Agent skill

Figure Ground Cues

by hashgraph-online in hashgraph-online/awesome-codex-plugins

Apply specific visual cues to control figure-ground perception — shadow, elevation, scale, contrast, saturation, opacity, and texture.

Apache-2.0Auto-check passed

Install Figure Ground Cues

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-cues -a claude-code

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

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins figure-ground-cues --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/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-cues .claude/skills/figure-ground-cues && 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
figure-ground-cues
GitHub stars
1.3k
Token cost
~2.2k tokens
SKILL.md length
1,194 words
Files
2 (incl. references)
Skills in repo
716
Repo updated
First seen
Licence
Apache-2.0

At a glance

Apply specific visual cues to control figure-ground perception — shadow, elevation, scale, contrast, saturation, opacity, and texture.

  • Designing layered interfaces
  • SKILL.md covers Shadow / elevation, Scrim / overlay, Scale and Contrast and saturation, plus 11 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Hover treatments

What it does

Figure Ground Cues is an agent skill from hashgraph-online/awesome-codex-plugins. Apply specific visual cues to control figure-ground perception — shadow, elevation, scale, contrast, saturation, opacity, and texture. Use when designing layered interfaces, focus states, hover treatments, or any context where one element should clearly stand forward against others. Each cue contributes a portion of the figure-ground signal; combining cues strengthens the effect. The skill is selecting and calibrating cues for the desired level of separation.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/elevation-systems.md`).

The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

When your agent uses it

  • Designing layered interfaces
  • Hover treatments
  • Any context where one element should clearly stand forward against others

Example prompts

  • “/figure-ground-cues”

What it can do on your machine

Read from SKILL.md and the folder at commit 3e1456a. 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

Figure Ground Cues loads about 2.2k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 121 tokens; SKILL.md has 1,194 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

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 hashgraph-online/awesome-codex-plugins at commit 3e1456a, republished under its Apache-2.0 licence (© hashgraph-online). 1,194 words, ~2,158 tokens.

Download SKILL.mdSave it as .claude/skills/figure-ground-cues/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
figure-ground-cues
description
Apply specific visual cues to control figure-ground perception — shadow, elevation, scale, contrast, saturation, opacity, and texture. Use when designing layered interfaces, focus states, hover treatments, or any context where one element should clearly stand forward against others. Each cue contributes a portion of the figure-ground signal; combining cues strengthens the effect. The skill is selecting and calibrating cues for the desired level of separation.

Figure-Ground — visual cues

The figure-ground sorting that the user's perception performs depends on specific visual cues. As a designer, you choose which cues to use and how strongly to apply them, calibrated to the desired separation between figure and ground.

The major cues, with notes on their relative strength:

Shadow / elevation

Strongest single cue for figure-ground in modern UI. A drop shadow under an element makes it appear closer to the viewer (figure), with the rest of the layout receding. Multiple levels of shadow create multiple levels of elevation.

Common implementations:

  • Cards with subtle shadow (2–4px blur) for moderate elevation.
  • Floating action buttons with stronger shadow (8–12px blur) for higher elevation.
  • Modals with very prominent shadow + scrim for highest elevation.

Material Design formalized this into a system of "elevation levels" (0, 1, 2, 4, 8, 16, 24 dp) each with a specific shadow recipe. The system makes consistent figure-ground separation across a product easier to maintain.

Scrim / overlay

A semi-transparent layer over the ground that makes the ground visibly recede. Most commonly used with modals: the modal sits above the scrim, the scrim sits above the page.

Calibration:

  • Light scrim (10–20% opacity) for soft separation.
  • Medium scrim (40–60% opacity) for clear modal-style separation.
  • Dark scrim (70%+ opacity) for full focus on the figure (image lightboxes, video players).

Scale

Larger elements tend to come forward as figure, especially when they're surrounded by smaller elements. A hero card among supporting cards reads as figure through scale.

But this can flip: a tiny element on a vast background can also read as figure (the small floating action button on a large canvas is figure despite its size). The cue depends on context.

Contrast and saturation

Higher contrast and more saturated colors come forward; lower contrast and muted colors recede. The active workspace at full saturation; inactive workspaces with muted colors.

This cue is subtle — it's often used in combination with others rather than alone. But it's powerful for distinguishing active from inactive content.

Opacity

Semi-transparent elements recede; fully opaque elements come forward. Reducing the opacity of inactive content (50–70% opacity) is a quick way to send it to the background.

Be careful not to reduce opacity to the point of illegibility. Even "ground" content should usually remain readable.

Sharpness vs. blur

Sharp, in-focus elements come forward; blurred elements recede. iOS uses background blur extensively — a modal's background is blurred, signaling that it's behind the modal.

Blur is a strong cue but expensive computationally. Use deliberately, not casually.

Texture and detail

More detailed elements come forward; smoother, less detailed elements recede. A photographic background with text overlaid feels different than a solid background with text — the texture of the photo competes with the text for figure status.

Outlines and borders

A clear, visible border around an element helps it read as a closed figure. Borderless elements may merge into their background.

But heavy borders can feel "heavy" or dated. Modern design often prefers shadow over border for figure separation.

Position in z-axis (layering)

Elements layered on top of others occlude them, which is a strong figure cue. The element on top is figure; the element behind is ground.

Implementation in CSS: z-index controls the layering order. In design systems: explicit layering levels (cards, popovers, modals, toasts each at their own z-axis level).

Combining cues

The cues compound. A modal that uses shadow AND scrim AND opacity reduction on the background is more clearly figure than a modal using only one of these.

For elements that need to clearly come forward (modals, popovers, focus states), combine cues. For elements that should subtly come forward (hover states, mild emphasis), use a single cue or a combination of subtle ones.

Avoid combining too many cues at high intensity — the result can feel theatrical. Match the cue strength to the actual importance of the figure.

Worked examples

A modal with full figure-ground

A modal opens. Cues applied:

  • Scrim: 50% opacity black overlay between modal and page.
  • Modal elevation: prominent shadow (16px blur, 40% opacity).
  • Modal background: pure white (sharp contrast against the dark scrim).
  • Page beneath: visible through scrim but clearly receding.

The user's perception is unambiguous: the modal is figure, the page is ground. Attention naturally goes to the modal.

Show full SKILL.md (491 more words)Show less
A card hover with subtle figure-ground

A card in a grid is hovered. Cues applied:

  • Shadow increases (from 2px blur to 4px blur).
  • Slight scale increase (1.02×).
  • Subtle background shift (0.5% lighter).

The card subtly comes forward. Other cards remain at baseline. The user gets gentle feedback about where their attention is, without dramatic visual change.

Active workspace differentiated from inactive

In a multi-workspace app, the active workspace is rendered with full saturation; inactive workspaces are at 60% opacity with muted colors. The active workspace is clearly figure.

When the user switches workspaces, the cues swap: the new active workspace becomes figure, the previously active workspace becomes ground.

Background photo competing with text

A hero section uses a photo background with text overlaid. Without intervention, the photo's detail and color compete with the text — figure-ground is ambiguous.

Add a dark gradient over the photo (figure-ground cue: scrim) to push the photo further into the background. The text now clearly reads as figure.

A card with too many cues

A card has: a thick border, a heavy drop shadow, a colored background, a glow effect, AND scaling on hover. The card screams. It feels theatrical, almost cartoonish.

The fix: reduce to one or two strong cues. A subtle shadow + a clean white background + a slight border on hover is enough. The figure-ground separation works without the theatrics.

Anti-patterns

Insufficient cues. A modal that uses only a thin border and no shadow or scrim. The figure-ground separation is too weak; the modal blurs into the page.

Mixed cues that fight. A modal with shadow (suggests it's in front) but with reduced opacity (suggests it's receding). Users get conflicting signals.

Overdone cues. Heavy shadows on every card; high-contrast borders everywhere; aggressive scale changes on hover. The cues lose meaning when applied universally.

Inconsistent cues across surfaces. Modals styled with shadow + scrim in one place; modals styled with just a border in another. Users can't form expectations about modality.

Cues that hurt accessibility. Reducing opacity so low that text becomes hard to read; using color-only cues that fail for color-blind users.

Reversed cues. Chrome (sidebar, header) styled with stronger figure cues than the content. Users look at the chrome instead of focusing on their work.

Heuristic checklist

When designing figure-ground separation, ask: What should be figure, and what should be ground? Be deliberate. Which cues am I using to communicate the sorting? List them. Are the cues consistent within the product? Inconsistent cues confuse users. Is the separation strong enough? Test by glancing at the design — what comes forward? Is the separation too aggressive? Theatrical cues feel wrong; calibrate to the actual importance.

  • figure-ground-relationship — parent principle on figure-ground perception.
  • figure-ground-overlays-and-modals — sibling skill on the most common figure-ground problem.
  • hierarchy — figure-ground is a primary mechanism for hierarchy.
  • signal-to-noise — figure should be high-signal; ground low-noise.
  • color — color choice is one figure-ground cue.

See also

  • references/elevation-systems.md — practical guidance on building consistent elevation/figure-ground systems across a product.

© hashgraph-online, Apache-2.0. 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 1 other file (references) in plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-cues of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/elevation-systems.md

Open the folder on GitHubat commit 3e1456a

Compare with similar skills

Figure Ground Cues 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.

Figure Ground Cues compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Figure Ground Cues this skillhashgraph-online/awesome-codex-plugins1.3k—~2.2kAutomated safety check: PassApache-2.0
Law Of Figure GroundOwl-Listener/designer-skills2.9k—~1.2kAutomated safety check: PassMIT
Figurevectorize-io/hindsight48k—~1.9kAutomated safety check: PassMIT
Figure Figcaptionthedaviddias/Front-End-Checklist74k—~816Automated safety check: PassMIT
Figurebrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~5.9kAutomated safety check: PassCustom licence
Figuresbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~2.1kAutomated safety check: PassCustom licence

Similar skills

  • Law Of Figure Ground

    Owl-Listener/designer-skills

    Apply the Law of Figure-Ground — establish which layer is foreground and actionable versus background.

    2.9k GitHub stars~1.2k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Figure

    vectorize-io/hindsight

    Draw an animated figure (boxes, arrows, moving data) as one self-contained SVG for a GitHub README, PR, issue or blog post.

    48k GitHub stars~1.9k tokensUpdated today
    Writing & ContentAuto-check passed
  • Figure Figcaption

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing image assets, markup, and CDN or build transforms related to Use <figure and <figcaption for image captions.

    74k GitHub stars~816 tokensUpdated 3 days ago
    Auto-check passed
  • Figure

    brycewang-stanford/Auto-Empirical-Research-Skills

    Econometrics skill for generating publication-quality figures for top economics journals.

    4.6k GitHub stars~5.9k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Figures

    brycewang-stanford/Auto-Empirical-Research-Skills

    Design and format publication-quality figures: chart choice, color, scales, legends, captions, reproducibility.

    4.6k GitHub stars~2.1k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Grounded Citations

    NousResearch/hermes-agent

    Attaches a numbered, URL-backed citation to every outside fact in an answer or document, rejecting quotes that aren't real.

    252k GitHub stars~3.1k tokensUpdated today
    Research & ScienceAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 716 skills in this repo
  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.3k GitHub stars~922 tokensUpdated today
    Auto-check passed
  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.3k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.3k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.3k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Calle

    hashgraph-online/awesome-codex-plugins

    Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.

    1.3k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.3k GitHub stars~618 tokensUpdated today
    Auto-check passed

Questions about Figure Ground Cues

What does Figure Ground Cues do?

Apply specific visual cues to control figure-ground perception — shadow, elevation, scale, contrast, saturation, opacity, and texture. Figure Ground Cues is an agent skill from hashgraph-online/awesome-codex-plugins. Apply specific visual cues to control figure-ground perception — shadow, elevation, scale, contrast, saturation, opacity, and texture.

When should I use Figure Ground Cues?

Figure Ground Cues fits situations like: designing layered interfaces; hover treatments; any context where one element should clearly stand forward against others.

How do I install Figure Ground Cues in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-cues -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-cues in hashgraph-online/awesome-codex-plugins) into .claude/skills/figure-ground-cues in your project. Claude Code loads it when a task matches its description.

How do I install Figure Ground Cues in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill figure-ground-cues -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/figure-ground-cues in hashgraph-online/awesome-codex-plugins) into .agents/skills/figure-ground-cues in your project. Codex loads it when a task matches its description.

Can I use Figure Ground Cues 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 hashgraph-online/awesome-codex-plugins --skill figure-ground-cues -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/figure-ground-cues, .gemini/skills/figure-ground-cues, .github/skills/figure-ground-cues and .opencode/skills/figure-ground-cues in your project.

What does Figure Ground Cues need to run?

SKILL.md names no scripts, command-line tools or credentials: Figure Ground Cues is instructions for the agent only.

Does Figure Ground Cues 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 Figure Ground Cues 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 Figure Ground Cues use?

Figure Ground Cues is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Figure Ground Cues use?

About 2.2k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.

What are the alternatives to Figure Ground Cues?

Skills that share tags, products or a category with Figure Ground Cues: Law Of Figure Ground (Owl-Listener/designer-skills, 2.9k stars), Figure (vectorize-io/hindsight, 48k stars), Figure Figcaption (thedaviddias/Front-End-Checklist, 74k stars) and Figure (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Figure Ground Cues?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,267 GitHub stars. The repository holds 716 skills in this directory. The repository was last updated on October 10, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.