CONTENT / DOCS — DEM0NHUB

5

clip-search

Semantic search inside any video file. Sample frames, embed with CLIP, find moments matching a text query like "neon bathroom", "fire in a forest", or "person walking on beach". Outputs top-K timestamps + labeled thumbnails + 3s preview clips around each hit. Use when the user wants to find a moment in long footage, asks "where in this video does X happen", needs to scrub a movie/Reel/dump for a specific shot, or wants to build a B-roll search index for music-video editing.

Find moments in a video by *describing* them. CLIP under the hood.
```bash
python3 ~/.claude/skills/clip-search/scripts/search.py \

CONTENT / DOCS 15 DL

1

flicky

by @glo

Generate AND edit images using Google Nano Banana 2 (Gemini 3.1 Flash Image) via OpenRouter. TRIGGER when the user asks to generate, create, make, draw, render, produce, edit, restyle, modify, retouch, alter, change, enhance, combine, or remix any image, photo, picture, illustration, render, artwork, logo, icon, or visual. Also triggers on phrases like "give me a picture of", "make me an image", "generate a photo", "render this", "draw me", "edit this image", "change the background of", "make this look like", "combine these images", "flicky". Supports text-to-image, image editing with reference images, multi-image composition, parallel variations, and auto-opens results in Preview. Reads OPENROUTER_API_KEY from environment.

Generates AND edits images using **Google Nano Banana 2** (`google/gemini-3.1-flash-image-preview`) via the OpenRouter API. Saves PNGs to disk, auto-opens them in Preview, and returns the file paths.

CONTENT / DOCS 5 DL

0

zine-rip

by @gualo

Rip any Internet Archive zine/magazine/book collection into searchable per-page JPEGs + auto-cropped photo regions + an OCR keyword index, optionally imported into Photos.app. Built originally for the Unsound industrial-zine archive (1983-1986, 10 issues, 579 pages, 576 cropped photos) but works on any IA item with PDF + _text.pdf companions. Use when the user sends an archive.org/details/... URL or identifier and wants the source material as image refs, not as PDFs.

Turns any Internet Archive item containing PDFs into a clean, searchable, per-page image library — and pulls just the photographs out of each page if you want the visuals separated from text.
Given an

CONTENT / DOCS 16 DL

0

ref-rip

by @gualo

Multi-source reference image scraper. Pulls 100+ images in parallel from Internet Archive, DuckDuckGo (Google/Bing proxy), Bing Images, Pinterest, Film-Grab, FrameSet, Tumblr, Flickr, eBay, and tshirtslayer.com for any text query — e.g. "mugshot pictures of dogs", "Breaking Bad still", "vintage band tee". Each scrape uses a fresh seed for new options every run. Auto-scores by resolution + size + source bias and keeps the top N. Optional contact-sheet PNG preview.

Multi-source image reference scraper. Hand it a text query and it returns 100+ download options pulled in parallel from ten sources, deduped, quality-scored, and saved locally with a manifest.
| Sourc

CONTENT / DOCS 17 DL

0

screenshot-text

by @bat

OCR any image (or PDF page, or video frame) to plain text. Uses Tesseract under the hood. Handles screenshots, scanned docs, photos of text, video stills, code snippets in images. Multi-language support, auto-rotates skewed images, outputs plain text + word-level bbox JSON. Use when the user asks to "extract text from this image", "OCR this", "what does this screenshot say", "read this PDF", "transcribe this photo", or sends an image and wants the text out.

Image (or PDF, or video frame) → plain text. Powered by Tesseract.
```bash
python3 ~/.claude/skills/screenshot-text/scripts/ocr.py --input screenshot.png

CONTENT / DOCS 12 DL

0

asci-x

by @bat

Generate smooth animated ASCII visuals from arbitrary shapes, images, videos, logos, symbols, silhouettes, UI mockups, or text prompts. Use when the user asks for ASCI X, asci-x, animated ASCII, ASCII product-card animations, ASCII ghost trails, source-to-ASCII video loops, or browser-ready ASCII art that should move smoothly.

Create polished animated ASCII visuals from any supplied shape/source or from a prompt-only concept. Prioritize smooth motion, clean silhouettes, ghost trails, and browser-ready previews.
1. Identify

CONTENT / DOCS 13 DL

0

lut-snap

by @bat

Extract a color palette from any reference image and render it as a 3D LUT (.cube file) you can apply to footage in ffmpeg, Premiere, DaVinci Resolve, or Final Cut. Sample any movie still, album cover, or photo and turn its grade into a reusable LUT. Also previews the LUT applied to a target video. Use when the user wants to color match footage to a reference, generate a LUT from an image, recreate a movie's grade, or apply a film look to their clip.

Sample a reference image's color palette and bake it into a usable .cube LUT.
```bash
python3 ~/.claude/skills/lut-snap/scripts/lut_snap.py extract \

CONTENT / DOCS 13 DL

0

cover-art

by @bat

Generate album cover art with curated typography templates for rap/industrial/avant aesthetics. Templates by era (carti-die-lit, yeat-2093, drain-gang, industrial-noise, brutalist, lo-fi-zine). Takes an art image (or generates one via flicky) and overlays artist + title type. Outputs 3000x3000 print-ready cover. Use when the user wants album art, single cover, mixtape cover, EP cover, or stylized typography over an image.

Album cover generator. Curated type templates + your art (or AI-gen).
```bash
python3 ~/.claude/skills/cover-art/scripts/cover_art.py \

CONTENT / DOCS 13 DL

0

vhs-deck

by @bat

True VHS tape simulator — chroma bleed, RF interference snow, head-switching noise lines, time-base wobble, tape-stretch warble, scanline interlace artifacts, generation loss. Drop-in over any clip with intensity 0-3. Stronger than film-grain — emulates the actual physics of consumer VHS playback. Use when the user wants VHS, tape look, generation loss, head-switch noise, or full analog tape damage.

Real VHS pipeline. Not just grain + scanlines — chroma bleeding, head-switching, time-base errors.
```bash
python3 ~/.claude/skills/vhs-deck/scripts/vhs_deck.py \

CONTENT / DOCS 14 DL

0

dem0n-auhor

by @bat

Validate, package, and publish Codex or Claude skill folders to DEM0NHUB through the DEM0NHUB API. Use when the user asks to publish a skill, upload a skill to DEM0NHUB, package a skill tarball, validate skill metadata before release, check DEM0NHUB auth, list DEM0NHUB skills, or prepare a release version and notes for a skill directory.

Use this skill to release skill folders to DEM0NHUB without hand-writing tar/curl commands. It validates the skill shape, builds a clean `tar.gz` with `SKILL.md` at archive root, and posts it to the D

CONTENT / DOCS 15 DL

0

blender-3d-maker

by @30wontjam

Create, modify, render, and animate 3D objects with Blender. Use when the user asks for Blender work, 3D models, 3D items, cars, objects, product renders, characters, creatures, skulls, logos as 3D, turntable animations, spinning GIFs/videos, or work with .blend, .stl, .obj, .fbx, .glb/.gltf, .ply, or other 3D assets. Prefer this over fake 2D rotations when the user wants real 3D form.

Use Blender for actual 3D geometry, lighting, camera, materials, and rendering. Do not satisfy a real 3D request with a flat image squash/flip animation unless the user explicitly asks for a 2D sprite

CONTENT / DOCS 10 DL

0

ascii-edgy

by @glo

Use when the user asks for edgy, detailed, occult, cyber, or dark ASCII art — demons, skulls, daemons, sigils, crosses, reapers, cyber-skulls, ravens, spiders, grim symbols, goth creatures. Triggers on phrases like "make me an ascii demon", "ascii skull", "edgy ascii", "cyber ascii", "dark ascii", "scary ascii", "grimoire ascii", "occult ascii", "fire ascii", or any ascii-art request paired with a dark/sharp/metal subject. Produces dense, symmetric, terminal-native ASCII with heavy texture and sharp focal points — the IRIS / pentboyz / BBS-grimoire aesthetic. NOT cartoon emoji faces, NOT bloated giants, NOT soft. Trigger even if the user just says "ascii" with any dark subject attached.

The goal is ASCII that looks like it escaped a 1997 BBS, a cursed CRT, or the cover of a SYSTEM zine. Dense. Symmetric. Sharp. Menacing. Readable at a glance, rewards close inspection.
Every piece obe

CONTENT / DOCS 13 DL

0

Product Render — 3D-Tilted Animated Product Pages

by @gualo

Generate a professional, character-aware **Next.js product render page** with a 3D-tilted hardware/app/object mockup and subtle living animations — the same visual language as the GIR Studios hero/pan

CONTENT / DOCS 14 DL

0

red-pearl

by @glo

Audio-reactive spectrum visualizer. Dark, punk, VHS-graded music video from a single audio file — no asset scraping. Built on ffmpeg's showcqt/showspectrum/showwaves with chromatic aberration, moving scanlines, strobe flashes, vignette, hue drift. Six palettes, three intensity levels, 16:9 / 9:16 / 1:1.

Pure-ffmpeg audio visualizer. No asset scraping. Takes an audio file and emits a dark, punk/VHS-graded music video driven entirely by audio-reactive filters (showcqt + showspectrum + showwaves) with h

CONTENT / DOCS 15 DL

0

analyst-pdf

by @glo

Default PDF generator for this setup — produces high-design branded PDFs from any content (reports, decks, memos, analyses, pitches, diagnostics, one-pagers, briefs, audits, dossiers, research writeups, case studies). Black + hot-pink pentboyz/dem0nhub aesthetic with embedded custom fonts (Anton / Space Grotesk / Bebas Neue / JetBrains Mono), matplotlib SVG charts (radar, density, delta bars, heatmaps, donuts), metric tiles, keyword focus-highlighting, themeable. Powered by Jinja2 + headless Chromium. USE THIS WHENEVER THE USER ASKS FOR A PDF — "make a PDF", "turn this into a PDF", "export as PDF", "save as PDF", "PDF of this", "PDF report", "PDF version", "beat bible PDF", "pen bible PDF", "analyst deck", "branded report", "one-pager", "deck", "brief" — unless they specifically ask for plain/unstyled or a .docx/.pptx/.xlsx file. Has a `standard` template that accepts arbitrary section-based content and a `beat-bible` template for catalog audits. Add new templates for recurring report shapes.

**The default PDF generator.** Whenever the user wants a PDF, reach for this skill — it renders branded, publication-grade output with embedded fonts, inline SVG charts, and the pentboyz · dem0nhub de

CONTENT / DOCS 13 DL

CONTENTDOCS