# AI use cases for Brand System Skill (amirmushichge/brand-system-skill) Repo: [amirmushichge/brand-system-skill](https://github.com/amirmushichge/brand-system-skill) | Use cases: 4 | Page: https://dedupedai.com/use-cases/amirmushichge-brand-system-skill/ A free, open-source Skill file that guides Lovart Agent through building an Anchor Brand Kit, guidelines, key visuals, and campaign and packaging concepts from one visual reference. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Build an Anchor Brand Kit from one visual reference: https://dedupedai.com/use-cases/amirmushichge-brand-system-skill/build-anchor-brand-kit-from-reference/ - Create original campaign scenes that stay on-brand: https://dedupedai.com/use-cases/amirmushichge-brand-system-skill/create-original-campaign-scenes-with-brand-lock/ - Diagnose and fix a weak brand direction before scaling: https://dedupedai.com/use-cases/amirmushichge-brand-system-skill/diagnose-and-correct-a-weak-brand-direction/ - Sketch packaging concepts that follow an existing product shape: https://dedupedai.com/use-cases/amirmushichge-brand-system-skill/generate-packaging-concepts-from-a-packaging-reference/ ## How to build an Anchor Brand Kit from one visual reference with Brand System Skill Repo: [amirmushichge/brand-system-skill](https://github.com/amirmushichge/brand-system-skill) | Difficulty: Beginner | Time: 60 minutes | Basis: From the README Turn one reference image into an approved Anchor Brand Kit with named Google Fonts and colors. **Who it is for:** A small brand owner or non-designer who has one image they like and needs a usable brand foundation before making any assets. **The problem:** Starting a brand from scratch with prompts gives inconsistent results, and a single image does not explain fonts, colors, or hierarchy. **The outcome:** An approved Anchor Brand Kit covering logo, typography, colors, hierarchy, graphic language, and white-space behavior, built from the reference without copying it. ### Steps 1. Open SKILL.md in the repo and click Raw. 2. Copy the complete document. 3. Start a new Lovart project in Thinking Mode and paste the complete Skill into the Agent chat, then send it. 4. Follow the onboarding, answer the project brief questions, and attach one main visual reference when requested. 5. Review the First Brand Kit and approve it at the Anchor Brand Kit gate, or reply HELP ME WITH THIS if a question is unclear. ### Prompt to paste into your agent ```text Using the brand-system-skill repo at https://github.com/amirmushichge/brand-system-skill, run onboarding in Lovart Agent for the project described in , with as the main visual reference. Expected output: a First Brand Kit with named Google Fonts and a color set, presented for approval. Verify that the Agent did not generate any assets before the Project Brief and Reference Direction gates were approved. ``` ### Caveat The Skill runs inside Lovart Agent and the README says copy and paste is the primary installation method, because Lovart does not currently accept .md files as attachments. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/amirmushichge-brand-system-skill/build-anchor-brand-kit-from-reference/ ## How to create original campaign scenes that stay on-brand with Brand System Skill Repo: [amirmushichge/brand-system-skill](https://github.com/amirmushichge/brand-system-skill) | Difficulty: Intermediate | Time: 90 minutes | Basis: From the README Generate campaign scenes that take mood and composition from a reference while the brand kit controls identity. **Who it is for:** A marketing lead who needs campaign visuals that look like the brand but are not copies of a competitor or inspiration image. **The problem:** Reference images can pull in someone else's logo, typography, or exact scene, and generated scenes often drift from the brand. **The outcome:** Campaign scenes that follow Brand Lock: composition and lighting from the scene reference, identity from the Anchor Brand Kit, and no near-duplicate of the reference. ### Steps 1. Complete the Anchor Brand Kit approval in the Skill workflow, since guidelines, campaigns, and packaging cannot start before it. 2. Set up Brand Lock and approve it at the Brand Lock gate. 3. Write a Generation Plan for the campaign and approve it before any credit-consuming generation. 4. Send RESUME to continue from the saved next action after the Agent checks required inputs. 5. Send AUDIT to run the consistency audit before scaling the campaign assets. ### Prompt to paste into your agent ```text Using the brand-system-skill repo at https://github.com/amirmushichge/brand-system-skill, set up Brand Lock in Lovart Agent for with as the scene reference and the approved Anchor Brand Kit for identity. Expected output: a written Generation Plan and then original campaign scenes. Verify that the generated scenes do not reproduce the scene reference's characters, poses, or object arrangement. ``` ### Caveat The README says generative models can distort text, so users must manually verify font usage and final copy before any campaign goes out. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/amirmushichge-brand-system-skill/create-original-campaign-scenes-with-brand-lock/ ## How to diagnose and fix a weak brand direction before scaling with Brand System Skill Repo: [amirmushichge/brand-system-skill](https://github.com/amirmushichge/brand-system-skill) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Use review and reject commands to isolate a failing direction and restart from the last approved stage. **Who it is for:** A creative lead whose generated visuals feel off-brand and who needs a diagnosis before spending more credits. **The problem:** Teams keep generating when a direction is already wrong, which wastes credits and spreads the problem across guidelines and campaigns. **The outcome:** A clear diagnosis of the visual problem, a rejected direction that is isolated, and a restart from the last approved stage. ### Steps 1. Send STATUS to get the current project checkpoint. 2. Send ART DIRECTOR REVIEW to activate Creative Director Support Mode for diagnosis and guidance. 3. Send REJECT DIRECTION to isolate the rejected direction and restart from the last approved stage. 4. Send GO BACK if an earlier approved stage needs reopening, and note which later work may become invalid. 5. Send AUDIT to run the relevant consistency audit without generating new assets. ### Prompt to paste into your agent ```text Using the brand-system-skill repo at https://github.com/amirmushichge/brand-system-skill, run STATUS, then ART DIRECTOR REVIEW in Lovart Agent on the project whose visuals look off-brand. Expected output: a diagnosis of the visual problems and a recommendation to refine or reject the direction. Verify that the Agent reports which later work becomes invalid before any GO BACK is confirmed. ``` ### Caveat The workflow is written for Lovart Agent with Thinking Mode, so these commands are chat commands inside that Agent, not commands in a local terminal. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/amirmushichge-brand-system-skill/diagnose-and-correct-a-weak-brand-direction/ ## How to sketch packaging concepts that follow an existing product shape with Brand System Skill Repo: [amirmushichge/brand-system-skill](https://github.com/amirmushichge/brand-system-skill) | Difficulty: Advanced | Time: 120 minutes | Basis: From the README Create packaging concept renders that keep a reference product shape and label zones, for early review. **Who it is for:** A product team in early design that needs packaging concept options to show stakeholders before engaging print or 3D specialists. **The problem:** Early packaging ideas are hard to compare when each concept uses a different shape, label layout, and brand treatment. **The outcome:** Packaging concept renders with product shape, label zones, and SKU architecture taken from the packaging reference and styled with the Anchor Brand Kit. ### Steps 1. Complete the Anchor Brand Kit approval first, since packaging cannot begin before it is approved. 2. Attach a Packaging Reference when the Agent requests it, so it can control product shape, label zones, and SKU architecture. 3. Approve the written Generation Plan before any credit-consuming generation. 4. Review the packaging concepts with the team and send AUDIT to check consistency across SKUs. 5. Use the final system review to decide which concepts move forward to production specialists. ### Prompt to paste into your agent ```text Using the brand-system-skill repo at https://github.com/amirmushichge/brand-system-skill, generate packaging concepts in Lovart Agent for using for shape, label zones, and SKU architecture, with the approved Anchor Brand Kit for styling. Expected output: a set of packaging concept renders with a Generation Plan approved first. Verify that every render is labeled as a concept and not a dieline, vector file, or production-ready model. ``` ### Caveat The README says packaging renders are concepts, not final dielines, vector files, prepress files, manufacturing specifications, or production-ready 3D models, so production still needs designers, print specialists, and legal review. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/amirmushichge-brand-system-skill/generate-packaging-concepts-from-a-packaging-reference/