Kortix Brand
kortix-ai/suna
Load FIRST for anything that carries the Kortix look or voice: product or mobile UI, copy of any kind, decks, social, images, email, CLI output, anything with the logo, and reviews of these.
Apply surface mimicry — making an interface element look like a familiar physical object to communicate its purpose at a glance.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill mimicry-surface -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mimicry-surface --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/mimicry-surface .claude/skills/mimicry-surface && 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 "mimicry-surface" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/mimicry-surface into .claude/skills/mimicry-surface/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry-surface", 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/mimicry-surfaceType 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 mimicry-surface -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mimicry-surface --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/mimicry-surface .agents/skills/mimicry-surface && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mimicry-surface" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/mimicry-surface into .agents/skills/mimicry-surface/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry-surface", 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 mimicry-surface -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mimicry-surface --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/mimicry-surface .cursor/skills/mimicry-surface && 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 "mimicry-surface" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/mimicry-surface into .cursor/skills/mimicry-surface/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry-surface", 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/mimicry-surface--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 mimicry-surface -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mimicry-surface --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/mimicry-surface .gemini/skills/mimicry-surface && 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 "mimicry-surface" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/mimicry-surface into .gemini/skills/mimicry-surface/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry-surface", 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 mimicry-surfaceInstalls 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 mimicry-surface -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/mimicry-surface .github/skills/mimicry-surface && 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 "mimicry-surface" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/mimicry-surface into .github/skills/mimicry-surface/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry-surface", 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 mimicry-surface -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 mimicry-surface --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/mimicry-surface .opencode/skills/mimicry-surface && 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 "mimicry-surface" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/mimicry-surface into .opencode/skills/mimicry-surface/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry-surface", 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.
mimicry-surfaceApply surface mimicry — making an interface element look like a familiar physical object to communicate its purpose at a glance.
Mimicry Surface is an agent skill from hashgraph-online/awesome-codex-plugins. Apply surface mimicry — making an interface element look like a familiar physical object to communicate its purpose at a glance. Use when introducing a control or container that has no native UI vocabulary, designing a niche product that benefits from a recognizable visual reference (a journal that looks like a journal, a wallet that looks like a wallet), or evaluating whether visual skeuomorphism is communicating or just decorating. Surface mimicry is most useful for novice users in unfamiliar mediums; it…
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/skeuomorphic-vs-flat.md`).
It sits in Mobile, covering Mobile UI design. 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 78497e5. 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.
Mimicry Surface loads about 2.8k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 153 tokens; SKILL.md has 1,533 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 78497e5, republished under its Apache-2.0 licence (© hashgraph-online). 1,533 words, ~2,797 tokens.
.claude/skills/mimicry-surface/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Surface mimicry is the visual layer of mimicry: an interface element rendered to look like a physical object. The fake-leather Calendar app of iOS 6, the legal-pad Notes app, the brushed-aluminum desktop widget — all are surface mimicry. The element behaves like a digital control, but the visual treatment communicates "this is the digital version of [thing]."
The strength of surface mimicry is recognition. A user looking at a fake-leather journal app immediately understands they're meant to write personal entries in it. They don't need a label; the visual reference does the work.
The weakness is that visual references age quickly. The leather-bound journal looked premium in 2010 and looks dated in 2026. The brushed-aluminum panel signaled "professional audio gear" in 2008 and signals "outdated software" today. Surface mimicry has a shelf life that depends on the source's continued relevance.
Surface mimicry is most valuable when:
The user has no other reference for what the thing is. A novel category of tool, an experimental interaction model, a unique form factor. Surface mimicry of a familiar physical object can be the fastest way to establish a mental model.
The audience genuinely knows the source. A journal app for adults who write in paper journals: leather-bound visual references work. A journal app for teenagers who've never owned a paper journal: the same references read as "Grandma's app."
The visual reference adds emotional or aesthetic value. A meditation app that looks like a Zen garden. A reading app whose pages have a subtle paper texture. The mimicry isn't strictly functional but contributes to the desired emotional register.
The product is targeting a niche where the source is part of the identity. A music-production app for vintage-synth enthusiasts can lean into hardware-mimicking knobs and faders because the audience values that aesthetic. The same mimicry in a general-audience tool would alienate users.
Surface mimicry becomes a liability when:
The audience doesn't know the source. Mimicking analog audio gear for users who've never used analog audio gear teaches nothing. The visual reference is just decorative.
The mimicry suggests limitations the digital version doesn't have. A fake-paper interface that doesn't support search, formatting, or sharing. Users primed by the visual to expect paper-like limitations may not discover the digital affordances.
The source has faded from common experience. Floppy disks, CRT televisions, tape cassettes, rotary phones. References that were universal in one decade may be unfamiliar a decade later.
The mimicry creates accessibility problems. Heavy textures, decorative typography, low-contrast skeuomorphic styling — all can hurt readability, screen-reader compatibility, and accessibility for users with vision differences. Decorative mimicry that compromises function is the wrong tradeoff.
The mimicry conflicts with brand or platform conventions. A skeuomorphic app on a flat-design platform feels foreign. Heavy visual decoration may conflict with the brand's broader aesthetic.
Surface mimicry runs from very literal to very abstract. The layers carry different costs and benefits.
Photorealistic. Detailed rendering of textures, lighting, materials — the calendar that looks like real torn paper, the journal with stitched leather. Highest recognition impact, highest aesthetic risk, shortest shelf life.
Stylized. A simplified visual reference — the calendar that has paper-edge serration but isn't trying to be photorealistic. Moderate recognition, more durable visually.
Iconic. A schematic reference — a simple folder icon that just suggests a folder. Low decoration cost, often the right level for ongoing UI elements.
Symbolic only. A label or word with no visual reference at all. No mimicry, just naming. Often the right choice for established conventions where the reference no longer needs visual reinforcement.
The flat-design movement of the 2010s pushed most UI to "iconic" or "symbolic only" — mimicry became simpler and more abstract while preserving the underlying metaphors. This is where most interfaces sit today.
An e-reader app uses subtle surface mimicry: a slight off-white "paper" background, a serif typeface in a comfortable line length, the page-turn animation when navigating. The mimicry is restrained — no fake leather binding, no torn-paper edges, no shadow effects suggesting depth. Just enough to evoke the reading experience.
The mimicry helps users settle into a reading mindset. It doesn't try to be a paper book — it's recognizably a digital reading experience, with search, lookup, and adjustable text. The mimicry contributes to the emotional register without locking the experience into paper limitations.
A music app for casual listeners is rendered to look like a vintage tape deck: cassette graphics, fake LCD displays, simulated spinning reels. The audience — people in their 20s and 30s — has rarely used cassettes. The visual references don't communicate; they're decorative kitsch. Users are mildly amused on first launch and indifferent thereafter.
Worse, the cassette metaphor implies limitations: linear playback, fast-forward and rewind, side A and side B. Users wonder if the app supports modern features (playlists, shuffle, smart queues) because the visual tells them not to expect those.
The fix would be to abandon the cassette mimicry in favor of modern abstract conventions (a play button, a queue, a visual representation of audio waveforms or album art) that don't carry obsolete affordance limitations.
A journal app for adults who keep written journals uses moderate surface mimicry: an off-white paper background, a generous serif typeface, a single elegant cursor. No fake leather, no stitching, no shadow rendering. Just enough to evoke the feeling of writing in a personal journal.
The mimicry is age-appropriate (adults who keep journals know what paper journals look and feel like) and tasteful (the visual reference doesn't shout). And the app extends paper's affordances: encrypted storage, cross-device sync, search across entries.
This is surface mimicry done well: it sets the emotional register without being decorative kitsch and without limiting the digital affordances.
A modern productivity tool uses no surface mimicry at all. Buttons are flat rectangles with brand color. Cards are plain containers with shadow only when elevated. The interface looks "computer-native" — no attempt to mimic physical objects.
This works because the underlying metaphors (folders, files, shared workspaces) are now widely understood without visual reinforcement. Users don't need a literal folder icon to understand what a folder is. The abstract treatment is faster, lighter, more performant, and more accessible than heavier surface mimicry.
For most modern productivity tools, this is the right baseline. Surface mimicry is reserved for the moments where it adds genuine value (an empty-state illustration, a one-off welcome screen).
A guitar amplifier simulator app is styled to look like an actual guitar amplifier: knobs for gain, treble, mid, bass; toggle switches for channels; an LED indicator. The audience — guitarists — knows what these controls look like and what they do because they're modeled on real hardware they own. The mimicry communicates instantly to the actual user.
This is surface mimicry in a niche: the audience genuinely knows the source, the source is current (people still buy guitar amps), and the references are functional rather than decorative.
Surface mimicry without behavioral or functional mimicry. A button that looks like a physical button but doesn't depress on click; a "page" that looks like paper but scrolls like a webpage. The visual promise isn't kept.
Surface mimicry of obsolete sources. Floppy disks, brushed metal panels, leather-bound journals for audiences that don't recognize the references.
Surface mimicry that hurts accessibility. Decorative typography, low-contrast skeuomorphic styling, heavy textures that interfere with screen readers or low-vision users.
Surface mimicry as a substitute for thought. Reaching for skeuomorphic styling to "make the interface feel friendly" without thinking about what specifically the mimicry is communicating. Often a sign that the underlying design hasn't been fully figured out.
Surface mimicry inconsistently applied. Some screens are heavily skeuomorphic, others are flat. The user can't form a coherent expectation of what the product is. Either commit to a register or commit to flat — don't drift between them within a single product.
Mimicry of competitor products' surface styling. "Make it look like X" without understanding why X looks the way it does. Often imports surface decisions that were appropriate for X's audience but not yours.
Before reaching for surface mimicry, ask: Does my audience know the source I'm referencing? If not, the mimicry communicates nothing. Is the mimicry communicating something specific about function or emotional register, or is it decorative? Decoration is fine, but be honest about it. Does the mimicry suggest limitations the digital medium doesn't have? If so, find a way to signal the additional capabilities. Will the source still be familiar in 5 years? If not, the mimicry has a short shelf life. Does the mimicry conflict with platform or accessibility conventions? If so, the cost may exceed the recognition benefit.
mimicry — parent principle on the strategy of borrowing from the familiar.mimicry-behavioral — sibling skill on behavioral mimicry.aesthetic-usability-effect — surface treatment shapes perceived usability; mimicry is one form.iconic-representation — icons are surface mimicry at the symbolic level.archetypes — brand archetypes and surface mimicry both shape emotional register.references/skeuomorphic-vs-flat.md — practical guidance on the spectrum from photorealistic to abstract surface treatment.© 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/mimicry-surface of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 78497e5
Mimicry Surface 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 |
|---|---|---|---|---|---|---|
| Mimicry Surface this skillhashgraph-online/awesome-codex-plugins | 1.2k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Kortix Brandkortix-ai/suna | 20k | — | ~4k | Automated safety check: Pass | Custom licence | |
| HugeIcons Finder for Composesue1231513/orangechat | 406 | 1 repos | ~467 | Automated safety check: Pass | Custom licence | |
| Codedrobe ThemeCodeDrobe/skills | 250 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Mobile App UI Designceorkm/mobile-app-ui-design | 400 | — | ~2k | Automated safety check: Pass | None | |
| Sleek Design Mobile Appssleekdotdesign/agent-skills | 584 | — | ~2.1k | Automated safety check: Pass | MIT |
kortix-ai/suna
Load FIRST for anything that carries the Kortix look or voice: product or mobile UI, copy of any kind, decks, social, images, email, CLI output, anything with the logo, and reviews of these.
sue1231513/orangechat
Looks up available HugeIcons by keyword from the compiled dependency JAR in the Gradle cache, then shows the correct Compose import for each match.
CodeDrobe/skills
Create, inspect, convert, apply, replace, verify, troubleshoot, update, publish, or restore reversible CodeDrobe themes for supported Chromium/Electron AI desktop apps, including OpenAI Codex…
ceorkm/mobile-app-ui-design
Design high-quality mobile app UI/UX screens, flows, and components.
sleekdotdesign/agent-skills
Design mobile app screens with Sleek, edit Sleek projects, and implement their designs in React Native or HTML.
skydoves/android-testing-skills
A skill your agent uses to verify Compose layout measurements from a UI test using assertWidthIsEqualTo, assertHeightIsEqualTo, assertWidthIsAtLeast, assertHeightIsAtLeast…
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
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
hashgraph-online/awesome-codex-plugins
Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and…
Categories
Apply surface mimicry — making an interface element look like a familiar physical object to communicate its purpose at a glance. Mimicry Surface is an agent skill from hashgraph-online/awesome-codex-plugins. Apply surface mimicry — making an interface element look like a familiar physical object to communicate its purpose at a glance.
Mimicry Surface fits situations like: introducing a control; container that has no native UI vocabulary; designing a niche product that benefits from a recognizable visual reference (a journal that looks like a journal; A wallet that looks like a wallet).
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill mimicry-surface -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/mimicry-surface in hashgraph-online/awesome-codex-plugins) into .claude/skills/mimicry-surface in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill mimicry-surface -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/mimicry-surface in hashgraph-online/awesome-codex-plugins) into .agents/skills/mimicry-surface 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 mimicry-surface -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mimicry-surface, .gemini/skills/mimicry-surface, .github/skills/mimicry-surface and .opencode/skills/mimicry-surface in your project.
SKILL.md names no scripts, command-line tools or credentials: Mimicry Surface 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.
Mimicry Surface 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 2.8k tokens (SKILL.md is roughly 11k 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.
Skills that share tags, products or a category with Mimicry Surface: Kortix Brand (kortix-ai/suna, 20k stars), HugeIcons Finder for Compose (sue1231513/orangechat, 406 stars), Codedrobe Theme (CodeDrobe/skills, 250 stars) and Mobile App UI Design (ceorkm/mobile-app-ui-design, 400 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 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 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.