  • PDF: A4 or Letter size recommended

© aws-samples, 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 chatbot-app/agentcore/skills/visual-design of aws-samples/sample-strands-agent-with-agentcore.

  • SKILL.md
  • canvas-design.md
  • diagram-design.md
  • library-reference.md

Open the folder on GitHubat commit 6dd9d13

Compare with similar skills

Visual Design 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.

Visual Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Visual Design this skillaws-samples/sample-strands-agent-with-agentcore194—~1.5kAutomated safety check: PassMIT
Microsim Generatordmccreary/ibook-skills105—~11kAutomated safety check: PassNone
Data Viz Rendererzebbern/claude-code-guide4.6k—~1.3kAutomated safety check: PassMIT
Apex Python Diagramsjonathan-vella/apex217—~2kAutomated safety check: PassMIT
Scientific Schematicsjimmc414/Kosmos594—~16kAutomated safety check: NotesNone
Alt Text DesignOwl-Listener/inclusive-design-skills103—~946Automated safety check: PassMIT

Similar skills

  • Microsim Generator

    dmccreary/ibook-skills

    Creates interactive educational MicroSims, routing to the best-matched generator - p5.js, Chart.js, Plotly, Mermaid, vis-network, timelines, maps, Venn, causal-loop/feedback-loop diagrams (CLD)…

    105 GitHub stars~11k tokensUpdated 2 days ago
    Data & AnalyticsAuto-check passed
  • Data Viz Renderer

    zebbern/claude-code-guide

    Generate self-contained HTML/SVG infographics from JSON data, including stat cards, bar charts, flow diagrams, and mixed dashboards.

    4.6k GitHub stars~1.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Apex Python Diagrams

    jonathan-vella/apex

    UTILITY SKILL — Python diagram generation for Azure architectures, WAF/cost/compliance charts, ERDs, swimlanes, timelines, and wireframes.

    217 GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Scientific Schematics

    jimmc414/Kosmos

    Create publication-quality scientific diagrams, flowcharts, and schematics using Python (graphviz, matplotlib, schemdraw, networkx).

    594 GitHub stars~16k tokensUpdated 3 days ago
    Data & AnalyticsAuto-check: notes
  • Alt Text Design

    Owl-Listener/inclusive-design-skills

    Write meaningful alternative text for images, charts, diagrams, and visual content.

    103 GitHub stars~946 tokensUpdated 3 mo ago
    Media & CreativeAuto-check passed
  • Charting

    oaustegard/claude-skills

    Select the right Python charting library (seaborn, matplotlib, graphviz) and produce publication-quality static visualizations.

    150 GitHub stars~1.5k tokensUpdated 5 days ago
    Data & AnalyticsAuto-check passed

More from aws-samples/sample-strands-agent-with-agentcore

All 24 skills in this repo
  • Doc Coauthoring

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Guide users through a structured workflow for co-authoring documentation.

    194 GitHub starsUsed in 39 repos~3.2k tokens
    Auto-check passed
  • Code Interpreter

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Test and prototype code in a sandboxed environment. An agent skill from aws-samples/sample-strands-agent-with-agentcore.

    194 GitHub stars~3.6k tokensUpdated yesterday
    Auto-check passed
  • Research Agent

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Deep research with structured reports and charts. An agent skill from aws-samples/sample-strands-agent-with-agentcore.

    194 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Workspace

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Read and write files in the shared session workspace. An agent skill from aws-samples/sample-strands-agent-with-agentcore.

    194 GitHub stars~721 tokensUpdated yesterday
    Auto-check passed
  • Code Agent

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Autonomous coding agent. An agent skill from aws-samples/sample-strands-agent-with-agentcore.

    194 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed
  • Delegate Work

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Delegate one independent, context-heavy task to an isolated asynchronous analyst or reviewer.

    194 GitHub stars~610 tokensUpdated yesterday
    Auto-check passed

Questions about Visual Design

What does Visual Design do?

Use this skill any time the user needs a visual output as an image or PDF — charts, diagrams, posters, infographics, abstract artwork, or any visual design. Visual Design is an agent skill from aws-samples/sample-strands-agent-with-agentcore, published by the product's own GitHub organization. Use this skill any time the user needs a visual output as an image or PDF — charts, diagrams, posters, infographics, abstract artwork, or any visual design.

When should I use Visual Design?

Visual Design fits situations like: : data visualization requests; poster/flyer creation; infographic design; artistic visuals.

How do I install Visual Design in Claude Code?

Run `npx skills add aws-samples/sample-strands-agent-with-agentcore --skill visual-design -a claude-code`. Or copy the skill folder (chatbot-app/agentcore/skills/visual-design in aws-samples/sample-strands-agent-with-agentcore) into .claude/skills/visual-design in your project. Claude Code loads it when a task matches its description.

How do I install Visual Design in Codex?

Run `npx skills add aws-samples/sample-strands-agent-with-agentcore --skill visual-design -a codex`. Or copy the skill folder (chatbot-app/agentcore/skills/visual-design in aws-samples/sample-strands-agent-with-agentcore) into .agents/skills/visual-design in your project. Codex loads it when a task matches its description.

Can I use Visual Design 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 aws-samples/sample-strands-agent-with-agentcore --skill visual-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/visual-design, .gemini/skills/visual-design, .github/skills/visual-design and .opencode/skills/visual-design in your project.

What does Visual Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Visual Design is instructions for the agent only. Our summary lists: Python 3.

Does Visual Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Visual Design 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 Visual Design use?

Visual Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Visual Design use?

About 1.5k tokens (SKILL.md is roughly 5.8k 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 Visual Design?

Skills that share tags, products or a category with Visual Design: Microsim Generator (dmccreary/ibook-skills, 105 stars), Data Viz Renderer (zebbern/claude-code-guide, 4.6k stars), Apex Python Diagrams (jonathan-vella/apex, 217 stars) and Scientific Schematics (jimmc414/Kosmos, 594 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Visual Design?

aws-samples (a GitHub organization, an official publisher) maintains it in aws-samples/sample-strands-agent-with-agentcore, which has 194 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 6, 2026.

Source: aws-samples/sample-strands-agent-with-agentcore on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.