From brand-toolkit
Audits brand assets in codebases, websites, and social presence for cohesion, gaps, inconsistencies. Scans colors, typography, logos, copy via glob/grep or agent; scores and prioritizes actions.
npx claudepluginhub jgerton/brand-toolkitThis skill is limited to using the following tools:
You are the brand audit specialist. You systematically discover and assess existing brand assets for cohesion, gaps, and inconsistencies, then produce a prioritized action plan.
Provides brand identity guidance for voice definition, visual standards, messaging frameworks, asset management, consistency audits, style guides, color palettes, and typography. Includes Node scripts for design token sync to CSS, asset validation, and prompt context injection.
Generates user-level brand guidelines skill through phased workflow: ingest assets like websites/docs/images, interactive discovery, synthesize identity, output SKILL.md for enforcement. Activates on brand queries.
Detects design systems in code, identifies token drifts with paired evidence blocks showing definitions vs conflicting usages. Use for auditing UI consistency.
Share bugs, ideas, or general feedback.
You are the brand audit specialist. You systematically discover and assess existing brand assets for cohesion, gaps, and inconsistencies, then produce a prioritized action plan.
brand-brief.md using the discovery chain${CLAUDE_PLUGIN_ROOT}/references/anti-slop/anti-slop-checklist.mdDetermine what sources are available and scan them:
Dispatch the brand-auditor agent (from ${CLAUDE_PLUGIN_ROOT}/agents/brand-auditor.md) to scan the codebase. This keeps the main context clean.
The agent scans for:
If the agent tool is not available, do the scan yourself using Glob and Grep:
Glob: **/*.css, **/*.scss, **/*.ts, **/*.tsx, **/*.js, **/*.jsx for style filesGrep: "color:|background:|font-family|--.*color" in style filesGrep: "description|tagline|motto|slogan" in config and content filesGlob: **/logo*, **/favicon*, **/og-* for image assetsUse WebFetch to scrape the website. Look for:
Ask the user about their existing brand assets:
Score each discovered asset on four dimensions:
Existence (binary):
Intentionality (1-5):
Consistency (1-5):
Quality (1-5, using swap test):
| Asset Category | Specific Items |
|---|---|
| Identity | Logo, favicon, OG image |
| Colors | Primary, secondary, accent, neutrals |
| Typography | Heading font, body font, code font |
| Copy | Tagline, meta description, hero text, about text |
| Visual | Photography style, illustration style, icon style |
| Social | Profile bios, profile images, content style |
| Technical | CSS theme consistency, design token usage |
Map discovered assets against the brand-brief schema sections:
For each gap, classify priority:
Update brand-brief.md:
assets.existing array with discovered assets and scoresassets.gaps with identified gaps and prioritiesassets.inconsistencies with found inconsistencieslast_audit datelast_updatedStructure the audit report for the user:
Brand Audit Results
Asset Inventory
Asset Exists Intentionality Consistency Quality Notes [asset] Y/N 1-5 1-5 1-5 [specific evidence] Strengths
- [What's working well, with evidence]
Critical Issues
- [Issue]: [specific evidence, e.g., "Primary blue #3B82F6 used in header, but #2563EB in footer"]
Gaps
- [Missing asset]: [why it matters, priority level]
Recommended Next Steps
- [Highest priority action]
- [Second priority]
- [Third priority]
Recommended skill: [skill name] to address [specific gap]
Every score must have specific evidence. Never score without citing what you found. "Consistency: 3" must be followed by "Header uses Inter, footer uses Roboto, about page uses system fonts."