Image To Editable Ppt
ningzimu/image-to-editable-ppt-skill
Rebuild slide images, scanned or image-based PPT/PPTX files, and PDF decks into object-level editable PowerPoint (.pptx), preserving speaker notes when supplied.
A skill your agent uses whenever a design has more than one element competing for the viewer's attention — which is essentially every design.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill hierarchy -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins hierarchy --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/perception-and-hierarchy-principles/skills/hierarchy .claude/skills/hierarchy && 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 "hierarchy" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/hierarchy into .claude/skills/hierarchy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hierarchy", 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/perception-and-hierarchy-principles/skills/hierarchyType 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 hierarchy -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins hierarchy --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/perception-and-hierarchy-principles/skills/hierarchy .agents/skills/hierarchy && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hierarchy" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/hierarchy into .agents/skills/hierarchy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hierarchy", 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 hierarchy -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins hierarchy --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/perception-and-hierarchy-principles/skills/hierarchy .cursor/skills/hierarchy && 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 "hierarchy" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/hierarchy into .cursor/skills/hierarchy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hierarchy", 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/perception-and-hierarchy-principles/skills/hierarchy--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 hierarchy -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins hierarchy --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/perception-and-hierarchy-principles/skills/hierarchy .gemini/skills/hierarchy && 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 "hierarchy" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/hierarchy into .gemini/skills/hierarchy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hierarchy", 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 hierarchyInstalls 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 hierarchy -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/perception-and-hierarchy-principles/skills/hierarchy .github/skills/hierarchy && 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 "hierarchy" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/hierarchy into .github/skills/hierarchy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hierarchy", 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 hierarchy -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 hierarchy --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/perception-and-hierarchy-principles/skills/hierarchy .opencode/skills/hierarchy && 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 "hierarchy" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/hierarchy into .opencode/skills/hierarchy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hierarchy", 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.
hierarchyA skill your agent uses whenever a design has more than one element competing for the viewer's attention — which is essentially every design.
Hierarchy is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill whenever a design has more than one element competing for the viewer's attention — which is essentially every design. Trigger when laying out a screen, page, slide, poster, dashboard, or any composition where you must decide what gets seen first, what supports it, and what recedes. Trigger when reviewing a design and the user says "everything looks the same," "I don't know where to look," "the page feels flat," or "what's the most important thing here?" Trigger when picking type sizes, when…
Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/research-and-cross-domain.md`).
It sits in Documents & Office, covering Slides and decks. 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.
3 steps, taken from the first numbered list in SKILL.md.
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 (its code samples are html and css).
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.
Hierarchy loads about 3.9k tokens when it runs, and up to ~5.8k if it reads all its reference files. Until then it costs about 212 tokens; SKILL.md has 1,700 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). 1,700 words, ~3,881 tokens.
.claude/skills/hierarchy/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Hierarchy is the ranking of importance among visible elements, made legible to the eye through differences in size, weight, color, contrast, position, density, and surrounding space. It is the single most decisive principle in visual design: when hierarchy is well-constructed, the rest of the layout almost designs itself; when it is missing, no amount of polish recovers the page.
A composition has visual hierarchy when the viewer can, at a glance and without instruction, identify a primary focal element, secondary supporting elements, and recessive background elements. Hierarchy is created by introducing deliberate differences along one or more visual dimensions (size, weight, color, position, density, motion). It is destroyed by making everything the same — and equally by making everything different at maximum intensity. Hierarchy is a contrast principle: emphasis is meaningful only against a quieter background.
The deliberate construction of visual hierarchy is one of the oldest practices in graphic communication. Its modern theoretical grounding draws from several lines of work:
The takeaway: hierarchy is not an aesthetic preference; it is a structural property that determines whether the composition will be readable at all.
When you scan a page, your eye is doing two things in rapid alternation: detecting salient features (high-contrast, isolated, unusual) and predicting meaningful features based on prior knowledge of the layout type. Hierarchy aligns those two: the salient features are the meaningful ones. Without that alignment, the viewer's eye is pulled to whatever is loudest (a stray red icon, a bold word, a big image) regardless of whether that thing is important.
The cost of weak hierarchy compounds: every visit, every screen, every interaction, the viewer pays a small tax to figure out what to look at. Multiply by daily users and the tax is significant.
Hierarchy is built by varying one or more visual dimensions across elements. Each dimension has different strengths and trade-offs:
| Dimension | What it does well | Cost / risk |
|---|---|---|
| Size | Strongest single signal; reads at any distance. | Cheap to overdo; gigantic headlines crowd context. |
| Weight | Strong, subtle, additive to size. | Bold-fatigue when overused; loses meaning if everything is bold. |
| Color (hue) | Carries categorical meaning; high attention pull. | Accessibility and cultural pitfalls; never the only signal. |
| Tone (value/contrast) | Most universal; works in monochrome and accessibility modes. | Subtle; needs other dimensions for headline-level emphasis. |
| Position | Top, center, leading edge — privileged by reading habits. | Real estate is finite; not every important thing fits at the top. |
| Whitespace / isolation | Gives an element room to breathe; reads as importance. | Costs space; can leave a layout thin if overused. |
| Density / repetition | Items repeated together read as a system; the lone item reads as primary. | Backfires if the "system" items become noise. |
| Motion | Strongest attention pull; cannot be ignored. | Easily overwhelming; accessibility (vestibular triggers, motion sensitivity); use sparingly. |
The competent use of hierarchy is stacking these dimensions: a primary heading is larger and heavier and darker and further from neighbors. A secondary action is medium-sized and outlined and placed left of the primary. Stacking compounds the signal; relying on a single dimension makes the hierarchy fragile.
A workable default for most compositions: aim for three levels of hierarchy.
Too few levels (everything primary, or everything tertiary) is flat. Too many levels (5+) blur into one another and the eye treats them as a continuous gradient rather than discrete ranks.
The examples below are framework-agnostic — written in plain HTML/CSS to make the principle decisions visible. Apply them to any framework.
A common case where weak hierarchy makes the page feel flat. Three elements; we want one to dominate.
Anti-pattern (flat):
<header class="page-header">
<h1 style="font-size: 1.25rem; font-weight: 500;">Invoices</h1>
<p style="font-size: 1.25rem; color: #555;">Sent and overdue, this quarter.</p>
<p style="font-size: 1.25rem; color: #555;">Last updated 3 minutes ago</p>
</header>Three lines all roughly the same size, weight, and color. The eye finds no focal point.
Right (three tiers):
<header class="page-header" style="display: grid; gap: 0.25rem;">
<h1 style="font-size: 1.875rem; font-weight: 600; line-height: 1.2;">Invoices</h1>
<p style="font-size: 0.95rem; color: #555;">Sent and overdue, this quarter.</p>
<p style="font-size: 0.8rem; color: #888; margin-top: 0.25rem;">Last updated 3 minutes ago</p>
</header>Now the title dominates by size + weight + tone. The subtitle supports it (smaller, mid-tone). The metadata recedes (smaller still, lower contrast). Three clear tiers, one focal point.
A frequent case in modal footers, form submissions, and toolbars. The wrong distribution of weight here is one of the most common UI mistakes.
Anti-pattern (all equal, eye doesn't know which to pick):
<div class="actions">
<button class="btn">Cancel</button>
<button class="btn">Save draft</button>
<button class="btn">Publish</button>
</div>Three same-styled buttons. The user must read all three labels and decide; primary intent is invisible.
Right (one primary, two recessive):
<div class="actions" style="display: flex; gap: 0.5rem; justify-content: flex-end;">
<button class="btn-ghost">Cancel</button> <!-- tertiary: text-only, low weight -->
<button class="btn-outline">Save draft</button> <!-- secondary: bordered, neutral -->
<button class="btn-primary">Publish</button> <!-- primary: filled, high contrast -->
</div>.btn-primary { background: #111; color: white; padding: 0.5rem 1rem; border-radius: 0.375rem; }
.btn-outline { background: transparent; border: 1px solid #d1d5db; padding: 0.5rem 1rem; border-radius: 0.375rem; }
.btn-ghost { background: transparent; border: 0; color: #555; padding: 0.5rem 1rem; }The primary action wins on color and weight. The secondary is recognizably a button (bordered) but quiet. Cancel is a soft escape — necessary but never the focal point.
Twelve KPI tiles, all the same. The eye gives up. Pick a primary KPI, make it dominate, let the rest recede.
<section class="dashboard" style="display: grid; gap: 1rem; grid-template-columns: repeat(4, 1fr);">
<article class="tile primary" style="grid-column: span 2; grid-row: span 2;">
<p class="label">Monthly revenue</p>
<p class="value" style="font-size: 3rem; font-weight: 600;">$48.2k</p>
<p class="delta" style="color: #16a34a;">+12% vs last month</p>
</article>
<!-- 8 secondary tiles, smaller, recessed -->
<article class="tile"><p class="label">Active users</p><p class="value">12,481</p></article>
<article class="tile"><p class="label">Churn</p><p class="value">2.1%</p></article>
<article class="tile"><p class="label">NPS</p><p class="value">42</p></article>
<!-- ... -->
</section>The primary tile spans 2x2 grid cells, has a 3rem value, includes a delta, and dominates the composition. The secondary tiles are smaller, single-line values, no delta. The eye reads the dashboard in seconds.
Even forms have hierarchy: the required path is primary; optional fields are secondary; help text is tertiary.
<form>
<fieldset class="primary">
<legend>Account</legend>
<label>Email <input type="email" required /></label>
<label>Password <input type="password" required /></label>
</fieldset>
<details class="secondary">
<summary>Profile (optional)</summary>
<label>Display name <input /></label>
<label>Bio <textarea></textarea></label>
</details>
<p class="tertiary" style="font-size: 0.8rem; color: #888;">
By signing up you agree to the Terms of Service.
</p>
<button class="btn-primary">Create account</button>
</form>Required fields are visible and primary. Optional fields are tucked behind a <details> disclosure (secondary). Legalese is tertiary in size and tone. The user's eye lands on the necessary path first.
A few quick checks for whether hierarchy is working:
filter: blur(8px)). Can you still see one element dominating? If not, hierarchy is too weak.alignment — hierarchy operates along a grid; misalignment fights hierarchy.proximity — proximity establishes grouping; hierarchy establishes ranking between groups.signal-to-noise-ratio — strong hierarchy increases SNR by making one thing carry the message.highlighting — emphasis works only when sparse; hierarchy is the systemic version.von-restorff-effect — the deliberately-different element is remembered; primary action of a composition leverages this.gutenberg-diagram — when hierarchy is absent, the eye falls back to the Z-pattern.hierarchy-typographic — type-scale, weight ladders, and how to construct hierarchy entirely through typography.hierarchy-spatial — using position, size, and whitespace to establish hierarchy.hierarchy-color-and-tone — using color, value, and contrast as a hierarchy dimension without sacrificing accessibility.Hierarchy is one of the few principles where "more is more" is genuinely a trap. The temptation is always to make the primary more primary — bigger, brighter, redder. This works once, briefly. After two or three uses the eye desensitizes and you're back where you started, but with a louder page. Restraint preserves the dimension you're spending. Spend it on the things that earn it.
© 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/perception-and-hierarchy-principles/skills/hierarchy of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 9e7b281
Hierarchy 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 |
|---|---|---|---|---|---|---|
| Hierarchy this skillhashgraph-online/awesome-codex-plugins | 1.3k | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | |
| Image To Editable Pptningzimu/image-to-editable-ppt-skill | 2.8k | — | ~4.3k | Automated safety check: Pass | MIT | |
| Slidesfcakyon/claude-codex-settings | 1.2k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Ppt Image FirstNyxTides/ppt-image-first | 1.2k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Vibe to Agentic Engineering Frameworkshanraisshan/claude-code-best-practice | 67k | — | ~3.3k | Automated safety check: Pass | MIT | |
| Gpt Image2 PptJuneYaooo/gpt-image2-ppt-skills | 1.3k | — | ~8.9k | Automated safety check: Notes | Apache-2.0 |
ningzimu/image-to-editable-ppt-skill
Rebuild slide images, scanned or image-based PPT/PPTX files, and PDF decks into object-level editable PowerPoint (.pptx), preserving speaker notes when supplied.
fcakyon/claude-codex-settings
Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities.
NyxTides/ppt-image-first
Build presentation plans for PPT / slides / decks through a conversation-first workflow, then propose multiple visual directions with preview images before writing deck specs.
shanraisshan/claude-code-best-practice
Explains the conceptual model behind a presentation on moving from unstructured vibe coding to fully configured agentic engineering, including its 4-level scoring system and slide conventions.
JuneYaooo/gpt-image2-ppt-skills
Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<collection/STYLEID.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx.
scunning1975/MixtapeTools
Create and compile beautiful Beamer presentations following the Rhetoric of Decks philosophy.
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
A skill your agent uses whenever a design has more than one element competing for the viewer's attention — which is essentially every design. Hierarchy is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill whenever a design has more than one element competing for the viewer's attention — which is essentially every design.
Hierarchy fits situations like: A design has more than one element competing for the viewers attention — which is essentially every design; laying out a screen; any composition where you must decide what gets seen first; what supports it.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill hierarchy -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/hierarchy in hashgraph-online/awesome-codex-plugins) into .claude/skills/hierarchy in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill hierarchy -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/hierarchy in hashgraph-online/awesome-codex-plugins) into .agents/skills/hierarchy 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 hierarchy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hierarchy, .gemini/skills/hierarchy, .github/skills/hierarchy and .opencode/skills/hierarchy in your project.
SKILL.md names no scripts, command-line tools or credentials: Hierarchy 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.
Hierarchy 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 3.9k tokens (SKILL.md is roughly 16k 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 Hierarchy: Image To Editable Ppt (ningzimu/image-to-editable-ppt-skill, 2.8k stars), Slides (fcakyon/claude-codex-settings, 1.2k stars), Ppt Image First (NyxTides/ppt-image-first, 1.2k stars) and Vibe to Agentic Engineering Framework (shanraisshan/claude-code-best-practice, 67k 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.