From forge-skills
Use when establishing brand foundations before any design work, when two products need to feel related, when defining voice and tone for microcopy, or when logo usage and visual identity rules need documenting.
How this skill is triggered — by the user, by Claude, or both
Slash command
/forge-skills:brand-and-identityThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Pin down brand essence, logo rules, color identity, typography identity, voice and tone, icon system, illustration style, and multi-product consistency *before* design tokens get chosen. Output is `.forge/brand-identity.md`. Upstream of `design-system` — brand colors map to UI semantic tokens; voice rules shape every microcopy decision; the icon system is inherited by `component-library`.
Pin down brand essence, logo rules, color identity, typography identity, voice and tone, icon system, illustration style, and multi-product consistency before design tokens get chosen. Output is .forge/brand-identity.md. Upstream of design-system — brand colors map to UI semantic tokens; voice rules shape every microcopy decision; the icon system is inherited by component-library.
design-systemincremental-implementation| Thought | Reality |
|---|---|
| "We'll figure out the brand later" | Every screen you ship without brand rules is brand debt. Later means inconsistency baked into 50 screens. |
| "Just pick a color and go" | A color without a system becomes 15 slightly different blues across two products. |
| "Microcopy doesn't matter" | Users read microcopy more than marketing copy. Every button label is a brand moment. |
| "We don't need logo rules, it's just us" | The moment someone else makes a slide deck, they'll stretch the logo. Rules prevent this. |
| "One product, no need for multi-product rules" | Products multiply. Define what's shared on day one, not day 365. |
One sentence that captures what the company feels like. Not what it does — what it feels like. "Calm in chaos." "Receipts, not opinions." "The clipboard that thinks." If the sentence could describe three other companies, it's too generic.
0.5x).24px digital, 0.5in print).Brand colors and UI colors are different layers.
design-system as semantic tokens (accent, surface, danger, etc.).Document the mapping explicitly:
brand.primary → UI.accent
brand.accent → UI.accent-emphasis (or product-specific)
brand.neutral → UI.surface scale (light + dark variants derived here)
A brand color may never appear in product code as a raw hex — it always enters through a semantic token.
regular body, medium UI emphasis, semibold headings, bold reserved for hero only).If brand and UI faces differ, document the visual relationship — they must look intentional together, not accidental.
How the product speaks. Examples, not just adjectives:
Pick a voice axis pair (e.g., "friendly but not casual", "expert but not technical") and stress-test every category against it.
16 / 20 / 24 / 32. Icons larger than 32px usually want illustration territory instead.If two or more products share a brand:
State the design promise: "Someone using Product A and Product B should feel they're from the same company but know they're different products."
.forge/brand-identity.mdSections in this order: Essence, Logo, Color, Typography, Voice, Iconography & Illustration, Multi-product. Prepend a forge:meta header (generated_by: brand-and-identity, generated_at: <ISO 8601 UTC with Z>, depends_on: [] — independent, no upstream, generated_from: {}, content_hash: <sha256 first 8 of THIS file's body>). See forge-dependency-graph.
.forge/brand-identity.md written with forge:meta headernpx claudepluginhub aneja5/forge-skills --plugin forge-skillsSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.