Brand Compliance Auditor logo

Brand Compliance Auditor

Community
andreworia
brand-compliance-auditor

Audits a finished deck against the brand and template and returns a flagged list of every off-brand and off-template element.

Overview

Publisherandreworia
Repositoryclaude-pptx-skills
Skill namebrand-compliance-auditor
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 Brand Compliance Auditor 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/brand-compliance-auditor
  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/brand-compliance-auditor .claude/skills/brand-compliance-auditor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Brand Compliance Auditor 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 Brand Compliance Auditor 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 Brand Compliance Auditor 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.

Brand Compliance Auditor

When to use

Use this skill when a finished deck needs a check before it ships. It is the pre-flight pass: the deck is built, you think it is on-brand, and you want a systematic sweep that catches the off-template layout, the hard-coded color, the rogue font, the stretched logo, and the missing page number before a partner or client does. Run it near the end of Stage 4, after the structural and asset fixes.

What it does

It walks the whole deck against a brand-and-template checklist and returns a prioritized list of every violation, grouped by severity, each with the slide, the issue, and the fix. It does not silently change the deck; it produces the punch list so a human (or the Reskin skill) can act.

Method

Audit against a fixed checklist so nothing is missed, and grade each finding by how much it hurts compliance.

  1. Structure checks. For each slide: is it on a real template layout (not Blank)? Is content in placeholders rather than rogue boxes? Are titles, content, and furniture inside the margins and safe zone?

  2. Color checks. Are fills and text bound to theme color slots rather than hard-coded hex? Is every color within the approved palette? Is there one accent per slide, used on the right element? Are charts on the brand sequence, not a rainbow?

  3. Type checks. Are only the two theme fonts used? Are all sizes on the type scale? Is case consistent? Is line spacing the brand value? Any rogue bold, italic, or all-caps?

  4. Logo checks. Is the correct, current logo used? The right variant for each background? Undistorted? At or above minimum size? Is clear space respected? Are partner logos fair and balanced?

  5. Icon and image checks. Do icons share one style, weight, corner, and color rule? Do photos share one treatment, allowed aspect ratios, and the crop convention? Any low-resolution asset?

  6. Furniture checks. Are titles uniform in position and style? Is the footer consistent? Are page numbers present, uniform, and in the right place? Are dividers parallel? Are the title and closing exceptions deliberate?

  7. Grade each finding. Classify as Blocker (cannot ship: wrong logo, off-template layout, off-palette brand color, unreadable text), Major (clearly off-brand but shippable in a pinch: rogue font, inconsistent footer, rainbow chart), or Minor (polish: a few points of misalignment, an icon weight mismatch).

  8. Order the punch list. Sort by severity, then by frequency, so the user fixes the systemic Blockers first. Point each finding at the skill that fixes it.

Inputs

  • The finished deck.
  • The brand and template references: template layouts, theme colors and fonts, approved palette, logo rules, icon and image rules, and furniture conventions. If any are missing, audit against what is provided and note the gaps.

Output format

A prioritized audit punch list:

  • A one-line headline count (Blockers, Majors, Minors).
  • Blockers, then Majors, then Minors. Each item: slide number, the issue, the rule it breaks, the fix, and the skill that fixes it.
  • A short systemic note: the two or three patterns that recur most, so they can be fixed once across the deck.

Close with a ship or hold recommendation based on whether any Blocker remains.

Example

Input: a 20-slide deck that looks finished.

Output (excerpt):

  • Headline: 3 Blockers, 6 Majors, 5 Minors. Recommendation: hold until Blockers cleared.
  • Blocker. Slide 1: outdated logo. Fix: replace with current asset (logo-and-lockup-compliance).
  • Blocker. Slides 4 and 11: off-template layout (Blank). Fix: map to Title and Content (master-and-layout-mapper).
  • Major. Slides 6 to 9: rainbow chart palette. Fix: brand chart sequence (brand-palette-guard).
  • Major. Slide 14: Calibri title. Fix: theme font (theme-font-and-type-scale-enforcer).
  • Systemic: hard-coded blue recurs across 8 slides; bind to Accent 1 once (theme-color-binder).

Frequently asked questions

What does the Brand Compliance Auditor AI skill do?

Audits a finished deck against the brand and template and returns a flagged list of every off-brand and off-template element.

Why use Brand Compliance Auditor on TypingMind?

Because you install it once and use it with any model. Brand Compliance Auditor 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 Brand Compliance Auditor in TypingMind?

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

Which AI models can use Brand Compliance Auditor?

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 Brand Compliance Auditor?

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

Is the Brand Compliance Auditor 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 👇