brand
Skill0 starsChanged 3 months agoMITView on GitHub
Sets up your visual brand identity. Writes brand colors, fonts, and visual style to .amplifyrc and Brand.md. Also saves visual inspiration references. Use when the user runs /brand or /brand add.
64 other projects use a version of this.
Adopted by
Most recently taken up by
- zstvns/design-skillstheir own version, first seen Nov 15, 2026
- kobiniv888-ai/Claude-codetheir own version, first seen Nov 15, 2026
- nextlevelbuilder/ui-ux-pro-max-skilltheir own version, first seen Nov 15, 2026
- whoamnesia/astudio-aiotheir own version, first seen Nov 8, 2026
- caiopizzol/brand.mdtheir own version, first seen Nov 8, 2026
- passion4it-gmbh/passionfruit-sitetheir own version, first seen Nov 5, 2026
Used with
Projects with it also use content, competitors and 10 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.
Rayan55050Skillcontent
Создание контента: посты, статьи, тексты
Also in 3 projects that use this
CesarjoquinSkillcompetitors
When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' 'competitive landing pages,' 'how do we compare to X,' 'battle card,' or 'competitor teardown.' Use this for any content that positions your product against competitors. Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. For sales-specific competitor docs, see sales-enablement.
Also in 3 projects that use this
hardikpandyaSkillstop-slop
Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
Also in 4 projects that use this
OpenAISkillimage-to-code
Implement a selected image, screenshot, mockup, or Image Gen reference as a faithful, responsive frontend.
Also in 5 projects that use this
AnasX7Skillbrandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.
Also in 5 projects that use this
AnasX7Skillminimalist-ui
Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
Also in 5 projects that use this
- +1 more from AnasX7
Other versions64 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 64
- nextlevelbuilder/ui-ux-pro-max-skill★ 150ksame name
- joye61/pic-smaller★ 2.9ksame name
- Ohh-889/skyroc-admin★ 795same name
- cdavid817/vanehub-ai★ 116same name
- saksham10arora-dotcom/everything-claude-codex★ 96same name
- cofoundy/brand-skills★ 79same name
- caiopizzol/brand.md★ 39same name
- zstvns/design-skills★ 33same name
- b1rdmania/claude-brand-skills★ 20same name
- rylsherdamz-rgb/stellar-forge★ 17same name
54 more not listed
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 repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- remotion-best-practicesSkill
- add-inspirationSkill
- craft-contentSkill
- draft-articleSkill
- draft-carouselSkill
- draft-diagramSkill
- draft-imagesSkill
- draft-videoSkill
- heygen-avatarSkill
- heygen-videoSkill
- humanizerSkill
- ingestSkill
- initSkill
- linkedin-postSkill
- lintSkill
- listenSkill
- meetingSkill
- voiceSkill
- wikiSkill
- youtube-descriptionSkill
- youtube-shortSkill
- youtube-uploadSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 4 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 19 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
When the user runs /brand, optionally followed by add [url or description]:
- Very specific: line 12
If the argument starts with add, go to Add Mode.
- Distinctive: line 25
Read the config and resolve the vault path.
- Very specific: line 27
Read {vaultPath}/{paths.voice} (Voice.md) if it exists.
- Distinctive: line 31
Ask these questions one at a time using AskUserQuestion or natural conversation.
- Distinctive: line 49
If they give a name or description, pick a specific hex.
- Distinctive: line 62
If they accept the default, derive it: lighten the primary color to ~90% lightness.
- Very specific: line 92
Read the existing .amplifyrc file.
- Very specific: line 120
Create {vaultPath}/Brand/ and {vaultPath}/Brand/Inspiration/ if they don't exist.
- Very specific: line 122
If paths.brand is set to something other than "Brand", use that path instead.
- Very specific: line 171
When the user runs /brand add [url or description]:
“Common” is measured: kept by at least 6 in 10 of the 19 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
Instructions
When the user runs /brand, optionally followed by add [url or description]:
If the argument starts with add, go to Add Mode. Otherwise, go to Setup Mode.
Setup Mode
Step 0: Load Context
Find the .amplifyrc config file. Check these locations in order:
.amplifyrcin the current working directory.amplifyrcat the path specified byVAULT_PATHenvironment variable
Read the config and resolve the vault path.
Read {vaultPath}/{paths.voice} (Voice.md) if it exists. This helps connect visual style to written voice.
Step 1: Interview
Ask these questions one at a time using AskUserQuestion or natural conversation. Wait for each answer before asking the next.
Introduce it:
"Let's set up your brand. This gives your videos, carousels, and articles a consistent visual identity."
Question 1: Brand name "What's your brand name? This appears in video intros and closers."
Question 2: Tagline (optional) "Got a tagline? One line that captures what you do. Skip if you don't have one."
Question 3: Domain (optional) "What's your domain? (e.g., example.com) This shows in video outros. Skip if you don't have one."
Question 4: Primary color "What's your primary brand color? Give me a hex code, a color name, or describe it (e.g., 'deep teal', '#35656e', 'forest green')."
If they give a name or description, pick a specific hex. Confirm: "I'll use {hex} for that. Good?"
Question 5: Accent color "What's your accent color? This is for highlights, CTAs, buttons. Something that pops against your primary."
Same hex resolution as above.
Question 6: Text color (offer default) "What color for body text? Most brands use a dark charcoal. I'll default to #394646 unless you have something specific."
Question 7: Background color (offer default) "Light background color? Used for card backgrounds, section fills. I'll default to a light tint of your primary unless you prefer something else."
If they accept the default, derive it: lighten the primary color to ~90% lightness.
Question 8: Neutral color (offer default) "Neutral/muted color? Used for borders, dividers, secondary elements. I'll default to a warm grey unless you prefer something."
Question 9: Font "What font do you use? (e.g., Inter, Poppins, DM Sans) If you're not sure, Inter works well for most brands."
Options:
- Inter (Recommended)
- Poppins
- DM Sans
- Other
Question 10: Visual style "How would you describe your visual style?"
Options:
- Minimal and clean
- Bold and high-contrast
- Warm and approachable
- Dark and moody
- Playful and colorful
- Other
Question 11: Visual inspiration (optional) "Any brands, designers, or creators whose visual style you admire? This helps inform design direction. Skip if nothing comes to mind."
Step 2: Write .amplifyrc brand section
Read the existing .amplifyrc file. Add or update the brand section:
{
"brand": {
"name": "Brand Name",
"tagline": "Your tagline",
"domain": "example.com",
"colors": {
"primary": "#35656e",
"text": "#394646",
"accent": "#fee19a",
"background": "#d3e9ee",
"neutral": "#ded8ce"
},
"fonts": {
"body": "Inter"
}
}
}Merge into the existing config without overwriting other sections. Write the updated JSON back.
Also add "brand": "Brand" to the paths section if not already present.
Step 3: Create Brand directory
Create {vaultPath}/Brand/ and {vaultPath}/Brand/Inspiration/ if they don't exist. Use mkdir -p.
If paths.brand is set to something other than "Brand", use that path instead.
Step 4: Write Brand.md
Copy the template from {amplifyRepoRoot}/templates/brand/Brand.md and personalize it with the user's answers.
Replace all {bracket} placeholders:
| Placeholder | Source |
{primary_name} | Color name from user (e.g., "Deep teal") |
{primary_hex} | Hex code |
{text_name} | Color name |
{text_hex} | Hex code |
{accent_name} | Color name |
{accent_hex} | Hex code |
{background_name} | Color name |
{background_hex} | Hex code |
{neutral_name} | Color name |
{neutral_hex} | Hex code |
{body_font} | Font name |
{heading_font} | Same as body unless they specified a heading font |
{visual_style_description} | 2-3 sentences describing their visual style based on Q10 answer |
{voice_to_visuals} | Connect Voice.md tone to visual choices. E.g., "Direct voice = clean layouts, bold type, no clutter." |
{inspiration_notes} | Q11 answer, or "None added yet. Run /brand add to save visual references." |
Write to {vaultPath}/{paths.brand}/Brand.md.
Step 5: Report
Brand set up.
Name: {name}
Colors: {primary_hex} (primary), {accent_hex} (accent)
Font: {font}
Style: {visual_style}
Config: .amplifyrc brand section written
Brand doc: {paths.brand}/Brand.md
Draft skills (/draft-video, /draft-carousel, /draft-article) will use this for visual decisions.
Video intros/outros will show "{name}" and "{domain}".Add Mode
When the user runs /brand add [url or description]:
Step 0: Load Context
Same as Setup Mode Step 0. Also read {vaultPath}/{paths.brand}/Brand.md if it exists.
Step 1: Determine Input Type
Parse what follows add:
- URL (starts with
http://orhttps://): go to Step 2a. - Text description: go to Step 2b.
Step 2a: Save URL Inspiration
Fetch the URL content using WebFetch. Summarize the visual elements:
- Color palette
- Typography choices
- Layout style
- Photography/illustration style
- Overall mood
Generate a slug from the page title or URL.
Write to {vaultPath}/{paths.brand}/Inspiration/{slug}.md:
---
type: brand-inspiration
source: "{url}"
saved: {YYYY-MM-DD}
---
# {Page Title or Description}
**Source:** {url}
## Visual Elements
{summary of visual choices: colors, typography, layout, imagery, mood}
## What to Take From This
{2-3 bullet points on what's worth borrowing for the user's brand}Step 2b: Save Description Inspiration
Take the user's text description and save it directly.
Generate a slug from the first few words.
Write to {vaultPath}/{paths.brand}/Inspiration/{slug}.md:
---
type: brand-inspiration
source: "manual"
saved: {YYYY-MM-DD}
---
# {First few words as title}
{user's description}Step 3: Report
Inspiration saved: {paths.brand}/Inspiration/{slug}.md
{one-line summary of what was captured}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.

