brand-guidelines
Skill2 starsChanged 4 months agoMITView on GitHub
Apply brand voice, tone, colors, typography, and visual style consistently across any artifact. Use when the user wants to ensure a document, presentation, email, website, or any content matches their brand identity — including color palette, font choices, tone of voice, imagery guidelines, and design standards. Also use when the user says "make it on-brand", "apply our brand style", or shares brand guidelines to follow.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- rvdbreemen/OTGW-firmwaretheir own version, first seen Nov 8, 2026
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- BrightGold70/skillstheir own version, first seen Nov 8, 2026
- yht-4403/jc-agent-skillstheir own version, first seen Nov 8, 2026
- ErikaAX08/erikas-skillstheir own version, first seen Nov 8, 2026
- okou-ai/okou-skillstheir own version, first seen Nov 4, 2026
Used with
Projects with it also use academy-guide, skill-share 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.
AnthropicSkillacademy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.
Also in 9 projects that use this
ArogyaReddySkillskill-share
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Also in 25 projects that use this
ArogyaReddySkillraffle-winner-picker
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Also in 26 projects that use this
zephyrwang6Skilldeepl
Übersetzt Texte, Dokumente und XLIFF-Dateien via DeepL API. Verwende für Übersetzungen mit /deepl translate, /deepl file oder /deepl xliff.
Also in 4 projects that use this
zephyrwang6Skillimagemagick-conversion
Convert and manipulate images with ImageMagick. Covers format conversion, resizing, batch processing, quality adjustment, and image transformations. Use when user mentions image conversion, resizing images, ImageMagick, magick command, batch image processing, or thumbnail generation.
Also in 4 projects that use this
- +3 more from zephyrwang6
- +4 more from ArogyaReddy
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/skills★ 189ksame name
- ComposioHQ/awesome-claude-skills★ 75ksame name
- ComposioHQ/awesome-codex-skills★ 17ksame name
- composio-community/awesome-codex-skills★ 16ksame name
- composio-community/open-claude-cowork★ 4.3ksame name
- ComposioHQ/open-claude-cowork★ 4.3ksame name
- Mayandev/notion-avatar★ 3.2ksame name
- Prat011/awesome-llm-skills★ 1.7ksame name
- ChenglinPoly/infiAgent★ 1.2ksame name
- polyuiislab/infiAgent★ 1.2ksame name
181 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 repository48 other files it gives its agents.
- agent-memorySkill
- ai-engineerSkill
- api-designSkill
- autoplanSkill
- backend-devSkill
- benchmarkSkill
- code-reviewerSkill
- commit-messageSkill
- database-architectSkill
- data-engineerSkill
- debuggerSkill
- design-explorerSkill
- devex-engineerSkill
- devops-platformSkill
- doc-coauthoringSkill
- forward-deployment-engineerSkill
- frontend-designSkill
- internal-commsSkill
- java-developmentSkill
- land-and-deploySkill
- mcp-builderSkill
- office-hoursSkill
- pdfSkill
- performance-optimizerSkill
- plan-ceo-reviewSkill
- plan-design-reviewSkill
- plan-eng-reviewSkill
- pptxSkill
- product-engineerSkill
- prompt-engineerSkill
- python-developmentSkill
- qa-engineerSkill
- react-developmentSkill
- release-engineerSkill
- research-agentSkill
- retro-engineerSkill
- safety-guardrailsSkill
- security-engineerSkill
- skill-creatorSkill
- spec-authorSkill
- sre-canarySkill
- system-designSkill
- technical-writerSkill
- test-writerSkill
- theme-factorySkill
- typescript-developmentSkill
- webapp-testingSkill
- xlsxSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 179 edited versions we read keep these.
7
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 20
When in doubt, ask for the guidelines: Never invent brand colors or voice.
- Distinctive: line 26
Before applying anything, collect:
- Distinctive: line 35
If the user has a brand guide document, ask them to share it.
- Distinctive: line 78
Check contrast: https://webaim.org/resources/contrastchecker/
- Distinctive: line 192
Document voice along four axes.
- Distinctive: line 245
Run this on any artifact before delivering:
- Distinctive: line 275
When guidelines are provided by the user, document them here for reference:
“Common” is measured: kept by at least 6 in 10 of the 179 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 Guidelines
Brand is not decoration — it is recognition. Every time a user encounters your product, email, presentation, or doc, they either build trust or erode it. Consistency builds trust. Inconsistency erodes it.
This skill applies brand identity across any artifact: presentations, documents, emails, landing pages, marketing copy, UI components, or any written content. It covers both visual identity (colors, fonts, spacing) and verbal identity (voice, tone, word choices).
Brand Guidelines Principles
- Consistency is the work. One perfectly on-brand artifact is easy. Applying the same standards to the 50th artifact in a quarter is the actual challenge. Document decisions so they can be applied without re-inventing each time.
- Brand is a system, not a vibe. "Make it feel premium" is not actionable. "Use Playfair Display at 40pt for headlines, #1A1A2E for text, and never use more than two typeface weights on a page" is actionable.
- Voice is harder than colors. Anyone can apply a hex code. Writing in a consistent voice — warm but not casual, authoritative but not cold — requires explicit rules and examples.
- Exceptions must be deliberate. Breaking brand rules is sometimes right (a playful social post, a technical doc for developers). But it must be a conscious choice, not an accident.
- When in doubt, ask for the guidelines. Never invent brand colors or voice. If the user hasn't shared guidelines, ask. A wrong brand color is worse than no color.
Step 0: Gather Brand Assets
Before applying anything, collect:
- Color palette — primary, secondary, accent, neutral, semantic (success/error/warning)
- Typography — headline font, body font, monospace font, sizes, weights, line heights
- Logo — file format, clear space rules, do/don't use cases
- Voice and tone guidelines — adjectives that describe the brand voice, examples of good/bad copy
- Imagery style — photography direction, illustration style, icon style
- Spacing and layout rules — grid system, margins, component spacing
If the user has a brand guide document, ask them to share it. If they only have partial guidelines, ask the targeted questions above and document what they provide.
Visual Identity Application
Color System
Define and apply colors as a semantic system — never use raw hex values scattered throughout:
PRIMARY PALETTE
━━━━━━━━━━━━━━
Primary: #[hex] — Main CTAs, key UI elements, headlines
Primary Dark:#[hex] — Hover states, dark mode accents
Primary Light:#[hex] — Backgrounds, subtle highlights
SECONDARY PALETTE
━━━━━━━━━━━━━━━━
Secondary: #[hex] — Supporting elements, secondary CTAs
Accent: #[hex] — Highlights, callouts, badges
NEUTRAL PALETTE
━━━━━━━━━━━━━━
Text Primary: #[hex] — Body text, labels
Text Secondary:#[hex] — Captions, metadata, muted text
Background: #[hex] — Page/slide background
Surface: #[hex] — Cards, panels, modal backgrounds
Border: #[hex] — Dividers, input borders
SEMANTIC COLORS
━━━━━━━━━━━━━━
Success: #[hex] — Confirmations, completed states
Warning: #[hex] — Caution states, pending items
Error: #[hex] — Errors, destructive actions
Info: #[hex] — Informational states, tipsContrast requirements (WCAG AA minimum):
- Normal text (< 18pt): 4.5:1 contrast ratio against background
- Large text (≥ 18pt or 14pt bold): 3:1 contrast ratio
- UI components and icons: 3:1 contrast ratio
Check contrast: https://webaim.org/resources/contrastchecker/
Typography System
TYPEFACE STACK
━━━━━━━━━━━━━
Heading: [Font Name], [fallback], sans-serif
Body: [Font Name], [fallback], serif
Monospace: [Font Name], [fallback], monospace
TYPE SCALE
━━━━━━━━━━
Display: 48–64px / 1.1 line-height / -0.02em tracking
H1: 36–40px / 1.15 line-height / -0.01em tracking
H2: 28–32px / 1.2 line-height / -0.01em tracking
H3: 22–24px / 1.25 line-height / 0em tracking
H4: 18–20px / 1.3 line-height / 0em tracking
Body Large: 18px / 1.6 line-height / 0em tracking
Body: 16px / 1.6 line-height / 0em tracking
Body Small: 14px / 1.5 line-height / 0em tracking
Caption: 12px / 1.4 line-height / 0.02em tracking
FONT WEIGHTS
━━━━━━━━━━━
Use maximum 2 weights per design:
Regular (400): body text
Medium (500): labels, UI elements
SemiBold (600):subheadings
Bold (700): headlines, emphasisApplying to Presentations (PPTX)
from pptx.dml.color import RGBColor
from pptx.util import Pt
# Brand colors (never use # prefix in pptxgenjs)
BRAND = {
"primary": RGBColor(0x1A, 0x1A, 0x2E),
"accent": RGBColor(0xE9, 0x4F, 0x37),
"light": RGBColor(0xF8, 0xF9, 0xFA),
"text": RGBColor(0x21, 0x25, 0x29),
"text_muted": RGBColor(0x6C, 0x75, 0x7D),
}
def apply_brand_text(run, style: str = "body"):
"""Apply brand typography to a text run."""
if style == "heading":
run.font.name = "Poppins" # or brand heading font
run.font.bold = True
run.font.color.rgb = BRAND["text"]
elif style == "body":
run.font.name = "Lora" # or brand body font
run.font.bold = False
run.font.color.rgb = BRAND["text"]
elif style == "accent":
run.font.name = "Poppins"
run.font.bold = True
run.font.color.rgb = BRAND["accent"]Applying to HTML/CSS
/* Brand Design Tokens */
:root {
/* Colors */
--color-primary: #1A1A2E;
--color-primary-dark: #0F0F1A;
--color-accent: #E94F37;
--color-background: #FFFFFF;
--color-surface: #F8F9FA;
--color-text: #212529;
--color-text-muted: #6C757D;
--color-border: #DEE2E6;
/* Typography */
--font-heading: 'Poppins', Arial, sans-serif;
--font-body: 'Lora', Georgia, serif;
/* Spacing scale (4px base) */
--space-1: 4px;
--space-2: 8px;
--space-3: 12px;
--space-4: 16px;
--space-6: 24px;
--space-8: 32px;
--space-12: 48px;
--space-16: 64px;
}
h1, h2, h3, h4, h5, h6 {
font-family: var(--font-heading);
color: var(--color-primary);
line-height: 1.2;
}
body, p, li {
font-family: var(--font-body);
color: var(--color-text);
line-height: 1.6;
}Verbal Identity (Voice & Tone)
Visual brand is only half the work. Voice consistency is what makes written content feel on-brand.
Defining Brand Voice
Document voice along four axes. Rate each 1–5:
| Axis | 1 | 5 |
| Formal ↔ Casual | Legal/corporate | Conversational/friendly |
| Serious ↔ Playful | Clinical precision | Wit and humor |
| Authoritative ↔ Humble | Expert pronouncements | Collaborative, asking |
| Technical ↔ Accessible | Deep jargon | Plain language |
Example: Stripe = Formal(3) Serious(3) Authoritative(4) Technical(3) — precise but human, expert but not arrogant.
Voice Application Rules
For each brand voice, create explicit do/don't rules:
BRAND VOICE: [Company Name]
━━━━━━━━━━━━━━━━━━━━━━━━━
We are: [3 adjectives]
We aren't:[3 adjectives]
DO:
✅ Use active voice: "We help teams ship faster" not "Teams are helped to ship faster"
✅ Lead with user benefit: "You get X" not "We provide X"
✅ Be specific: "Reduces deploy time by 40%" not "Significantly faster"
✅ Use contractions: "you'll", "we're", "it's" — sounds human
✅ Address the reader as "you" — direct, personal
DON'T:
❌ Use filler superlatives: "amazing", "incredible", "game-changing"
❌ Use passive voice in marketing copy
❌ Start sentences with "We are excited to announce..."
❌ Use jargon without explanation in user-facing copy
❌ Use ALL CAPS for emphasis — use bold instead
❌ Use more than one exclamation point per pageTone Adaptation by Context
Brand voice stays constant. Tone adapts to context:
| Context | Tone shift | Example |
| Marketing copy | More energetic, aspirational | "Ship with confidence." |
| Error messages | More direct, helpful, calm | "Your session expired. Sign in again to continue." |
| Onboarding | Warmer, encouraging | "You're almost ready — just one more step." |
| Technical docs | More precise, less personality | "The API returns a 401 status code when..." |
| Crisis / incident | Calm, factual, direct | "We identified an issue affecting X users at HH:MM UTC." |
Brand Audit Checklist
Run this on any artifact before delivering:
Visual
- All colors are from the brand palette — no off-brand hex values
- All fonts are brand-specified fonts (or approved fallbacks)
- Font sizes follow the type scale — no arbitrary sizes
- Contrast ratios meet WCAG AA on all text
- Logo used correctly — correct version, correct clear space
- No unapproved color combinations (e.g., accent on accent)
- Spacing follows the grid/scale — no random padding values
- Images match the brand photography/illustration direction
Verbal
- Voice matches the brand voice profile (formal/casual, serious/playful)
- No banned words or phrases (per do/don't list)
- CTAs are specific and active ("Start your free trial" not "Get started")
- No filler superlatives ("amazing", "revolutionary", "game-changing")
- Contractions used appropriately for the voice
- Technical terms defined or linked on first use
- All copy reviewed for tone match to context
Consistency
- Same terminology used throughout — no synonym drift ("workspace" vs "project" vs "board")
- Product names spelled and capitalized correctly every time
- Date/number formats consistent (US vs EU, $1,000 vs $1.000)
Brand Style Reference Card
When guidelines are provided by the user, document them here for reference:
## [Company] Brand Quick Reference
### Colors
| Name | Hex | Use |
|---|---|---|
| Primary | #______ | [use case] |
| Accent | #______ | [use case] |
| Background | #______ | [use case] |
| Text | #______ | [use case] |
### Typography
| Element | Font | Size | Weight |
|---|---|---|---|
| Headline | | | |
| Subheading | | | |
| Body | | | |
| Caption | | | |
### Voice
- Tone: [adjectives]
- Do: [key dos]
- Don't: [key don'ts]
### Logo Rules
- Minimum size: [px or mm]
- Clear space: [measurement]
- Approved on: [white / dark / brand color]
- Never: [common misuses]Definition of Done — Brand Guidelines
- Brand palette documented with named tokens and hex values
- Typography stack documented with sizes, weights, and line heights
- Voice profile documented with do/don't examples
- Tone adaptation defined for at least 3 key contexts
- All artifacts pass the visual brand audit checklist
- All copy passes the verbal brand audit checklist
- Consistency audit done — no synonym drift, no off-brand terminology
- Brand style reference card updated with any new decisions
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.

