Story Multi-Perspective Review
zenstory-ai/oh-story-claudecode
Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.
Apply the principle of Mimicry — borrowing the form, behavior, or visual language of something familiar to make a new design recognizable.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill mimicry -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mimicry --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 .claude/skills/mimicry && 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" 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 into .claude/skills/mimicry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry", 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/mimicryType 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 -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mimicry --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 .agents/skills/mimicry && 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" 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 into .agents/skills/mimicry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry", 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 -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mimicry --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 .cursor/skills/mimicry && 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" 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 into .cursor/skills/mimicry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry", 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--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 -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins mimicry --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 .gemini/skills/mimicry && 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" 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 into .gemini/skills/mimicry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry", 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 mimicryInstalls 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 -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 .github/skills/mimicry && 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" 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 into .github/skills/mimicry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry", 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 -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 --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 .opencode/skills/mimicry && 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" 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 into .opencode/skills/mimicry/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mimicry", 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.
mimicryApply the principle of Mimicry — borrowing the form, behavior, or visual language of something familiar to make a new design recognizable.
Mimicry is an agent skill from hashgraph-online/awesome-codex-plugins. Apply the principle of Mimicry — borrowing the form, behavior, or visual language of something familiar to make a new design recognizable. Use when introducing a novel feature whose function would be opaque without an analogy, choosing between metaphor and convention, designing for a category your users already know, or evaluating whether a "skeuomorphic" element helps or hurts. Mimicry comes in surface (visual resemblance), behavioral (acts like the source), and functional (does what the source does) forms. Used…
Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/lineage.md`).
It sits in Writing & Content, covering Creative writing and fiction. 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 loads about 3.5k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 158 tokens; SKILL.md has 2,031 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). 2,031 words, ~3,506 tokens.
.claude/skills/mimicry/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Definition. Mimicry is the design strategy of borrowing the appearance, behavior, or function of something the user already knows in order to make a new design recognizable and learnable. The desktop metaphor (folders, files, trash can) is mimicry of office tools. The "card" pattern in mobile UIs is mimicry of physical cards. The page-turn animation in early e-readers is mimicry of physical books. Each borrows from a familiar source to give users an instant mental model for an unfamiliar medium.
The principle is the same one that early software pioneers used to onboard users into a fundamentally new medium: borrow visual and behavioral language from the physical world so users had something to ground their understanding. The desktop metaphor of the original Macintosh mimicked the world of paper documents and folders that office workers already understood. Hypertext mimicked the cross-references in a book. The mouse pointer mimicked the index finger pointing.
Mimicry works because it short-circuits learning. The user doesn't have to be told what a "trash can" does because they already know what a trash can does. The interface borrows the user's existing knowledge.
Mimicry can happen at one or several layers. The distinction matters because the layers come with different costs and benefits.
Surface mimicry. The new design looks like the source. A button styled to look like a physical button (with a 3D bevel, shadow, and pressed state). A note app styled to look like a yellow legal pad. A music player styled to look like an analog mixer. Surface mimicry is the strongest form for first-encounter recognition — users can see at a glance what the thing references — but it can feel dated or kitschy if the visual reference becomes anachronistic.
Behavioral mimicry. The new design behaves like the source. The page-turn animation in an e-reader. The drag-to-rearrange gesture that follows physical-world manipulation. The springy bounce when a list reaches its end (Apple's "rubber band" scrolling). Behavioral mimicry is often subtler than surface mimicry but more durable — the behavior carries the recognition without depending on visual style.
Functional mimicry. The new design does what the source does. A "shopping cart" in an e-commerce site mimics the function of a supermarket cart: collect items, decide what to buy, check out. A "notebook" in a journaling app mimics the function of a paper notebook: record thoughts, organize by date or topic. The mimicry is conceptual — the user understands the new tool because they understand the source's function.
A successful mimicry usually combines layers: a shopping cart is functionally a cart, looks at least vaguely like a cart (icon), and behaves like one (you add items, then check out). The layers reinforce each other.
Mimicry pays off most clearly when the source is universally understood and the new medium genuinely benefits from the analogy.
The source is universally understood. The trash can, the folder, the cart, the book, the pencil. When the source is something nearly every user has encountered, mimicry is essentially free. When the source is specialized (a knob mimicking an analog audio-mixer fader, in an interface for non-audio-engineers), mimicry teaches less than it might seem to.
The new medium genuinely benefits from the analogy. Hypertext genuinely benefits from "page" and "link" metaphors borrowed from books. The desktop metaphor genuinely benefited from "folder" and "document" metaphors borrowed from paper offices. The analogy isn't just decorative — it gives users a useful mental model for navigating the new medium.
The analogy doesn't carry forward limitations. A digital folder doesn't have to be limited to one location (a file can have multiple "tags," unlike a physical document). A digital trash can doesn't have to be emptied physically. Successful mimicry often borrows the recognizable parts of the source while shedding limitations the new medium doesn't have.
Mimicry fails in a few characteristic ways.
The analogy is forced. A music app where the mixer view is styled like a 1980s analog mixer board — knobs, faders, panels, all rendered in 3D. New users don't recognize the references (they've never used an analog mixer). Old users find it kitschy. The mimicry was designed for an audience that no longer exists.
The analogy carries limitations the new medium doesn't have. An e-reader that mimics page-turning so faithfully that you can't search across pages, or scroll through content, or jump to a chapter. The visual analogy locks the interface into the limitations of the physical book, sacrificing the digital advantages.
The analogy obscures the actual functionality. A note-taking app styled to look like a physical legal pad but with rich-text formatting, embedded images, and AI auto-summaries. Users see the legal-pad surface and assume the functionality is also paper-like; they don't discover the AI features because the visual mimicry tells them not to expect them.
The analogy is misleading. A "trash can" icon for an action that doesn't actually delete (it removes from view but keeps the data). The user, primed by the mimicry, thinks the data is gone and is then surprised to find it. The mimicry created false expectations.
Mimicry of mimicry. A new design that mimics an established software design that itself mimicked something physical. Eventually the chain of references is so abstracted that no one remembers the original source, and the design is just inheriting forms without understanding why. Question whether the original mimicry is still serving its purpose.
Skeuomorphism — visual mimicry of physical objects, often very literal — was the dominant interface aesthetic in the late 2000s and early 2010s. iOS 6 had felt-textured Game Center, leather-bound Calendar, and a Notes app styled like a yellow legal pad. iOS 7 (2013) deliberately stripped much of this away in favor of "flat" design.
The shift wasn't a rejection of mimicry as a principle; it was a rejection of literal surface mimicry in favor of behavioral and functional mimicry. The flat-design era kept the underlying metaphors (folders are still folders, the trash can is still the trash can) but stopped rendering them with leather, paper, and shadow. The reasoning: by 2013, users no longer needed the literal visual reference to understand the metaphor — they had years of accumulated experience with the abstract version.
This is a useful lesson about mimicry's lifecycle. Strong literal mimicry helps when the source is the user's primary reference; it becomes optional once users have internalized the metaphor; it becomes anachronistic when the source has faded from common use.
A note-taking app uses functional mimicry of the paper notebook (you write notes; notes are organized by topic or date) and behavioral mimicry of the paper experience (typing feels responsive, the cursor advances as you type, the page scrolls naturally). It does not visually mimic paper (no fake paper texture, no lined background by default) — modern users don't need the visual reference. And it adds digital affordances that paper doesn't have (search across all notes, tags, automatic backup, sharing).
This is mimicry done well: borrowing what helps users understand the tool, shedding limitations that don't apply, adding capabilities the source didn't have.
A digital audio workstation styled to look like a physical hardware mixer: 3D knobs, fader strips, LED meters, wood-paneled bezels. Old audio engineers find it nostalgic; new users find it bewildering — they have no idea what the knobs do because they've never used a hardware mixer. The mimicry is teaching nothing.
The fix is to abandon the surface mimicry and use modern UI conventions for the controls (sliders, value displays, clear labels) while preserving the underlying functional model (channels, buses, sends) that the source genuinely contributes.
A calendar app uses the standard month-grid, week-column, and day-detail views that every calendar app has used for decades. The mimicry isn't of physical calendars (no fake leather binding); it's of the category-conventional digital calendar. Users from any other calendar app are immediately at home.
This is mimicry of an established software pattern rather than a physical object — and it's just as valuable. The user's accumulated learning across other calendar apps transfers directly.
In macOS, "smart folders" are saved searches that look and behave like folders but contain results of a query rather than a fixed set of files. The interface mimics the folder enough that users understand the affordance (you can browse it, drag from it) but extends the metaphor to do something paper folders can't (auto-update with new matching files).
The mimicry is partial: enough to get the user started, with explicit framing ("smart folder") to signal the difference. The user gets the recognition benefit and the new capability.
The card pattern (a rectangular container with content, often with a slight shadow) mimics physical cards (index cards, business cards, playing cards) at the visual level. The behavioral mimicry is partial: cards in a feed can be swiped (like flicking a physical card aside) or tapped to expand. The mimicry is loose enough not to constrain the digital affordances (cards can have video, animations, interactive elements) but tight enough to give users an instant mental model.
This has become one of the dominant UI patterns of the mobile era. The mimicry of a familiar physical object proved durable.
Mimicry that prevents discovery of new affordances. A digital book that looks so much like a paper book that users don't try to search, scroll, or jump. The visual mimicry tells them to expect paper-book limitations.
Mimicry of obsolete sources. The floppy disk for save in 2026. The mailing-envelope icon for email when most users have never sent physical mail. These references are increasingly mysterious to users who've never encountered the source.
Visual mimicry without behavioral mimicry. A button that looks like a physical button (3D bevel, shadow) but doesn't actually depress when you click it, or clicks with an unconvincing animation. The visual promise isn't kept by the behavior.
Behavioral mimicry without visual mimicry. A slider that physically follows your finger (good behavioral mimicry) but is rendered as an abstract line with no clear indication that it's draggable. The visual doesn't suggest the behavior.
Mimicry of an analogy that doesn't fit. A "wallet" metaphor for a tool that doesn't actually hold cards — perhaps it shows balances or transactions but doesn't store payment methods. The analogy creates expectations the tool doesn't meet.
Pure decoration disguised as mimicry. Adding fake paper textures or leather backgrounds because they "look classy," with no functional justification. Decoration is fine, but don't claim it's mimicry; mimicry has a job to do.
Before reaching for a mimicry, ask: What is the source, and is it universally understood by my audience? If not, the mimicry teaches less than it seems to. What does the mimicry actually communicate — function, behavior, or just visual style? Be deliberate about which layer you're using. Does the source's limitations apply to the new medium? If not, shed them. Is the mimicry necessary? If users would understand the new design just as well with modern abstract conventions, the mimicry may be decoration rather than communication. Has the source faded from common experience? If so, the mimicry may be becoming a barrier rather than an aid.
references/lineage.md — origins in skeuomorphic design and metaphor theory.mimicry-surface/ — sub-skill on visual mimicry.mimicry-behavioral/ — sub-skill on behavioral mimicry.© 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 of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 78497e5
Mimicry 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 this skillhashgraph-online/awesome-codex-plugins | 1.2k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode | 7.4k | 3 repos | ~3k | Automated safety check: Pass | MIT | |
| Story Toolbox Routerzenstory-ai/oh-story-claudecode | 7.4k | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Short Web Fiction Trend Scanzenstory-ai/oh-story-claudecode | 7.4k | 3 repos | ~1.2k | Automated safety check: Pass | MIT | |
| InkOS Creative HarnessNarcooo/inkos | 10k | 1 repos | ~1.1k | Automated safety check: Pass | AGPL-3.0 | |
| Novel Arteternityspring/shuohao-skills | 4.2k | — | ~1.1k | Automated safety check: Notes | Apache-2.0 |
zenstory-ai/oh-story-claudecode
Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.
zenstory-ai/oh-story-claudecode
Routes a Chinese web-novel writing request to the matching tool in a 13-skill toolbox, covers author habit memory, and can launch a local dashboard for browsing a project.
zenstory-ai/oh-story-claudecode
Scans popular short web-fiction rankings on Chinese platforms such as Dianzhong and Heiyan to surface trending emotional hooks, themes and topic candidates with an expiry warning.
Narcooo/inkos
Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.
eternityspring/shuohao-skills
给 AI 短剧出美术设定集(场景 + 叙事道具):场景的设计意图、一致性锚点、光照时段变体、 空景提示词;道具的戏剧功能、状态变体、尺度参照、白底无手提示词。
zenstory-ai/oh-story-claudecode
Rewrites AI-sounding Chinese web novel text so it reads naturally, changing as little as possible and keeping plot, names and numbers intact.
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 the principle of Mimicry — borrowing the form, behavior, or visual language of something familiar to make a new design recognizable. Mimicry is an agent skill from hashgraph-online/awesome-codex-plugins. Apply the principle of Mimicry — borrowing the form, behavior, or visual language of something familiar to make a new design recognizable.
Mimicry fits situations like: introducing a novel feature whose function would be opaque without an analogy; choosing between metaphor and convention; designing for a category your users already know; evaluating whether a skeuomorphic element helps.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill mimicry -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/mimicry in hashgraph-online/awesome-codex-plugins) into .claude/skills/mimicry in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill mimicry -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/mimicry in hashgraph-online/awesome-codex-plugins) into .agents/skills/mimicry 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 -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, .gemini/skills/mimicry, .github/skills/mimicry and .opencode/skills/mimicry in your project.
SKILL.md names no scripts, command-line tools or credentials: Mimicry 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 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 3.5k tokens (SKILL.md is roughly 14k 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 1.9k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Mimicry: Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.4k stars), Story Toolbox Router (zenstory-ai/oh-story-claudecode, 7.4k stars), Short Web Fiction Trend Scan (zenstory-ai/oh-story-claudecode, 7.4k stars) and InkOS Creative Harness (Narcooo/inkos, 10k 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.