Not in the top 1,000 by GitHub stars
amirmushichge/brand-system-skill
An open-source, agent-guided creative-direction workflow for turning one visual reference into a connected brand system with Lovart Agent.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 30f6084ddf6a
No earlier version was observed for comparison.
181GitHub stars
38stars in 7 days
1skill in this repository
0commits in 30 days
Heat
4.5- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
brand-system-builder
When your agent uses it
Guides Lovart Agent from one visual reference to a coherent brand system, campaign assets, and packaging concepts through a gated creative-direction workflow.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
6,146 tokensWhen the skill is activated
Reference documents
2,547 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Principle
- Operating Rules
- Generation Plan — Required Before Every Generation
- Never Invent
- Project State
- Workflow Map
- Objective
- Mass-User-Friendly Briefing
- Ask the User
- Output
- APPROVAL GATE 1 — Project Brief
- Required Input
- Objective
- Analysis Framework
- Recommended Agent Instruction
- APPROVAL GATE 2 — Reference Direction
- Required Input
- Objective
- Brand Kit Must Include
- Typography Requirements
- Recommended Agent Instruction
- Output
- Objective
- Audit Criteria
- Recommended Agent Instruction
- Refine or Reject Decision
- Creative Director Support Mode
- Refinement Instruction
- APPROVAL GATE 3 — Anchor Brand Kit
- Required Input
- Objective
- Available Guideline Modules
- Master Guideline Instruction
- Module Requirements
- Approval
- Objective
- Required Input
- Recommended Agent Instruction
- Review
- Definition
- Required Inputs
- Reference Roles
- Brand Lock Generation Instruction
- APPROVAL GATE 4 — Brand Lock
- Objective
- Recommended Agent Instruction
- Approval Rule
- Objective
- Recommended Agent Instruction
- Objective
- Requirements
- Recommended Agent Instruction
- Objective
- Recommended Agent Instruction
- Objective
- Review Checklist
- Completion Report
- Bonus A — Responsive Formats
- Bonus B — Localization
- Bonus C — Motion From Still
- Bonus D — Social and Banner Extensions
Files
.github/ISSUE_TEMPLATE/feature-request.mddoc414 bytes.github/ISSUE_TEMPLATE/skill-bug.mddoc747 bytes.gitignoreasset78 bytesBENCHMARK.mddoc1,659 bytesCHANGELOG.mddoc706 bytesCITATION.cffasset716 bytesCONTRIBUTING.mddoc1,243 bytesLICENSEasset18,658 bytesREADME.mddoc6,646 bytesSKILL.mdcore30,868 bytesSKILL.mdcore30,868 bytesSKILL.mdcore30,868 bytesSKILL.mdcore30,868 bytesSKILL.mdcore30,868 bytesSKILL.mdcore30,868 bytesSKILL.mdcore30,868 bytesSKILL.mdcore30,868 bytesSKILL.mdcore30,868 bytesSKILL.mdcore30,868 bytesassets/brand-lock.pngasset80,713 bytesassets/cover.pngasset1,851,727 bytesassets/workflow.pngasset169,598 bytes
Read SKILL.md
# Brand System Builder
## Purpose
Use this Skill to guide a user from one visual reference to a coherent, scalable brand system.
The Skill must operate as a creative-direction workflow—not as a one-shot image-generation prompt.
The intended result is a connected system containing:
- a structured project brief;
- a deconstructed visual reference;
- an approved Anchor Brand Kit;
- brand-guideline modules;Skills included
- brand-system-builder
Repository facts
- License
- CC-BY-4.0
- Created
- Aug 11, 2026
- Last pushed
- Aug 11, 2026
- Forks
- 15
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 9 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 13 network referencesin 2 files: README.md:7 CITATION.cff:8
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 1 reference to secretsin 1 file: .gitignore:8
- No requests to vote in Hot
Show all 14 signals by file
.gitignore
- Access to secretsline 8
[Credential-related source omitted]
CITATION.cff
- Network accessline 8
- family-names: Mushich given-names: Amir website: "https://x.com/AmirMushich" - Network accessline 9
given-names: Amir website: "https://x.com/AmirMushich" license: CC-BY-4.0 - Network accessline 10
website: "https://x.com/AmirMushich" - Network accessline 11
license: CC-BY-4.0 repository-code: "https://github.com/amirmushichge/lovart-brand-system-skill" url: "https://github.com/amirmushichge/lovart-brand-system-skill" - Network accessline 12
repository-code: "https://github.com/amirmushichge/lovart-brand-system-skill" - Network accessline 13
url: "https://github.com/amirmushichge/lovart-brand-system-skill"
README.md
- Network accessline 7
[](https://github.com/amirmushichge/lovart-brand-system-skill/releases/tag/v0.2.0-alpha) - Network accessline 8
[](LICENSE) - Network accessline 9
[](https://amirmushich.link/design_agent) - Network accessline 15
[Open Lovart Agent](https://amirmushich.link/design_agent) - Network accessline 37
Use the Skill in [Lovart Agent](https://amirmushich.link/design_agent) with **Thinking Mode** enabled. Start a fresh project, paste the complete Skill, and keep one clear main visual reference ready. The workflow is written for non-designer - Network accessline 67
https://raw.githubusercontent.com/amirmushichge/lovart-brand-system-skill/main/SKILL.md - Network accessline 183
Created by [Amir Mushich](https://x.com/AmirMushich).
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 7 facts
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in prose of documentationREADME.md:8Low confidence
- Network access in prose of documentationREADME.md:9Low confidence
- Network access in prose of documentationREADME.md:15Low confidence
- Network access in prose of documentationREADME.md:37Low confidence
- Network access in code of documentationREADME.md:67Low confidence
- Network access in prose of documentationREADME.md:183Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
