A tool for turning information from a knowledge base into a single-page visual summary, such as an infographic or poster. It creates an HTML page and a PNG image.

Use it to make visual note cards, knowledge summaries, infographics, and presentation or social-media images.

It helps readers understand and share dense notes without assembling the layout by hand.

visual-card — Skill for Claude Code by NatsuFox

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add NatsuFox/Tapestry --skill visual-card

Clone the repo

git clone --depth 1 https://github.com/NatsuFox/Tapestry

Made for: Claude Code.

Or install Tapestry, the plugin that ships this one along with the rest of its 9 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/natsufox/tapestry/visual-card.svg)](https://agentmods.dev/skills/natsufox/tapestry/visual-card)

Your own site

<a href="https://agentmods.dev/skills/natsufox/tapestry/visual-card"><img src="https://agentmods.dev/badge/skills/natsufox/tapestry/visual-card.svg" alt="Measured on agentmods" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,319 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.02319
Opus 5	$0.00030	$0.01159
Sonnet 5	$0.00012	$0.00464
Haiku 4.5	$0.00006	$0.00232

Measured 8d ago against content hash e37d78149e22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

visual-card scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (_scripts/generate_card_from_synthesis.py, _scripts/generate_card_legacy.py, _scripts/generate_card.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/tapestry/visual-card/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tapestry Visual Card

Generate professional visual note cards from knowledge base content: $ARGUMENTS

When to use this skill

Use this skill when:

A user wants to create a visual note card or infographic from KB content
The user asks to "visualize", "create a card", "make an infographic", or "generate a visual summary"
The user mentions 视觉笔记, 知识卡片, 信息图, or one-pager summary
You need to present knowledge base content in a shareable, poster-style format
The user wants to export KB content for social media or presentations

Purpose

This skill transforms structured knowledge base content into beautiful, information-dense visual cards following an editorial magazine aesthetic. It produces:

A self-contained HTML file with embedded styles and export functionality
A high-quality PNG image (via Playwright rendering)

The cards follow a fixed layout structure optimized for readability and social sharing.

Workflow

Architecture: Agent-Driven Content Synthesis

This skill uses an Agent-driven approach where the Agent reads the template specification and autonomously decides how to map source content to template blocks.

Key principle: The template structure is fixed (7 display blocks), but content mapping is intelligent and adaptive.

Step 1: Identify the Source Content

Resolve the target from the argument:

If a specific chapter path is provided (e.g., "ai-and-development-tools/ai-agent-architecture.md"), use that chapter
If a topic is provided (e.g., "ai-and-development-tools"), offer to generate cards for its chapters
If no argument, list available topics and ask the user to choose

# List available topics
ls -d data/books/*/

Step 2: Run the Context Preparation Script

python visual-card/_scripts/generate_card.py --chapter "<topic>/<chapter.md>"

This prints a JSON object with three keys:

source.content: the raw chapter markdown
source.frontmatter: parsed metadata (title, author, date, etc.)
template_specification: full natural language spec of the 7 template blocks
instructions: task description

Read the full file on GitHub · 253 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 253 lines · 59 tokens per session scan A e37d78149e22

Subscribe to this mod's changes

visual-card is a skill published in the GitHub repository NatsuFox/Tapestry (64 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 2,319 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Creative and media agent-skills codex knowledge-base openclaw workflow

kimicode-vision-bridge

Use when the current Agent LLM cannot process images directly and visual analysis is needed — bridges images through KimiCode CLI print mode to a multimodal Kimi model for text description.

Dqz00116/skill-lib · 43 tokens

ve-terminal-mono

OpenDesign from the CLI: driving the full design workflow with the od command — scripted, composable, agent-ready. Built as a decision-grade AI literacy deck for developers, power users.

nexu-io/open-design · 45 tokens

morph-ppt

Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…

iOfficeAI/OfficeCLI · 169 tokens

visual-card