Angora media

Skill Aysnc-Labs/angora/.claude/skills/angora-media

A design system and site builder powered by Claude Code

Install

npx -y skills add Aysnc-Labs/angora --skill angora-media

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Process images from `inbox/` into the media system — read each image visually to generate alt text under 125 characters, extract dimensions, assign a nanoid filename, move the file to `public/media/`, and insert a row into the `media` table. Trigger whenever the user wants to process, pipeline, ingest, or register images from inbox (jpg, png, webp, avif, gif, svg). Phrases like 'process the photos in inbox', 'pipeline the hero images', 'generate alt text for the screenshots in inbox', 'get the product photos into the media table', 'handle the avatars in inbox' all trigger this. Do NOT use for importing CSV/JSON data (→ angora-import).

SKILL.md

3.0 KB, as published. Nobody here has run it

Media

Process images from the inbox/ directory into the media system.

Before you start

Check inbox contents — list inbox/ directory. If empty (only .gitkeep), report "Inbox is empty. Drop images into inbox/ and run this again."
Check current media table — run:

node -e "
  import db from './src/data/db.ts';
  import { media } from './src/data/schema/tables/media.ts';
  const rows = db.select().from(media).all();
  console.table(rows);
"

Pipeline (for each image)

1. Visual analysis

Read the image file with the Read tool (Claude vision). Write alt text:

Describe what's in the image, under 125 characters
Don't start with "Image of" or "Photo of"
Use alt="" for purely decorative images (backgrounds, dividers)

2. Read dimensions

node -e "
  import { imageSize } from 'image-size';
  const result = imageSize('inbox/<filename>');
  console.log(JSON.stringify(result));
"

Skip for SVGs (scalable — dimensions not meaningful).

3. Generate unique filename

node -e "
  import { nanoid } from 'nanoid';
  console.log(nanoid(8));
"

Preserve the original extension. Result: V1StGXR8.jpg

4. Move file

mv inbox/<original> public/media/<nanoid>.<ext>

5. Insert into media table

node -e "
  import db from './src/data/db.ts';
  import { media } from './src/data/schema/tables/media.ts';
  db.insert(media).values({
    path: 'media/<nanoid>.<ext>',
    alt: '<alt text>',
    type: 'image',
    width: <width>,
    height: <height>,
    sourceName: '<original filename>',
  }).run();
  console.log('Inserted.');
"

6. Summary table

After processing all images, show a summary:

Original	New path	Dimensions	Alt text
hero-bg.jpg	media/V1StGXR8.jpg	1920x1080	Dark gradient background with subtle grid pattern

Rules

Supported types: jpg, jpeg, png, gif, webp, avif, svg
SVGs: skip dimension reading (scalable), set type to svg
Never delete inbox files without explicit permission — ask after processing
Skip non-image files — report them: "Found non-image files: [list]. These can be processed with the import skill (/angora-import)."
Process images one at a time to ensure accuracy of alt text