Kill AI Slop
yetone/kill-ai-slop
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project.
Apply iconic resemblance — designing or choosing icons that visually look like what they represent.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill iconic-resemblance -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins iconic-resemblance --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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/cognition-and-learnability-principles/skills/iconic-resemblance .claude/skills/iconic-resemblance && rm -rf skills-srcUse ~/.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/
Install the "iconic-resemblance" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance into .claude/skills/iconic-resemblance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iconic-resemblance", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblanceType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill iconic-resemblance -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins iconic-resemblance --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance .agents/skills/iconic-resemblance && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "iconic-resemblance" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance into .agents/skills/iconic-resemblance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iconic-resemblance", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill iconic-resemblance -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins iconic-resemblance --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance .cursor/skills/iconic-resemblance && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "iconic-resemblance" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance into .cursor/skills/iconic-resemblance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iconic-resemblance", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/hashgraph-online/awesome-codex-plugins.git --path plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill iconic-resemblance -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins iconic-resemblance --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance .gemini/skills/iconic-resemblance && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "iconic-resemblance" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance into .gemini/skills/iconic-resemblance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iconic-resemblance", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install hashgraph-online/awesome-codex-plugins iconic-resemblanceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add hashgraph-online/awesome-codex-plugins --skill iconic-resemblance -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance .github/skills/iconic-resemblance && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "iconic-resemblance" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance into .github/skills/iconic-resemblance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iconic-resemblance", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill iconic-resemblance -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins iconic-resemblance --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance .opencode/skills/iconic-resemblance && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "iconic-resemblance" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance into .opencode/skills/iconic-resemblance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iconic-resemblance", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
iconic-resemblanceApply iconic resemblance — designing or choosing icons that visually look like what they represent.
Iconic Resemblance is an agent skill from hashgraph-online/awesome-codex-plugins. Apply iconic resemblance — designing or choosing icons that visually look like what they represent. Use when picking icons for actions or objects with strong visual referents (camera, clock, lock, calendar), evaluating whether a custom icon is communicating, or testing whether your icon set actually conveys meaning to your audience. Resemblance is the strongest form of icon recognition because it requires no prior learning; it fails when the function has no visual referent or when the audience doesn't recognize…
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/icon-design-process.md`).
It sits in Frontend & Design, covering Icons and illustration. 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.
Read from SKILL.md and the folder at commit 9e7b281. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Iconic Resemblance loads about 2.4k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 141 tokens; SKILL.md has 1,393 words of instructions outside code blocks.
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.
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.
The full file from hashgraph-online/awesome-codex-plugins at commit 9e7b281, republished under its Apache-2.0 licence (© hashgraph-online). 1,393 words, ~2,433 tokens.
.claude/skills/iconic-resemblance/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Resemblant icons are those that visually look like what they represent. A camera icon for "take photo" — the shape literally depicts a camera. A clock icon for "time" — the shape depicts a clock. A folder icon for "folder" — the shape depicts a manila folder. The user understands what the icon means because it looks like the thing.
This is the strongest form of icon recognition because it requires no prior learning. A user who has never seen the icon before but who has seen a camera in real life can interpret the camera icon. The work is done by the resemblance itself.
Resemblance works when:
The function or concept has a clear visual referent. Camera (take photo), clock (time), envelope (email), magnifying glass (search/look closer), lock (security/private), trash can (delete), pencil (edit), calendar (date/schedule), star (favorite/rating), heart (like/love).
The referent object is universally familiar. A camera is recognized worldwide. A clock is recognized worldwide. A trash can is recognized in most cultures (with regional variations in shape). A envelope is recognized in cultures that have postal systems.
The icon's level of abstraction matches the audience. A photorealistic camera works for very literal contexts. A simple silhouetted camera works for general UI. A highly abstracted geometric "camera" may need to be tested to verify it still reads as a camera.
The space allows enough detail to be recognizable. A camera icon needs enough detail (the body, the lens, perhaps a viewfinder or shutter) to be identifiable. At very small sizes, detail is lost and the icon becomes a generic blob.
Resemblant icons fail when:
The function has no visual referent. "Reset password," "compare versions," "advanced filters," "permissions." These abstract operations don't depict anything physical. Inventing an icon (a circular arrow for reset, two overlapping shapes for compare) becomes example-based or symbolic rather than truly resemblant, and recognition rates drop.
The referent isn't familiar to the audience. A telegraph-machine icon for "send fast." A rotary-phone icon for "call." A typewriter for "writing." These references don't transfer to audiences who've never encountered the source.
The icon is too abstracted to read. A "camera" rendered as just two concentric circles might still be a camera to the designer who knows the lineage, but to a fresh user it's just two circles. Test for the threshold of recognizability.
The icon is visually similar to other icons. A camera and a video camera. A folder and a closed envelope. A pencil and a pen. When two functions have visually similar referents, the icons risk being confused.
The function is too specific for a general icon. "Take HDR photo" doesn't have a distinct visual referent — both HDR and non-HDR photos use a camera. Resemblance bottoms out at the camera; further specificity requires text or a secondary symbol.
When you're designing a new resemblant icon, a few practices help.
Pick the most identifying features of the referent. A camera is identifiable by its body and lens — that's enough. Don't add a strap, a shutter button, an SD card slot. Each addition is detail that the user has to parse without adding recognition.
Stylize but stay readable. The icon should be simplified enough to render clearly at icon sizes (16px–32px typical), but retain enough features to be unmistakable. Test at the actual rendering size, not just the design canvas.
Use silhouette over rendering. A silhouette of a camera is more readable at icon sizes than a detailed perspective rendering. Silhouettes scale down better and read more quickly.
Consider the line weight of your icon set. A camera icon outlined at 1.5px weight should match other icons in your set. Mismatched weights make icons look like they came from different libraries.
Test with users. Show the icon at the rendering size, alongside other icons from your set, with no label. Ask users what they think it means. Anything below 80% recognition needs work or needs a label.
A standard convention: a rounded rectangle (the camera body), a circle in the middle (the lens), a small square or dot at the top-left (the viewfinder or flash). Recognized worldwide. Works at sizes from 16px upward.
Variants: a movie camera (with film reels on top, recognized as "video"), a film camera (with the film canister visible), a phone camera (with phone outline). Each conveys a more specific subtype.
A standard convention: a circle with two hands (one short, one long) pointing at angles. Recognized worldwide. Works at very small sizes because the silhouette is distinctive.
Variants: digital clock (rectangular with numeric digits), stopwatch (with crown and start button), alarm clock (with bells on top). Each conveys a more specific function.
A standard convention: a stylized padlock with a U-shaped shackle on top. Recognized in cultures that use padlocks. Works at small sizes because the silhouette is distinctive.
Variants: open padlock (unlocked), padlock with key (security/access), padlock with checkmark (confirmed lock).
A standard convention: a manila-folder shape (a tab on top of a rectangle). Recognized in cultures with paper office filing systems — increasingly an acquired convention rather than a universal recognition. Works at small sizes.
The folder convention is starting to weaken as paper folders fade from common workplaces. For some audiences (younger users, mobile-native users) the folder is now an acquired convention rather than a similar icon — they recognize it because they've seen it in software, not because it resembles an object they use.
Initial design: a stylized neural-network diagram with three nodes connected by lines. Tested with users; recognition is 12%. Most users see "abstract geometric shape."
Revised design: a sparkle or four-pointed star. Tested with users; recognition is now around 40%, and rising as the convention spreads.
The lesson: there is no inherent visual referent for "AI assistant." The sparkle is becoming a symbolic convention (it works because users have started to associate it with AI features), not a similar icon. Similarity alone doesn't help here; the convention has to do the work.
Same product offers both photo and video capture. The icons are very similar (a camera body for photo; a camera body with film reels or a movie-camera form for video). The distinction is real but subtle, and users sometimes tap the wrong one.
The fix is usually to make the difference more visually salient (a camera icon and a play-triangle for video, for instance) or to pair both with text labels.
Resemblance icons that don't actually resemble. A custom icon designed to be "stylized" enough that it's no longer recognizable as the referent. The designer knows what it's meant to be; the user sees an abstract shape.
Decorative detail that obscures recognition. A camera icon with a strap, lens cap, neck loop, brand logo, and shutter button — all the details add nothing and make the icon harder to read at small sizes.
Resemblance icons paired with similar resemblance icons that confuse. A "camera" and a "video camera" icon that look nearly identical. Make the difference clear or pair with text.
Resemblance based on dying referents. Icons resembling rotary phones, floppy disks, CRT TVs, mailing envelopes. The audience may not recognize the referent, in which case the resemblance does nothing.
Resemblance icons rendered inconsistently with the rest of the icon set. A heavily-rendered photorealistic camera in a set of flat geometric icons. The visual mismatch suggests they came from different sources.
For each resemblant icon you're considering, ask: Does my audience have a clear mental image of the referent? If not, recognition will fail. Does my icon depict the referent recognizably at the rendering size? Test at actual size. Is the icon visually distinct from other icons in my set? Confused icons are worse than text labels. Have I tested recognition with real users from my audience? The designer's read is unreliable. Does the icon's style match the rest of my set? Coherence in style aids recognition.
iconic-representation — parent principle on iconic communication.iconic-arbitrary-and-symbolic — sibling skill on convention-based icons.mimicry-surface — resemblance icons are visual mimicry of the depicted object.mapping-cultural — icon recognition is a form of cultural mapping.recognition-over-recall — icons exploit recognition; this is the most direct form.references/icon-design-process.md — practical workflow for designing and testing resemblant icons.© 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
SKILL.md and 1 other file (references) in plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 9e7b281
Iconic Resemblance 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Iconic Resemblance this skillhashgraph-online/awesome-codex-plugins | 1.3k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Kill AI Slopyetone/kill-ai-slop | 1.3k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Better Iconsdtsola/xiaoyaosearch | 1k | 2 repos | ~895 | Automated safety check: Pass | Custom licence | |
| Fluent Icons Lookupcoltongriffith/fluenticons | 442 | — | ~492 | Automated safety check: Pass | None | |
| Review UI DesignColourCloudSky/review-ui-design-skill | 119 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Solar Iconssaoudi-h/solar-icons | 186 | — | ~2.1k | Automated safety check: Pass | MIT |
yetone/kill-ai-slop
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project.
dtsola/xiaoyaosearch
Searches more than 200 Iconify icon libraries and fetches icons as SVG from a command line tool or an MCP server.
coltongriffith/fluenticons
Looks up Microsoft Fluent UI System Icons and their exact @fluentui/react-icons component names through the Fluent Icons MCP server or HTTP API, instead of guessing.
ColourCloudSky/review-ui-design-skill
评审单份或一组产品 UI 设计稿,像资深设计专家团一样从视觉质量、交互体验、设计系统三个方面发现问题并给出具体、可执行、按优先级排序的优化建议;在可行时默认生成与报告编号对应的问题标注图和优化建议图,并支持修改稿增量复评。Use when the user provides UI screenshots, icon sets, screen recordings, product flows…
saoudi-h/solar-icons
Add Solar Icons via @solar-icons/cli to any React, Vue, Svelte, Solid, Angular, React Native, Nuxt, Static, vanilla JS, or Laravel Blade project.
smallnest/goal-workflow
Illustrate an article (Markdown, HTML, etc.) with animated-style icons from itshover.com/icons.
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.
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
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…
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…
hashgraph-online/awesome-codex-plugins
Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
Categories
Apply iconic resemblance — designing or choosing icons that visually look like what they represent. Iconic Resemblance is an agent skill from hashgraph-online/awesome-codex-plugins. Apply iconic resemblance — designing or choosing icons that visually look like what they represent.
Iconic Resemblance fits situations like: picking icons for actions; objects with strong visual referents (camera; evaluating whether a custom icon is communicating; testing whether your icon set actually conveys meaning to your audience.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill iconic-resemblance -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance in hashgraph-online/awesome-codex-plugins) into .claude/skills/iconic-resemblance in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill iconic-resemblance -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/iconic-resemblance in hashgraph-online/awesome-codex-plugins) into .agents/skills/iconic-resemblance in your project. Codex loads it when a task matches its description.
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 iconic-resemblance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/iconic-resemblance, .gemini/skills/iconic-resemblance, .github/skills/iconic-resemblance and .opencode/skills/iconic-resemblance in your project.
SKILL.md names no scripts, command-line tools or credentials: Iconic Resemblance is instructions for the agent only.
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.
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.
Iconic Resemblance 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.
About 2.4k tokens (SKILL.md is roughly 9.7k 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 1.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Iconic Resemblance: Kill AI Slop (yetone/kill-ai-slop, 1.3k stars), Better Icons (dtsola/xiaoyaosearch, 1k stars), Fluent Icons Lookup (coltongriffith/fluenticons, 442 stars) and Review UI Design (ColourCloudSky/review-ui-design-skill, 119 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,255 GitHub stars. The repository holds 714 skills in this directory. The repository was last updated on October 9, 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.