Engraved Figures logo

Engraved Figures

Community
OutThisLife
engraved-figures

Create scientific figures, technical plates, research posters and diagram collections in a monochrome engraved-paper style. Use for old-school wireframes, stippled plots, dense academic layouts, or understated redacted-document graphics. Supports precise SVG documentation and illustrative raster art.

Overview

PublisherOutThisLife
Repositorybrooklyn-skills
Skill nameengraved-figures
Stars
200
Forks
6
Bundled files
9
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by OutThisLife on GitHub. Read the source before you install it.

Installation

Install the Engraved Figures AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/OutThisLife/brooklyn-skills/tree/main/skills/engraved-figures
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/OutThisLife/brooklyn-skills.git /tmp/brooklyn-skills
mkdir -p .claude/skills
cp -r /tmp/brooklyn-skills/skills/engraved-figures .claude/skills/engraved-figures
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Engraved Figures in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Engraved Figures on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Engraved Figures is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Engraved figures

Scientific drawing carries the composition: fine wireframes, stippled points, clear axes, serif labels, and generous space inside a dense page. Before choosing a layout, open the reference showcase: one landscape plate (reference-plate.png) and a net-metric chart (reference-chart.png). Cyclic or redacted posters follow poster direction without a bundled poster file. Read multi-figure plates and chart direction. Match bundled density and grammar; use the user's subject and real data when claiming measured results.

Choose the right kind of figure

  • Technical documentation: derive the relationships from source material or implementation. Prefer editable SVG with real text and an accessible title/description. Describe exactly what the marks, lines, boundaries and axes mean. Keep the mechanism legible. Read technical figures.
  • Quantitative charts on paper: thin smoothed daily lines, one combined moving average, shaded windows and dashed event markers — not dashboard widgets. Read chart direction.
  • Illustrative poster or standalone art: use the available image-generation workflow when a raster illustration is requested. Scientific geometry can serve as a metaphor, clearly labeled schematic. A torus does not establish a storage topology; a landscape is not measured performance. Read poster and redaction direction.
  • Interactive or animated composition: use actual geometry in the requested renderer. Preserve the approved page, typography and camera composition. Agree the meaningful behavior from the request: rotating a form, scrubbing a time slice, following a path, selecting a neighborhood. Keep text stationary and readable. Add motion controls and respect reduced motion. Animation and export workflows remain separate from this visual style.

Honor the user's requested medium. Do not turn a request for an image into a website, a paper into an animation, or a diagram into a new product interface.

Visual grammar

  • Black and neutral gray ink on clean white or gently warm paper. Monochrome is the default; color needs a reason or a user request.
  • Fine curved mesh lines and stippling form the drawings. Use heavier lines for selected paths or meaningful boundaries. Nodes remain small; avoid glossy spheres and dramatic shading.
  • Serif typography throughout the paper. STIX Two Text is appropriate for technical publishing; Times is a useful fallback. Use italic annotations and restrained small caps. Monospace belongs to actual identifiers, not all labels.
  • Hairline rules organize the page. Avoid rounded cards, icons, UI panels, badges, gradients, shadows and decorative controls.
  • Several substantial figures beat one central generic network surrounded by tiny icons. Match the reference's number, scale and distribution of figures when a reference is supplied. A full poster might use five main figures and several lower-column diagrams; a single figure should stay a single figure.
  • Keep labels outside dense geometry. Use short leaders when needed. At final display or print size, the labels must remain readable.
  • Preserve clean paper. Simulated aging, stains, copier dirt, stamps, invented document codes and agency seals require explicit requests. “Redacted files” usually means opaque rectangles on an ordinary document, not a spy-movie prop.

Adapt the form to the explanation

Point clouds can illustrate many observations. Wireframe slices can show successive views. Neighborhood graphs explain relationships. A narrowing field can illustrate bounded selection. Gate planes can separate stages. Choose based on the claim, not a fixed visual inventory.

For explanatory work, distinguish illustrative form from data encoding. A time cutoff needs an actual timeline. A rank display needs a defined ordering; do not invent scores. A model diagram needs its real inputs and boundaries. Keep speculative parts visibly separate from implemented behavior.

Redaction, when requested

Use opaque, sharp black rectangles over the actual lettering, with slight padding. White lettering on a black label is a heading, not a redaction. A thin strike-through does not conceal a word.

For an irregular, casually withheld look, mix complete labels, individual words and a few partial phrases. Vary bar lengths and coverage; preserve enough text to establish context. If names must never appear, check every caption, heading, footer, legend and table—not only the main title.

Partial coverage is an aesthetic choice only when the user wants the text inferable. For real confidentiality, use irreversible redaction, remove hidden text and metadata, and verify the exported artifact. Never present a CSS overlay or recoverable SVG text as secure redaction.

Produce and verify

  1. Read the actual reference. Identify its composition, figure scale, line treatment, typography and density.
  2. Map the requested content to figures. Preserve explicit labels, implementation boundaries and any approved visual decisions.
  3. Create a first complete composition. For revisions, change only what the user criticized and keep the praised version.
  4. Inspect the output at its intended size. Check labels, arrows, line intersections, clipping, contrast and the actual coverage of redactions. For papers, inspect both browser and rendered PDF.
  5. Save standalone figures when requested. Preserve originals and use versioned sibling outputs for visual revisions.

Measure and report actual raster dimensions. Cropping or enlarging a small plot does not recover detail. Generative standalone redraws can improve detail but are not pixel-identical extractions. For sharp arbitrary-size technical figures, deliver SVG; rasterize at the requested dimensions only when needed.

When a page is published, verify the deployed page contains and renders the new figures. This skill does not itself authorize publication, git writes, external messages or unrelated documentation changes.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Engraved Figures AI skill do?

Create scientific figures, technical plates, research posters and diagram collections in a monochrome engraved-paper style. Use for old-school wireframes, stippled plots, dense academic layouts, or understated redacted-document graphics. Supports precise SVG documentation and illustrative raster art.

Why use Engraved Figures on TypingMind?

Because you install it once and use it with any model. Engraved Figures is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Engraved Figures in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/OutThisLife/brooklyn-skills/tree/main/skills/engraved-figures. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Engraved Figures?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Engraved Figures?

As many as you like. As long as a model supports skills, you can use Engraved Figures with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Engraved Figures AI skill free?

Yes. It is published on GitHub by OutThisLife under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇