Imagery And Photo Treatment logo

Imagery And Photo Treatment

Community
andreworia
imagery-and-photo-treatment

Applies a single image treatment, aspect ratio, and duotone or filter rule so photos stop clashing in crop, color, and style.

Overview

Publisherandreworia
Repositoryclaude-pptx-skills
Skill nameimagery-and-photo-treatment
Stars
4
Forks
2
Bundled files
Instructions only
LicenseMIT
Links
  • 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 andreworia on GitHub. Read the source before you install it.

Installation

Install the Imagery And Photo Treatment AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/andreworia/claude-pptx-skills/tree/main/skills/imagery-and-photo-treatment
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/andreworia/claude-pptx-skills.git /tmp/claude-pptx-skills
mkdir -p .claude/skills
cp -r /tmp/claude-pptx-skills/skills/imagery-and-photo-treatment .claude/skills/imagery-and-photo-treatment
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Imagery And Photo Treatment 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 Imagery And Photo Treatment 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 Imagery And Photo Treatment 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.

Imagery and Photo Treatment

When to use

Use this skill when photos clash in crop, color, or treatment. Symptoms include one warm stock photo next to one cold one, images at three different aspect ratios, some photos full color and some greyscale, inconsistent cropping that cuts heads or leaves dead space, and a low-resolution image stretched to fill. Run this in Stage 3 with the other brand-asset work.

What it does

It brings the deck's photography onto one treatment: a consistent aspect ratio and crop convention, a single color treatment (for example a brand duotone or a defined filter), consistent placement, and a minimum resolution. The result is imagery that reads as one library shot for this brand rather than assorted stock.

Method

A brand image style is usually a small ruleset: a treatment, an aspect ratio or two, a crop convention, and a placement pattern. The job is to apply it to every photo.

  1. State the image rules. From the brand, record the treatment (full color, brand duotone, or a defined filter and overlay), the allowed aspect ratios, the crop convention (rule-of-thirds focal point, no cut heads), the placement pattern (full-bleed, half-bleed, or framed), and the minimum resolution.

  2. Inventory the images. Walk the deck and record each photo: its current treatment, aspect ratio, crop, placement, and resolution. Flag the off-rule ones.

  3. Apply the color treatment. Convert each photo to the brand treatment. For a duotone, recolor the image to the brand's two-color duotone (in PowerPoint, Picture Format then Color then a duotone recolor, or set a brand-color overlay at a fixed opacity). For a filter, apply the same correction to every photo so warmth and contrast match.

  4. Normalize aspect ratio and crop. Crop each image to an allowed aspect ratio and apply the crop convention: place the focal point on a third, keep faces and product whole, and avoid awkward dead space. Use Crop to Fill within a picture placeholder so all images in a row share a ratio.

  5. Standardize placement. Apply the placement pattern consistently: if the layout is half-bleed image plus text, every image slide should follow it rather than one being framed and another full-bleed.

  6. Enforce resolution. Replace any image below the minimum resolution or that is visibly soft when scaled. Do not upscale a small image to fill; source a larger one.

  7. Fix overlays and text legibility. Where text sits on a photo, use the brand's scrim or overlay (a consistent dark or brand-color gradient at a set opacity) so text stays legible without each slide inventing its own overlay.

  8. Keep real imagery honest. Do not warp a photo to fit a frame; crop instead. Do not mirror a photo that contains text or a recognizable place if that misrepresents it.

Inputs

  • The deck.
  • The brand image rules: treatment, aspect ratios, crop convention, placement, overlay, and minimum resolution. If undocumented, ask, or define a single consistent treatment and state it.

Output format

An imagery treatment report:

  • The image rules, restated.
  • A per-image list: current state and the action (apply duotone or filter, re-crop to ratio, reposition, replace low-resolution, add overlay).
  • A note on any image that must be replaced rather than treated.

Close with a confirmation that all photos share one treatment, allowed aspect ratios, and the crop convention.

Example

Input: three image slides, one warm full-color photo, one cold one, and one greyscale, at three aspect ratios.

Output:

  • Rules: brand duotone, 16:9 and 4:3 only, focal point on a third, half-bleed placement, dark scrim at 35 percent for text.
  • Apply the brand duotone to all three so color matches.
  • Crop all to 16:9 with the focal point on a third; fix the one with a cut head.
  • Result: one treatment, consistent ratio and crop across the three slides.

Frequently asked questions

What does the Imagery And Photo Treatment AI skill do?

Applies a single image treatment, aspect ratio, and duotone or filter rule so photos stop clashing in crop, color, and style.

Why use Imagery And Photo Treatment on TypingMind?

Because you install it once and use it with any model. Imagery And Photo Treatment 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 Imagery And Photo Treatment in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/andreworia/claude-pptx-skills/tree/main/skills/imagery-and-photo-treatment. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Imagery And Photo Treatment?

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 Imagery And Photo Treatment?

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

Is the Imagery And Photo Treatment AI skill free?

Yes. It is published on GitHub by andreworia under the MIT 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇