brand-architecture
Define how multiple brands, sub-brands, and product lines relate to each other under one organization. Use when the user says "brand architecture",…
Assess the health and consistency of an existing brand — identity, messaging, voice, positioning, and market perception. Use when the user says "brand audit", "brand review", "assess our brand", "is our brand consistent", "brand health check", "brand analysis", "something's off
$ npx -y skills add cofoundy/brand-skills --skill brand-audit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/brand-auditContext preview
The summary Claude sees to decide when to auto-load this skill.
Assess the health and consistency of an existing brand — identity, messaging, voice, positioning, and market perception. Use when the user says "brand audit", "brand review", "assess our brand", "is our brand consistent", "brand health check", "brand analysis", "something's off
name: brand-audit description: Assess the health and consistency of an existing brand — identity, messaging, voice, positioning, and market perception. Use when the user says "brand audit", "brand review", "assess our brand", "is our brand consistent", "brand health check", "brand analysis", "something's off with our brand", "our brand feels outdated", "brand diagnosis", "review our brand", "brand gap analysis", or wants to understand where their brand is strong and where it needs work before investing in brand development. metadata: version: 1.1.0
You are a brand strategist conducting a brand health assessment. Your job is to evaluate how well the brand is working — its clarity, consistency, differentiation, and alignment — and deliver a clear diagnosis with prioritized recommendations.
**Load the brand package first.** Look for `brand.yaml` (in `./`, `./brand/`, or `brands/<slug>/`); read it and `context.md` from the same folder before asking anything. Use that context as the brand's *declared* intent — but do not treat it as ground truth. No package yet? Run `brand-init` first. Legacy fallback: `.agents/brand-context.md`.
**Then establish the source of truth — declared vs. live.** The brand package, brand book, and guidelines are what the brand *says* it is (declared). They are frequently stale. The brand the market actually experiences lives in the **current production touchpoints** — the live site, app, or the repo that ships it. Before scoring anything:
---
Ask the user to share:
1. **Live brand materials** — the **current production** website URL, app, and the repo that ships it (confirm which version is live if several exist); plus social profiles, existing brand guidelines, pitch deck, or marketing materials. Prioritize what's live over what's documented. 2. **What prompted this audit** — what specific concern or trigger led to this review? 3. **Business context** — any recent changes (new leadership, new product, new market, funding, rebrand considerations)? 4. **Internal perception** — how does the internal team describe the brand? 5. **External perception** — any customer feedback, research, or NPS data about brand perception? 6. **Key competitors** — who should the brand be benchmarked against?
---
Evaluate across 6 dimensions. Score each 1–5 (1 = needs significant work, 5 = excellent).
> **Score what's live, not what's filed.** For every dimension, assess the current production touchpoints first; use the brand package/book only to measure intent against reality. If the documented brand and the live brand disagree, score the live brand and record the gap under "What's Not Working" (flagging whether it's stale docs or real drift).
---
**What to assess:**
**Questions to answer:**
---
**What to assess:**
**Questions to answer:**
---
**What to assess:**
**Questions to answer:**
---
**What to assess:**
**Questions to answer:**
---
**What to assess:**
---
**What to assess:**
**Turn an idea into a real brand — name, identity, voice, and a brand book — without leaving your AI agent.** 15 open-source Agent Skills for founders, indie hackers, and agencies building AI-native — in Claude Code, Cursor, Windsurf, and 70+ agents.
Define how multiple brands, sub-brands, and product lines relate to each other under one organization. Use when the user says "brand architecture",…
Foundation skill that captures and stores core brand context — identity, audience, positioning, values, and voice. Use when the user says "set brand context",…
Create a comprehensive brand standards document — covering logo usage, color, typography, voice, messaging, and application rules. Use when the user says…
Create a visual identity brief for a brand — logo direction, color palette, typography, imagery style, and design system foundations. Use when the user says…
Initialize a structured, versioned brand package (and optionally register it in a brand portfolio). Use when the user says "start a new brand", "create a…
Build a brand's messaging hierarchy — taglines, value propositions, key messages, and proof points for each audience. Use when the user says "brand messaging",…