brand-architecture
Skill17 starsChanged 2 days agoMITView on GitHub
Design or audit the strategic relationships among a parent brand, sub-brands, endorsed brands, products, services, and acquisitions. Use when a portfolio needs a coherent naming, identity, migration, or governance system; do not use for logo execution or website information architecture alone.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- 1999AZZAR/designer-mcpword for word, first seen Nov 15, 2026
- Hela-Ecosystem/designer-mcpword for word, first seen Nov 15, 2026
- Insightful-Pipe/marketing-strategy-skillstheir own version, first seen Nov 1, 2026
- brainbytes-dev/everything-claude-marketingtheir own version, first seen Nov 1, 2026
- cofoundy/brand-skillstheir own version, first seen Oct 13, 2026
- skyf0xx/gambittheir own version, first seen Sep 30, 2026
Other versions7 projects use a version of this.
Word for word · 2
- 1999AZZAR/designer-mcp★ 17100% same
- Hela-Ecosystem/designer-mcp★ 17100% same
Edited · 0
None found.
Wrote their own version · 5
- cofoundy/brand-skills★ 79same name
- skyf0xx/gambit★ 29same name
- brainbytes-dev/everything-claude-marketing★ 9same name
- productionx-in/Core-Skills★ 1same name
- Insightful-Pipe/marketing-strategy-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- logo-designSkill
- modern-web-guidanceSkill
- motion-designerSkill
- videoSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
Design governance: Create an intake and approval path for new offers, acquisitions, partnerships, local exceptions, renames, and …
- Distinctive: line 49
Stress-test the system: Test a new product, acquisition, regional exception, co-brand, failed sibling, and retired offer.
- Distinctive: line 67
Every entity has one declared role and one accountable owner.
- Very specific: line 78
Use brand_fetch_design_md for an existing brand's published design context.
- Very specific: line 79
Use brand_list or logo_search_library for bounded comparative reference, never as proof of strategic fit.
- Very specific: line 81
Use generate_tokens, generate_rules, or logo_workflow after the architecture and expression rules are approved.
- Distinctive: line 86
Read the research-backed framework before choosing a model or writing a portfolio recommendation.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Brand Architecture
Turn a portfolio of brands and offers into an explicit system of relationships that customers, teams, and future acquisitions can understand.
Core distinction
Brand architecture is the strategic structure of a portfolio: brand roles, relationships, naming hierarchy, visible endorsement, equity transfer, and governance. It is not merely a logo chart, a product taxonomy, a design system, or a campaign calendar. Keep those layers separate and show where they connect.
Workflow
- Inventory the portfolio. List the corporate/master brand, ranges, sub-brands, products, services, variants, descriptors, campaigns, acquired brands, and internal names. Record audience, promise, market, lifecycle, current name, current visual relationship, owner, and evidence quality.
- Clarify roles and equity. For every entity, state what it contributes, what it borrows from a parent, what must remain independent, and what would be damaged if the parent or sibling changed. Mark assumptions instead of inventing customer research.
- Choose a relationship model. Compare branded house, sub-brand,
endorsed brand, house of brands, and hybrid options against shared audience,
parent credibility, differentiation, reputational coupling, investment,
acquisition autonomy, and regulatory or geographic constraints. Use the
decision matrix in
references/brand-architecture-framework.md. - Define the naming hierarchy. Specify the grammar from master brand to offer family, product/service, and descriptor or variant. Define collision, abbreviation, localization, trademark, domain, and retirement rules. Flag legal or linguistic checks as work to be verified; never imply clearance.
- Define expression rules. Describe the verbal endorsement, logo lockup, typography, color, imagery, navigation, metadata, and packaging relationship for each level. State the invariant parent cues and the permitted reasons for differentiation. Route actual token or mark production to Phenotype tools only after the strategic relationship is approved.
- Design governance. Create an intake and approval path for new offers, acquisitions, partnerships, local exceptions, renames, and retirements. Assign decision rights, required evidence, review cadence, and a single source of truth for the portfolio map.
- Plan migration. For an existing portfolio, sequence customer notice, naming changes, redirects, packaging, product UI, sales enablement, and measurement. Preserve legacy equity deliberately; do not recommend a clean rebrand merely because the diagram looks untidy.
- Stress-test the system. Test a new product, acquisition, regional exception, co-brand, failed sibling, and retired offer. If the architecture cannot answer where each belongs, the rules are incomplete.
Required deliverables
Produce only the artifacts the brief needs, normally:
- a portfolio inventory and relationship map;
- a model decision with rejected alternatives and trade-offs;
- naming hierarchy and naming grammar;
- verbal/visual relationship rules;
- governance and exception matrix;
- migration or rationalization roadmap; and
- a measurement plan with baselines, hypotheses, and owners.
Quality gates
- Every entity has one declared role and one accountable owner.
- The chosen model follows business and audience evidence, not visual taste.
- Parent-brand visibility and reputational coupling are explicit.
- Naming rules produce valid examples and reject plausible collisions.
- Hybrid architecture has boundaries; it is not permission for arbitrary cases.
- Legacy equity, legal review, localization, and migration cost are visible.
- Claims about awareness, preference, or customer behavior are sourced or labeled as hypotheses.
Phenotype integration
- Use
brand_fetch_design_mdfor an existing brand's published design context. - Use
brand_listorlogo_search_libraryfor bounded comparative reference, never as proof of strategic fit. - Use
generate_tokens,generate_rules, orlogo_workflowafter the architecture and expression rules are approved. - Store the final architecture decision and unresolved assumptions in Genome when the workflow includes project memory.
Read the research-backed framework before choosing a model or writing a portfolio recommendation.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

