Image Curator

Community

XuanRanL

image-curator

Produces image_metadata.json with all 4 WordPress media fields (title, alt_text, caption, description) per image slot. Runs AFTER image generation and BEFORE WordPress upload. Without this, captions and descriptions are empty in the media library and figcaptions never render in posts. Stage 27f of phase-publish image sub-pipeline.

Overview

Publisher	XuanRanL
Repository	`loamwright-SEO-Skill`
Skill name	`image-curator`
Stars	52
Forks	9
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by XuanRanL on GitHub. Read the source before you install it.

Installation

Install the Image Curator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/XuanRanL/loamwright-SEO-Skill/tree/main/subskills/image/image-curator
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/XuanRanL/loamwright-SEO-Skill/tree/main/subskills/image/image-curator

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/XuanRanL/loamwright-SEO-Skill.git /tmp/loamwright-SEO-Skill
mkdir -p .claude/skills
cp -r /tmp/loamwright-SEO-Skill/subskills/image/image-curator .claude/skills/image-curator

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Image Curator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Image Curator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Image Curator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Image Curator

Generates the 4-field metadata that the WordPress publisher requires on every image upload. This is non-optional: without curated metadata, the publisher uploads images with empty caption + description fields, and the media library record is SEO-incomplete.

Inputs

workspace/{task_id}/outline.json — section context for each slot
workspace/{task_id}/image_slots.json — slot allocation (cover + sections)
workspace/{task_id}/image_prompts.json — the prompts used to generate each image
workspace/{task_id}/research.json — entity intelligence, primary keyword
projects/{slug}/brand/brand-config.json — brand voice, banned competitor mentions

Output

workspace/{task_id}/image_metadata.json:

json
[
  {
    "media_id": null,
    "slot": "cover",
    "title": "{primary_keyword} {short_context}",
    "alt_text": "{accessibility-first description, ~120-180 chars, contains primary keyword naturally}",
    "caption": "{one short sentence visible under image, ~120-160 chars, reader-facing context}",
    "description": "{paragraph-length 400-1000 chars, includes technical entities + primary keyword + image's significance — populates the attachment page body}"
  },
  ...
]

media_id is null at this stage; the publisher populates it after the upload returns the WP media ID.

The four-field discipline

All four fields are required on every image. Each serves a distinct SEO + accessibility purpose:

Field	Length	Renders where	Purpose
title	≤80 chars, kebab-case-derived	Media library list, attachment page `<title>`	Internal identification + AI image search
alt_text	100–180 chars	`<img alt="">`	Screen readers + image SEO (primary keyword woven naturally)
caption	100–180 chars	`<figcaption>` under image in post	Reader-facing context; also `ImageObject.caption` schema
description	400–1000 chars	Attachment page body	Long-tail image-related queries; full technical context

The publisher will refuse to publish if any image has empty caption or empty description (blocking gate added in wp_publisher.py post-Stage 4).

Tone & voice

All four fields must match brand/brand-config.json voice:

Use brand-approved voice (NN-Group formality/humor/respectfulness/enthusiasm tuple)
Reference primary keyword naturally (not stuffed)
Include 1–2 technical entities from research.json in description (PPFD, DLC, OSRAM, etc.)
Respect ymyl_banned_phrases (no health claims, no yield guarantees, etc.)
Don't name banned_competitors in alt/caption/description

Handoff

recommended_next_skill: wordpress-publisher. The publisher reads image_metadata.json and passes all four fields to wp_media.upload() on each image upload.

Frequently asked questions

What does the Image Curator AI skill do?

Why use Image Curator on TypingMind?

Because you install it once and use it with any model. Image Curator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Image Curator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/XuanRanL/loamwright-SEO-Skill/tree/main/subskills/image/image-curator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Image Curator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Image Curator?

As many as you like. As long as a model supports skills, you can use Image Curator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Image Curator AI skill free?

Yes. It is published on GitHub by XuanRanL under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Accessibility

affaan-m

CommunityPopular

WCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。

Archify

Validated interactive HTML diagrams, upstream-maintained.

Auteur

Design and build cinematic, award-level web pages.

Concept Diagrams

Generate flat, minimal educational SVG visuals as HTML.

Image Curator

Overview