brand-audit
Skill64 starsChanged 8 months agoMITView on GitHub
Discover and assess existing brand assets for cohesion, gaps, and inconsistencies. Scans codebases, websites, and social presence. Triggers when someone wants to evaluate their current brand, find brand gaps, or assess brand consistency.
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 39
If the agent tool is not available, do the scan yourself using Glob and Grep:
- Distinctive: line 47
Use WebFetch to scrape the website.
- Distinctive: line 59
Ask the user about their existing brand assets:
- Distinctive: line 163
Every score must have specific evidence.
- Distinctive: line 167
Don't use vague assessments: "Your brand could be stronger" fails.
- Distinctive: line 168
Every recommendation must be specific and actionable
“Common” is measured: kept by at least 6 in 10 of the 6 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
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.
Step 0: Load Context
- Find and read
brand-brief.mdusing the discovery chain - Load reference:
${CLAUDE_PLUGIN_ROOT}/references/anti-slop/anti-slop-checklist.md - Note what identity and business context is already known
Step 1: Discovery Phase
Determine what sources are available and scan them:
Source A: Codebase (if path exists)
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:
- Colors: CSS/SCSS variables, Tailwind config, theme files, color constants
- Typography: font-family declarations, Google Fonts imports, font configs
- Logos/Images: logo files, favicon, OG images, apple-touch-icon
- Copy: README taglines, meta descriptions, about page text, hero sections
- Config: package.json description, manifest.json, site metadata
- Inconsistencies: different colors in different files, multiple font stacks, conflicting metadata
If the agent tool is not available, do the scan yourself using Glob and Grep:
Glob: **/*.css, **/*.scss, **/*.ts, **/*.tsx, **/*.js, **/*.jsxfor style filesGrep: "color:|background:|font-family|--.*color"in style filesGrep: "description|tagline|motto|slogan"in config and content filesGlob: **/logo*, **/favicon*, **/og-*for image assets
Source B: Website URL (if provided)
Use WebFetch to scrape the website. Look for:
- Meta title and description
- OG image and metadata
- Hero section copy
- Footer copy and social links
- Color usage (CSS custom properties if accessible)
- Font usage
- Navigation structure and page hierarchy
- Calls to action
Source C: Guided Interview (if no codebase or URL)
Ask the user about their existing brand assets:
- "Do you have a logo? Where is it stored?"
- "Do you have defined brand colors? What are they?"
- "Do you have a tagline or value proposition written down?"
- "Do you have a website? What's the URL?"
- "Do you have social media profiles? Which platforms?"
- "Do you have any brand guidelines document?"
- "What brand assets do you feel GOOD about? What feels off?"
Step 2: Assessment
Score each discovered asset on four dimensions:
Scoring Rubric
Existence (binary):
- Does this asset exist at all?
Intentionality (1-5):
- 1: Clearly accidental or default (e.g., Bootstrap default blue, placeholder text)
- 2: Minimal thought, probably picked quickly
- 3: Some intentionality, reasonable choice
- 4: Clearly deliberate, aligns with a strategy
- 5: Deeply intentional, tied to brand strategy with rationale
Consistency (1-5):
- 1: Contradicts other assets (different colors in different places)
- 2: Mostly inconsistent, some alignment
- 3: Mixed, some consistent, some not
- 4: Mostly consistent across touchpoints
- 5: Perfectly consistent everywhere
Quality (1-5, using swap test):
- 1: Completely generic, passes to any brand (fails swap test badly)
- 2: Slightly customized generic
- 3: Acceptable but not distinctive
- 4: Distinctive, recognizably this brand
- 5: Highly distinctive, passes swap test perfectly
Assets to Score
| 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 |
Step 3: Gap Analysis
Map discovered assets against the brand-brief schema sections:
- Positioning gaps: Is there a clear competitive position? Or does the brand try to be everything?
- Messaging gaps: Is there a consistent story? Or is the messaging different on every page?
- Voice gaps: Is there a recognizable voice? Or is it generic/inconsistent?
- Visual gaps: Is there a cohesive visual system? Or random visual choices?
- Asset gaps: What's missing entirely? (No OG image, no favicon, no brand guide, etc.)
For each gap, classify priority:
- Critical: Actively hurting the brand (contradictory messaging, broken assets, generic where distinctiveness needed)
- Important: Missing but not yet harmful (no formal brand guide, inconsistent but not contradictory)
- Nice to have: Would improve but not urgent (secondary color system, icon library, etc.)
Step 4: Write to Brand Brief
Update brand-brief.md:
- Populate the
assets.existingarray with discovered assets and scores - Populate
assets.gapswith identified gaps and priorities - Populate
assets.inconsistencieswith found inconsistencies - Update
last_auditdate - Update
last_updated - Append to Decision Log with audit summary
Step 5: Present Results
Structure 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."
Anti-Slop Checks on Audit Output
- Don't use vague assessments: "Your brand could be stronger" fails. "Your tagline 'Innovative solutions for modern teams' fails the swap test because any SaaS company could claim it" passes.
- Every recommendation must be specific and actionable
- Tie recommendations to framework principles (Dunford, Neumeier, etc.)
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- cofoundy/brand-skills★ 67same name
- skyf0xx/gambit★ 29same name
- hunthung-code/fashion-director★ 4same name
- gauravv-g/claude-skills-collection★ 1same name
- productionx-in/Core-Skills★ 1same name
- xeroc/skills★ 1same 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.
Used alongsideProjects with it also use brand-architecture, competitor-branding and 5 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
cofoundySkillbrand-architecture
Define how multiple brands, sub-brands, and product lines relate to each other under one organization. Use when the user says "brand architecture", "sub-brand", "brand portfolio", "master brand", "house of brands", "branded house", "product naming system", "how do our brands relate", "parent brand", "brand hierarchy", "brand family", "we have multiple products and need a naming system", "brand extension", "new product launch under existing brand", or when a company has grown beyond a single brand and needs a system to manage brand relationships.
Also in 3 projects that use this
cofoundySkillcompetitor-branding
Analyze how competitors present their brand — identity, messaging, positioning, voice, and visual style — to find gaps and opportunities. Use when the user says "competitor brand analysis", "analyze competitor brands", "how do competitors position themselves", "competitor messaging", "competitor identity", "what are competitors saying", "benchmark competitors", "competitive brand landscape", "how do we compare to competitors", "competitive audit", or wants to understand the brand landscape before defining their own position.
Also in 3 projects that use this
vivy-yiSkillrebranding
品牌重塑 - 账号定位、视觉和内容的全面升级
Also in 3 projects that use this
akachandan1Skillbrand-story
Receipts-based marketing storytelling engine for LinkedIn and X personal-brand, founder, and brand accounts. Use when the user wants to plan social content, write a LinkedIn post or X thread, research what's being said on social platforms before writing, react to a trend, or build a content calendar. Triggers: "brand story", "plan my content", "write a post", "LinkedIn post", "X thread", "tweet", "content calendar", "what should I post", "social listening", "research this topic", "react to this", "post about", "founder content".
Also in 3 projects that use this
Google CloudSkillbrand-strategy
Brand strategy and campaign positioning expertise. Covers audience segmentation, competitive differentiation, value proposition frameworks, and campaign brief creation. Load this skill when setting up campaigns, selecting audience segments, or defining creative direction.
Also in 3 projects that use this
JetBrainsSkillbrand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Also in 3 projects that use this
- +1 more from cofoundy
In this repository9 other files it gives its agents.
- brand-ad-copySkill
- brand-competitor-scanSkill
- brand-landing-pageSkill
- brand-messagingSkill
- brand-positioningSkill
- brand-radarSkill
- brand-visual-identitySkill
- brand-voiceSkill
- startSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

