Agent skill

Similarity Grouping

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

Use visual similarity to create perceptual groups — making related items look alike so users perceive them as a set.

Apache-2.0Auto-check passed

Install Similarity Grouping

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill similarity-grouping -a claude-code

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

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins similarity-grouping --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/similarity-grouping .claude/skills/similarity-grouping && 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
similarity-grouping
GitHub stars
1.3k
Token cost
~1.8k tokens
SKILL.md length
1,037 words
Files
2 (incl. references)
Skills in repo
716
Repo updated
First seen
Licence
Apache-2.0

At a glance

Use visual similarity to create perceptual groups — making related items look alike so users perceive them as a set.

  • Designing lists with categorized items
  • SKILL.md covers Core grouping techniques, When grouping by similarity is…, Worked examples and Anti-patterns, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Navigation systems

What it does

Similarity Grouping is an agent skill from hashgraph-online/awesome-codex-plugins. Use visual similarity to create perceptual groups — making related items look alike so users perceive them as a set. Use when designing lists with categorized items, navigation systems, status displays, dashboards with multiple data series, or any layout where you want users to see "these things go together" at a glance. The strongest grouping cues, in order, are color, size, shape, and orientation; combine multiple cues for the strongest grouping.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/grouping-patterns.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 lists with categorized items
  • Navigation systems
  • Status displays
  • Dashboards with multiple data series

Example prompts

  • “these things go together”
  • “/similarity-grouping”

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

Similarity Grouping loads about 1.8k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 118 tokens; SKILL.md has 1,037 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~118
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.5k

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 hashgraph-online/awesome-codex-plugins at commit 3e1456a, republished under its Apache-2.0 licence (© hashgraph-online). 1,037 words, ~1,834 tokens.

Download SKILL.mdSave it as .claude/skills/similarity-grouping/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
similarity-grouping
description
Use visual similarity to create perceptual groups — making related items look alike so users perceive them as a set. Use when designing lists with categorized items, navigation systems, status displays, dashboards with multiple data series, or any layout where you want users to see "these things go together" at a glance. The strongest grouping cues, in order, are color, size, shape, and orientation; combine multiple cues for the strongest grouping.

Similarity — grouping

When you want users to perceive a set of items as belonging together — as a category, as related, as the same kind of thing — visual similarity is the most direct way to communicate it. Two items styled the same way are perceived as a pair; ten items styled the same way are perceived as a set; an entire list styled consistently is perceived as a category.

Core grouping techniques

Same color. The strongest grouping cue. All "active" items in one color; all "inactive" items in another. All items in a category share a color tag or background tint.

Same size. Items at the same visual scale group. All section headings at the same size; all body text at the same size; all icons at the same size.

Same shape. Items in the same shape group. All cards have the same proportions; all buttons have the same corner radius; all icons share a stroke style.

Same icon or symbol. Items marked with the same icon group. All "important" items get a star; all "deletable" items get a trash icon visible on hover.

Same typographic treatment. Bold weight, italic, color shift — applied consistently — makes a class of words read as a group (every link, every keyword, every status name).

Combine multiple cues for stronger grouping. A "selected" item with both a colored background AND a colored border AND a checkmark icon is grouped much more strongly than an item with just one of those cues.

When grouping by similarity is the right move

Related items spread across a layout. If items aren't physically close (proximity grouping isn't available) but should be perceived as related, similarity carries the grouping. Selected items in a long list, for example.

Mixed categories in a single view. A dashboard showing servers in different statuses, files of different types, projects in different stages. Similarity by category lets users scan and segment.

Repeating elements with shared role. Buttons of the same priority; navigation items at the same level; cards of the same type. Consistent styling makes the role recognizable.

Status communication. Active vs. inactive, healthy vs. failing, approved vs. pending. Different visual treatment for each status; consistent within each status.

Worked examples

A multi-status dashboard

A monitoring dashboard shows 50 services. Each service can be in one of four states: healthy, degraded, down, unknown.

  • Healthy: green background tint + checkmark icon.
  • Degraded: yellow background tint + warning icon.
  • Down: red background tint + X icon.
  • Unknown: gray background tint + dash icon.

The user can scan all 50 services and immediately see the distribution of states. Color does most of the grouping; icons reinforce.

If only one cue had been used (only icons, no color), the perceptual grouping would be much weaker; users would have to focus on each item individually.

A document list with file-type grouping

A file manager shows mixed file types. PDFs all have a red PDF icon; Word docs have a blue Word icon; images have a small thumbnail; folders have a folder icon. The visual similarity within each file type makes scanning easy: "show me all the PDFs" is just "find all the items with the red icon."

If file types had been distinguished only by extension in the filename, scanning would be much harder.

A navigation hierarchy

A sidebar nav has primary nav items (top level) and secondary nav items (children, indented). Primary items use a slightly larger size, bolder weight, and consistent icon treatment. Secondary items use smaller size, regular weight, indented position.

Within each level, items group by similarity. The two levels are distinguished by their differences. Users see the hierarchy at a glance.

Show full SKILL.md (436 more words)Show less
Selected items in a long list

A list of 100 items. The user has selected 12 of them. Selected items have a colored background tint (the brand color at 15% opacity); unselected items have no background.

Even though selected items are scattered through the list, the color similarity makes them visually group. The user can see how many are selected, and where they are, without scrolling carefully.

If selection had been indicated with just a small checkmark in the corner, the selected items wouldn't group as strongly; the user would need to scan more carefully.

A pricing table

A pricing table shows three plans (Basic, Pro, Enterprise). Each plan card has the same visual structure (price, features list, CTA button). Within each card, the features list uses the same typography, the same checkmark icon for included features, the same X icon for excluded features.

The structural similarity across cards makes them comparable: the user can scan horizontally to compare features. The styling similarity within each card makes each card readable as a coherent unit.

Anti-patterns

Grouping cues that conflict. A card with a colored background that says "Important" but a small subtle border that says "Inactive." The user gets contradictory grouping signals.

Inconsistent styling within a category. Some items in the "important" category styled with a red border, others with a red background, others with just a red icon. The category fragments visually.

Subtle differences that don't communicate. A 5% opacity change between two states. The visual similarity is so strong the dissimilarity goes unnoticed; users don't perceive distinct groups.

Overgrouping. Trying to make every item in a long list look subtly different to encode many dimensions of metadata. Users can't process more than ~5 visual categories at a time without effort. Reduce the categories or use other mechanisms (filters, sort) for the rest.

Color used for grouping but accessible only by color. Color-blind users can't perceive color-only grouping. Always pair color with shape or position.

Heuristic checklist

When designing a layout with multiple item types, ask: What are the categories of items? Each category should have a consistent visual treatment. Which similarity cues am I using to communicate each category? Color is strongest; combine with shape or icon for accessibility. Are items within each category styled consistently? Inconsistency fragments the grouping. Are different categories distinguished sufficiently? Subtle differences may not be perceived.

  • gestalt-similarity — parent principle on similarity-based perception.
  • similarity-and-contrast — sibling skill on dissimilarity for distinction.
  • proximity — proximity grouping; complementary to similarity.
  • color — color is the strongest similarity cue.
  • consistency — consistency creates similarity within a product.

See also

  • references/grouping-patterns.md — patterns for specific grouping situations.

© 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/similarity-grouping of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/grouping-patterns.md

Open the folder on GitHubat commit 3e1456a

Compare with similar skills

Similarity Grouping 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.

Similarity Grouping compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Similarity Grouping this skillhashgraph-online/awesome-codex-plugins1.3k—~1.8kAutomated safety check: PassApache-2.0
Add Permission Group Itemsimstudioai/sim30k—~8.3kAutomated safety check: PassApache-2.0
Validate Permission Group Itemsimstudioai/sim30k—~5.9kAutomated safety check: PassApache-2.0
Harness Similarityruvnet/ruflo74k—~866Automated safety check: NotesMIT
Public Relationscoreyhaines31/marketingskills54k—~2.4kAutomated safety check: PassMIT
Public Relationssickn33/agentic-awesome-skills47k1 repos~1.8kAutomated safety check: PassMIT

Similar skills

  • Add a new governed item to Sim's enterprise permission groups — a boolean restriction, an allowlist, or a denylist — wired end-to-end from the field registry through the capability rule to the…

    30k GitHub stars~8.3k tokensUpdated today
    Auto-check passed
  • Audit an existing enterprise permission-group item end-to-end — registry entry, schemas, type, defaults, tolerant parser, admin UI, capability rule, enforcement site, and tests — proving the gate…

    30k GitHub stars~5.9k tokensUpdated today
    Auto-check passed
  • Harness Similarity

    ruvnet/ruflo

    ADR-152 — weighted similarity between two harness fingerprints (genome + score JSON).

    74k GitHub stars~866 tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Public Relations

    coreyhaines31/marketingskills

    When the user wants help with public relations, earned media, press coverage, journalist outreach, or media strategy (not pull requests).

    54k GitHub stars~2.4k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Public Relations

    sickn33/agentic-awesome-skills

    When the user wants help with public relations, earned media, press coverage, journalist outreach, or media strategy (not pull requests).

    47k GitHub starsUsed in 1 repo~1.8k tokens
    DevelopmentAuto-check passed
  • Groups

    parcadei/Continuous-Claude-v3

    Problem-solving strategies for groups in abstract algebra. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 1 repo~956 tokens
    Research & ScienceAuto-check: notes

More from hashgraph-online/awesome-codex-plugins

All 715 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~2.5k 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 Similarity Grouping

What does Similarity Grouping do?

Use visual similarity to create perceptual groups — making related items look alike so users perceive them as a set. Similarity Grouping is an agent skill from hashgraph-online/awesome-codex-plugins. Use visual similarity to create perceptual groups — making related items look alike so users perceive them as a set.

When should I use Similarity Grouping?

Similarity Grouping fits situations like: designing lists with categorized items; navigation systems; status displays; dashboards with multiple data series.

How do I install Similarity Grouping in Claude Code?

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

How do I install Similarity Grouping in Codex?

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

Can I use Similarity Grouping 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 similarity-grouping -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/similarity-grouping, .gemini/skills/similarity-grouping, .github/skills/similarity-grouping and .opencode/skills/similarity-grouping in your project.

What does Similarity Grouping need to run?

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

Does Similarity Grouping 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 Similarity Grouping 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 Similarity Grouping use?

Similarity Grouping 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 Similarity Grouping 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. Its references folder adds about 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Similarity Grouping?

Skills that share tags, products or a category with Similarity Grouping: Add Permission Group Item (simstudioai/sim, 30k stars), Validate Permission Group Item (simstudioai/sim, 30k stars), Harness Similarity (ruvnet/ruflo, 74k stars) and Public Relations (coreyhaines31/marketingskills, 54k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Similarity Grouping?

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.