Agent skill

Openkb Deck Neon

by VectifyAI in VectifyAI/OpenKB

A skill your agent uses when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow /…

Apache-2.0Auto-check passedFrontend & Design

Install Openkb Deck Neon

skills CLI
$ npx skills add VectifyAI/OpenKB --skill openkb-deck-neon -a claude-code

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

GitHub CLI
$ gh skill install VectifyAI/OpenKB openkb-deck-neon --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/VectifyAI/OpenKB.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openkb-deck-neon .claude/skills/openkb-deck-neon && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
openkb-deck-neon
GitHub stars
4.8k
Used in
1 other repo
Token cost
~4.3k tokens
SKILL.md length
2,081 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow /…

  • Works in 3 steps: Aurora: 3–4 blurred radial-gradients in… → Grain: an inline SVG feTurbulence noise… → Optional faint dot-grid via…
  • The user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark
  • SKILL.md covers How this skill is invoked, Required output, Design system: Aurora Glass and Slide grammar (7 permitted…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Openkb Deck Neon is an agent skill from VectifyAI/OpenKB. Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷). Generates a polished single-file HTML deck in the Aurora Glass visual direction (near-black background, teal/sky/magenta/amber neon accents, glassmorphism panels, aurora gradient atmosphere) — opened in a browser, full-screened, shared. For the warm, printed, serif look use openkb-deck-editorial…

Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering Slides and decks, Deep research and Typography. The repository describes itself as: OpenKB: Open LLM Knowledge Base. The licence is Apache-2.0.

When your agent uses it

  • The user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark
  • Neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷)

Example prompts

  • “/openkb-deck-neon”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Aurora: 3–4 blurred radial-gradients in teal / sky / magenta / amber,
  2. Grain: an inline SVG feTurbulence noise data-URI at opacity:.04
  3. Optional faint dot-grid via radial-gradient background, alpha < .06.

What it can do on your machine

Read from SKILL.md and the folder at commit ff54396. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are css).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Openkb Deck Neon loads about 4.3k tokens when it runs. Until then it costs about 164 tokens; SKILL.md has 2,081 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~164
When it runs · the whole SKILL.md, loaded when a task matches
~4.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from VectifyAI/OpenKB at commit ff54396, republished under its Apache-2.0 licence (© VectifyAI). 2,081 words, ~4,252 tokens.

Download SKILL.mdSave it as .claude/skills/openkb-deck-neon/SKILL.md (or your agent's skills folder).
name
openkb-deck-neon
description
Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷). Generates a polished single-file HTML deck in the Aurora Glass visual direction (near-black background, teal/sky/magenta/amber neon accents, glassmorphism panels, aurora gradient atmosphere) — opened in a browser, full-screened, shared. For the warm, printed, serif look use openkb-deck-editorial instead. Does NOT apply to generating skills (`openkb skill new`), research reports, or scrolling long-form documents.
od.mode
deck
od.output_path_template
output/decks/{slug}/index.html

Aurora Glass deck skill

You are designing a presentation, not writing a research report. Each slide carries one idea. In this visual direction, light, color and glow organize the slide — dark canvas holds it, neon points the eye, glass adds depth.

How this skill is invoked

The user typed something like "make a deck about X" (and asked for a dark / neon / 科技 look) inside openkb chat. You have wiki-read tools in your normal tool set, plus a write_file tool that can write under output/**, plus a tool to read this SKILL.md and files in skills/openkb-deck-neon/ if needed.

Pick a kebab-case slug (e.g. okf-pitch) and write the output to output/decks/<slug>/index.html.

Required output

Exactly one file: output/decks/<slug>/index.html.

It must be self-contained: NO external <link rel="stylesheet">, NO external <script src>, NO remote <img>, and NO web fonts (no Google Fonts link — that is an external link and breaks self-containment). All CSS in one inline <style>; keyboard-nav JS in one inline <script> at end of <body> (no scaling script needed — CSS fills the viewport). Use the local font stacks in §Type system — do not reach for Inter, Chakra Petch, Orbitron, or any fonts.googleapis.com import.

The body is a sequence of <section class="slide" data-type="..."> blocks; each data-type is one of the 7 values in §Slide grammar. Keyboard nav: ← / → move between slides, F toggles fullscreen, P triggers print.

Design system: Aurora Glass

Use this fixed design system. Do not improvise nearby colors, do not add a fifth accent hue, do not bring in emojis. Glow and gradient are allowed here (unlike the editorial skill) — but they are seasoning, not the meal.

Color palette
css
:root {
  --bg:      #080b11;  /* near-black blue — the canvas, never pure #000 */
  --bg-elev: #0f141d;  /* raised surface / slide inner */
  --ink:     #eef2f7;  /* primary text — body copy uses THIS, not muted */
  --soft:    #aeb8c7;  /* secondary text */
  --muted:   #69748a;  /* labels / folio / metadata */
  --line:    rgba(255,255,255,.09);  /* hairline borders */
  --glass:   rgba(255,255,255,.04);  /* glassmorphism fill */
  --teal:    #2dd4bf;  /* PRIMARY accent */
  --sky:     #38bdf8;  /* secondary accent */
  --magenta: #e879f9;  /* tertiary accent */
  --amber:   #f6b94b;  /* highlight / numbers-in-code only */
}

These 4 neon hues + the neutrals are the only colors. No purple-on-white gradients, no rainbow, no per-slide recoloring.

Type system (local fonts only — NO web fonts)
css
--font-display: ui-sans-serif, system-ui, -apple-system, "Segoe UI", Roboto,
                "PingFang SC", "Microsoft YaHei", sans-serif; /* heavy weights */
--font-mono:    ui-monospace, "SF Mono", "JetBrains Mono", Menlo, Consolas,
                monospace;  /* labels, numbers, code, kickers */

Display titles use --font-display at weight 800 with letter-spacing:-.02em. The tech character here comes from mono for every label / number / kicker / code, not from a fancy downloaded display face.

Type scale — use clamp() so type scales with the viewport (fixed px look tiny on a 2560px screen). vw drives the middle value; the rem caps keep it sane:

  • --type-display: clamp(2.8rem, 5.2vw, 5.5rem) / 1.05 — cover/chapter titles
  • --type-title: clamp(1.9rem, 3.2vw, 3rem) / 1.12 — normal slide titles
  • --type-body: clamp(1.05rem, 1.4vw, 1.4rem) / 1.6 — body copy (var(--ink))
  • --type-quote: clamp(1.6rem, 2.6vw, 2.2rem) / 1.35 — pull quotes
  • --type-label: size clamp(.66rem,.8vw,.8rem), letter-spacing:.22em, uppercase, mono — label tracks
Atmosphere (fixed background layers on every slide)
  1. Aurora: 3–4 blurred radial-gradients in teal / sky / magenta / amber, low alpha (.10–.16), filter: blur(14px). Positioned off the title.
  2. Grain: an inline SVG feTurbulence noise data-URI at opacity:.04 (data-URI is inline, NOT an external image — allowed).
  3. Optional faint dot-grid via radial-gradient background, alpha < .06.

These three layers are what stop the dark background from looking flat/cheap.

Frame (every slide)
  • Every slide fills the entire viewport — edge to edge, no letterbox, no fixed card. The slide IS the window; design for a wide canvas and let flexbox + clamp() sizing adapt to any window ratio:
    css
    html,body{height:100%;margin:0;overflow:hidden;background:var(--bg)}
    .slide{position:fixed;inset:0;display:none;flex-direction:column;
      justify-content:center;
      padding:clamp(40px,5vh,72px) clamp(56px,5vw,128px)}
    .slide.active{display:flex}
    No scaling/transform tricks — CSS alone fills the viewport. On an ultrawide window the slide is simply wider than 16:9; content reflows and the dark background + aurora bleed to all four edges — never a centered card with dark side-bands. One slide visible at a time; ← / → swap the active slide, F fullscreen, P print (they do not scroll).
  • The aurora, dot-grid, top label row and the bottom signature bar all span the FULL viewport width (they live on .slide, which is the whole window). Inner padding uses the clamp() values above so content breathes on any size.
  • One screen, no scroll — content MUST fit the viewport height. With overflow:hidden + justify-content:center, a slide taller than the window is clipped at BOTH top and bottom and is unreachable. Stay within the bullet/word caps (§Failure modes), lean on the vh terms in the type scale so text shrinks on short viewports, and if a slide would overflow, CUT content — never let it clip.
  • Visual signature: a glowing 3px bar along the bottom edge, gradient teal → sky → magenta, with box-shadow:0 0 14px of --teal. This is the deck's signature — present on every slide.
  • Top label row (mono, --muted): left = chapter id ("CHAPTER 03"), right = source mark. Cover/closing use "OPENKB" on the left instead.
  • Bottom folio row (mono): left = N / Total, right = source short label.
Glow & glass rules (read this — it is the #1 failure mode)
  • Glow only the protagonist of a slide: the display title, the one big number, graph nodes. Body copy, labels, tables NEVER glow. A slide where everything glows reads as blurry mush.
  • Glass (--glass fill + backdrop-filter:blur(8px) + 1px --line border + subtle inset highlight) is for compare columns and data cards only.
  • Gradient text (teal→sky→magenta via background-clip:text) is reserved for cover / chapter / closing big titles and data numbers — not for body.
Composition rules

Use the WHOLE canvas — never a left sliver with a big empty right half. This is the #1 layout failure under fill-viewport. Every slide must span the width via ONE of these (vary them across the deck):

  • Split — default for thesis / chapter / closing (and cover when it has a visual). A 2-column grid that fills the slide: .inner{display:grid; grid-template-columns:1.05fr .95fr; gap:clamp(40px,5vw,96px); align-items:center; width:100%; max-width:min(1600px,92vw); margin:0 auto}. Text in one column; a first-class VISUAL in the other — a big labeled stat, a schema/spec table, stacked labeled cards, or a simple diagram — sized width:100% to fill its column, NEVER a thumbnail in a corner. Build the visual with HTML + CSS (flex/grid); put every label in its own HTML box so boxes auto-wrap and auto-space and never collide. Do NOT put text in <svg><text> — SVG text does not wrap or reflow, so multiple labels in a narrow column overlap into an unreadable smear. Use SVG ONLY for lines / arrows / shapes between the HTML boxes (or skip SVG). Keep it to ≤4 nodes/cards with SHORT labels (node ≤2 words, caption ≤4 words); if labels run long or there are many, use a VERTICAL stack of full-width rows, never a cramped horizontal graph.
  • Full-bleed headline — cover, big thesis. The gradient display title spans ~70vw across the upper canvas; subtitle + a thin full-width detail row (kicker / stat strip / row of chips) beneath. The title fills the width, so there is no right-hand void.
  • Centered focus — data, quote. .inner{max-width:min(900px,72vw); margin:0 auto; text-align:center} with SYMMETRIC breathing room on both sides (never one-sided dead space).
  • compare — .inner{max-width:min(1180px,90vw); margin:0 auto; display:grid; grid-template-columns:1fr 1fr; gap:clamp(24px,3vw,56px)}, with the glowing teal rule between columns.

Per-slide self-test: is there a large empty right half? Then the layout is wrong — widen the headline, add the visual column, or center it. The closing diagram, compare columns, and any flow/graph MUST fill their region, never shrink to a corner. Never size a content box to min-content/fit-content (collapses to a sliver).

  • data big number: give it its OWN width — display:inline-block; width:max-content; max-width:92vw; white-space:nowrap; margin:0 auto — so it is NOT clipped by the .inner text column, and (with background-clip:text) the gradient covers the WHOLE string instead of stopping at the column edge and leaving the last char unpainted/smeared under the glow. Size a SINGLE number with clamp(3.5rem,11vh,9rem); a COMPARISON number (A → B, A vs B) is far wider — drop it to clamp(2.4rem,7vh,5.5rem) and keep the whole string (incl. the trailing %) inside 92vw, never overflowing. Body beneath stays centered in the .inner as a readable ~3-line paragraph.
  • Cover/chapter titles never wrap an article ("the"/"an"/"to") onto its own line.
  • Contrast: body is --ink on --bg; never body copy in --muted/--soft (exception: quote pull-quotes and cover/closing subtitles may be --soft).
Show full SKILL.md (842 more words)Show less

Slide grammar (7 permitted data-type values)

data-typeUseNeon signature
covertag + huge gradient title + 1-line subtitlestrongest aurora; mono "OPENKB" top-left; gradient display title
chaptersection divider: oversize number + namenumber clamp(4rem,12vh,9rem) mono, teal with glow; name in --type-display
thesisone claim + short explanationtitle fills ~60% height; ONE keyword in teal+glow; rest --ink
quoteitalic pull-quote + attributioncentered; left teal glowing vertical rule; quote in --soft
comparetwo-column comparison, 3–5 lines eachtwo glass panels; glowing teal vertical rule between them
dataone number + label + one-line readsingle number clamp(3.5rem,11vh,9rem); comparison A → B clamp(2.4rem,7vh,5.5rem); width:max-content;max-width:92vw (per §Composition); micro-copy in --type-label
closingmirrors cover; thanks / next stepsame scale as cover; aurora dims toward calm

Cover/closing have no chapter context → top-left label is "OPENKB".

Working method

  1. Survey first. Use wiki-read tools to list concepts/ and summaries/ and read wiki/index.md. Build a mental map before deciding the argument.
  2. Choose a narrative arc. One-line thesis, then an 8–12 step arc. Each step → 1–2 slides, landing 8–15 slides total.
  3. Read the relevant content. For each concept the arc touches, read the concept page; for cited documents read a targeted slice. The deck is only as expert as the source-reading you do here. Generic restatements are a failure mode — name a specific technique, number, or quote on each slide.
  4. Outline slides with concrete data-type assignments. Vary types — ≥4 distinct, no run of 3+ consecutive same type.
  5. Write output/decks/<slug>/index.html in one write_file call. Inline all CSS, inline keyboard-nav JS, inline <svg> for any graphics, inline noise as a data-URI. No external anything.
  6. Revise against §Failure modes; touch at least one slide if any match.
  7. Self-check the invariants below; fix anything failing.
  8. Report the deck path + a one-line summary of the arc.

Failure modes (negative checklist)

  1. External fonts/assets — any fonts.googleapis.com, <script src>, <link>, or remote <img>. Breaks self-containment AND the deck validator. Use the local stacks; the look does not depend on a downloaded font.
  2. Glow soup — more than the protagonist glowing. Body/labels/tables flat.
  3. Low contrast — body text in --muted/--soft on dark. Body is --ink.
  4. Palette drift — any hue outside teal/sky/magenta/amber + neutrals; purple-gradient-on-white; emoji; per-slide recoloring.
  5. Bullet dump — >5 bullets. Cut to 3 or restructure into compare/data.
  6. Wall of text — slide body >~80 words. Cut or split.
  7. Visual monotony — 3+ consecutive slides of one data-type.
  8. Decorative-only viz — an SVG/graph that says nothing. If you draw a graph, its nodes/edges must encode real concepts/links from the KB. On a single slide prefer a small, exact, hand-placed SVG over a fake "force layout".
  9. Generic titles — "Introduction"/"Background". Titles carry content.
  10. Definition-grade content — "X is Y where Y is…" with no named technique, number, or source quote. Re-read sources (step 3) first.
  11. Letterbox / fixed-size card — capping the slide with max-width or a fixed 1280×720 box, leaving dark side-bands on a wide window. Slides are position:fixed;inset:0 and fill the viewport edge-to-edge (§Frame).
  12. Collapsed content column — a centered / data box sizing to min-content or a tiny max-width, squashing text into a narrow sliver on a wide screen (and breaking big numbers). Wrap content in an .inner with an explicit max-width (§Composition); big numbers white-space:nowrap.
  13. Invalid SVG sizing — height="auto" written as an SVG attribute (invalid; fires a console error). Give inline SVG a viewBox and size it with CSS (width:100%;height:auto in a style) or fixed width/height attributes — never height="auto" as an attribute.
  14. Left sliver / right void — content crammed into a left column with a large empty right half (the worst look). Use a split / full-bleed / centered layout (§Composition) so the right half is content or symmetric space.
  15. Overflowing big number — a data comparison number (A → B/A vs B) at the single-number font size overruns its container; the trailing % falls outside the background-clip:text gradient and smears under the glow. Give the number width:max-content; max-width:92vw and the smaller comparison font size (§Composition).
  16. Overlapping diagram labels — text placed in <svg><text> (which never wraps) so multiple labels in the narrow visual column collide into a smear. Build the visual in HTML/CSS with each label in its own auto-spaced box; use SVG for lines/shapes only, ≤4 nodes, short labels (§Composition).

Self-check (before reporting back)

  1. Does output/decks/<slug>/index.html exist with NO external <link>/<script src>/web-font import/remote <img>?
  2. At least one data-type="cover" and one data-type="closing"?
  3. Total slide count between 8 and 15?
  4. At least 4 distinct data-type values, no run of 3+ same?
  5. Is body copy in --ink (readable on dark) — quote pull-quotes and cover/closing subtitles in --soft being the only allowed exceptions — and is glow limited to titles / big numbers / graph nodes only?
  6. Do slides fill the viewport edge-to-edge (position:fixed;inset:0, no max-width / fixed 1280px box, no letterbox side-bands)?
  7. Is content wrapped in an .inner with an explicit max-width — no narrow sliver / min-content collapse, and big numbers white-space:nowrap?
  8. Does every slide use the full width (split / full-bleed / centered) with NO large empty right half, and do text-heavy slides carry a visual?

If any answer is no, revise and re-run this self-check.

© VectifyAI, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/openkb-deck-neon of VectifyAI/OpenKB.

Open the folder on GitHubat commit ff54396

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in VectifyAI/OpenKB, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Openkb Deck Neon 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.

Openkb Deck Neon compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openkb Deck Neon this skillVectifyAI/OpenKB4.8k1 repos~4.3kAutomated safety check: PassApache-2.0
Swiss Creative Mode Templatenexu-io/open-design100k—~563Automated safety check: PassApache-2.0
Visualizedisplay-dev/visualize136—~7.4kAutomated safety check: PassMIT
Design Style Skillhaojing8312/WorkClaw1411 repos~1.1kAutomated safety check: PassApache-2.0
Pro Deck Builderthatrebeccarae/claude-marketing162—~6.1kAutomated safety check: PassMIT
Design SystemOhh-889/skyroc79511 repos~1.7kAutomated safety check: PassMIT

Similar skills

  • Swiss Creative Mode Template

    nexu-io/open-design

    Swiss-inspired creative-mode presentation template skill with bold editorial typography, high-contrast geometric cards, interactive slide navigation, theme switching, hotspot overlays, and palette…

    100k GitHub stars~563 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Visualize

    display-dev/visualize

    Generate beautiful, on-brand HTML artifacts — reports, diagrams, diff reviews, slide decks, plans, recaps, dashboards.

    136 GitHub stars~7.4k tokensUpdated 23 days ago
    Frontend & DesignAuto-check passed
  • Design Style Skill

    haojing8312/WorkClaw

    Select a consistent visual design system for PPT slides using radius/spacing style recipes.

    141 GitHub starsUsed in 1 repo~1.1k tokens
    Frontend & DesignAuto-check passed
  • Pro Deck Builder

    thatrebeccarae/claude-marketing

    Create polished HTML slide decks and PDF-ready documents for consulting deliverables.

    162 GitHub stars~6.1k tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed
  • Design System

    Ohh-889/skyroc

    Token architecture, component specifications, and slide generation.

    795 GitHub starsUsed in 11 repos~1.7k tokens
    Frontend & DesignAuto-check passed
  • Theme Factory

    anthropics/skills

    Official

    Applies one of ten preset color and font themes to slide decks, documents or HTML pages, or creates a new theme on the fly after you choose from a showcase.

    180k GitHub starsUsed in 48 repos~781 tokens
    Frontend & DesignAuto-check passed

More from VectifyAI/OpenKB

  • Openkb Deck Editorial

    VectifyAI/OpenKB

    A skill your agent uses when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content.

    4.8k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed
  • Openkb

    VectifyAI/OpenKB

    A skill your agent uses when the user asks about content in their OpenKB knowledge base — research topics, concepts compiled from their documents, cross-document synthesis — or mentions openkb, an…

    4.8k GitHub starsUsed in 1 repo~2k tokens
    Auto-check: warnings
  • Openkb HTML Critic

    VectifyAI/OpenKB

    A skill your agent uses to review a generated HTML deck or single-page artifact for visual quality and structural correctness.

    4.8k GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed

Questions about Openkb Deck Neon

What does Openkb Deck Neon do?

A skill your agent uses when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow /…. Openkb Deck Neon is an agent skill from VectifyAI/OpenKB. Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷).

When should I use Openkb Deck Neon?

Openkb Deck Neon fits situations like: the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark; neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷).

How do I install Openkb Deck Neon in Claude Code?

Run `npx skills add VectifyAI/OpenKB --skill openkb-deck-neon -a claude-code`. Or copy the skill folder (skills/openkb-deck-neon in VectifyAI/OpenKB) into .claude/skills/openkb-deck-neon in your project. Claude Code loads it when a task matches its description.

How do I install Openkb Deck Neon in Codex?

Run `npx skills add VectifyAI/OpenKB --skill openkb-deck-neon -a codex`. Or copy the skill folder (skills/openkb-deck-neon in VectifyAI/OpenKB) into .agents/skills/openkb-deck-neon in your project. Codex loads it when a task matches its description.

Can I use Openkb Deck Neon in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VectifyAI/OpenKB --skill openkb-deck-neon -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openkb-deck-neon, .gemini/skills/openkb-deck-neon, .github/skills/openkb-deck-neon and .opencode/skills/openkb-deck-neon in your project.

What does Openkb Deck Neon need to run?

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

Does Openkb Deck Neon access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Openkb Deck Neon safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Openkb Deck Neon use?

Openkb Deck Neon is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Openkb Deck Neon use?

About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Openkb Deck Neon?

Skills that share tags, products or a category with Openkb Deck Neon: Swiss Creative Mode Template (nexu-io/open-design, 100k stars), Visualize (display-dev/visualize, 136 stars), Design Style Skill (haojing8312/WorkClaw, 141 stars) and Pro Deck Builder (thatrebeccarae/claude-marketing, 162 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openkb Deck Neon?

VectifyAI (a GitHub organization) maintains it in VectifyAI/OpenKB, which has 4,767 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on July 22, 2026.

Source: VectifyAI/OpenKB on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.