Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Brand Guidelines

ASecurity

Build and apply brand guidelines — voice, visual identity, and usage rules that keep every touchpoint consistent.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsgoexpressgit

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill brand-guidelines --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Brand Guidelines?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Brand Guidelines
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-brand-guidelines/badge)](https://www.skillsdirectory.com/skills/aicodedecode-brand-guidelines)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: brand-guidelines
description: Build and apply brand guidelines — voice, visual identity, and usage rules that keep every touchpoint consistent.
category: business-marketing
---

## Overview

Brand guidelines turn "it just feels like us" into rules anyone can follow. This skill walks through creating or applying a complete brand system: positioning, voice and tone, visual identity, and usage rules. A good guideline set answers three questions for any creator: what to say, how to say it, and what it should look like.

The output of this skill is typically a brand guide document plus reusable components (voice examples, do/don't pairs, templates) that let others produce on-brand work without a brand manager hovering over them.

## When to use

- Creating a new brand identity from scratch (startup launch, rebrand)
- Onboarding designers, writers, or agencies who need to produce brand-aligned work
- Auditing an existing brand for consistency across channels
- Settling disputes about what "on brand" means with concrete examples
- Defining voice and tone before scaling content production

- Rebranding after a merger, acquisition, or positioning shift
- Creating templates (decks, docs, social) that stay on-brand without designer review
- Licensing the brand to partners or franchisees who need clear boundaries
- Onboarding agencies or freelancers quickly
- Auditing brand consistency across touchpoints
- Preparing for international market expansion
## Core concepts

**Brand positioning.** One sentence: who the brand is for, what it does differently, and why that matters. Everything else ladders up to this. If two positioning statements could apply to a competitor, they are too generic.

**Brand personality vs. voice vs. tone.** Personality is the brand as a person (e.g., "the helpful expert"). Voice is how that person always sounds (consistent). Tone is how the voice adapts to the situation (a failed payment email sounds different from a launch announcement, but the same voice delivers both).

**Visual identity system.** Logo (primary, secondary, monochrome versions), color palette (primary + secondary + neutrals with hex/RGB/CMYK values), typography (display and body fonts with fallbacks), imagery style (photography vs. illustration direction, filters, composition rules), spacing and layout rules.

**Usage rules with examples.** Every rule needs a do/don't pair. "Don't stretch the logo" is forgettable; a side-by-side visual example is memorable. Rules should cover: logo misuse, color misuse, typography hierarchy, voice examples per channel, and co-branding.

**Brand architecture.** For companies with multiple products: endorsed brands, sub-brands, or house of brands. Decide how naming, logos, and voice relate across the portfolio.


**Brand voice scale.** Plot voice on 2–3 sliding scales (e.g., formal/casual, serious/playful, technical/simple) and mark where the brand sits. Scales beat adjectives because they show range: the brand can move along the scale by channel while staying recognizably itself.

**Signature assets.** 2–3 distinctive, ownable elements (a color combination, an illustration style, a recurring format) that make the brand recognizable even with the logo removed. Test: cover the logo — is it still identifiable?

**Logo system, not just a logo.** Primary, secondary, monochrome, and favicon versions → clearspace rules (minimum padding = height of a defined element) → minimum sizes (print and digital) → approved backgrounds → co-branding lockups.
One logo file used everywhere breaks somewhere; a system flexes without breaking.
**Color discipline.** Primary palette (2–3 colors, exact HEX/RGB/CMYK/Pantone) → secondary palette → functional colors (success, warning, error) → accessibility-checked combinations (contrast ratios documented).
Document which combinations are approved — designers guess wrong without explicit guidance.
**Typography hierarchy.** Display, heading, body, and caption styles with sizes, weights, line-heights, and usage rules.
Specify fallbacks for environments without brand fonts (email, docs). Two typefaces maximum for most brands — restraint reads as confidence.
## Practical workflow

1. **Discovery and research.** Collect existing materials, interview founders/stakeholders, survey customers on current perception. Document the gap between how the brand is seen and how it should be seen.
2. **Draft positioning.** Write the positioning statement and 3–5 proof points (evidence that the claim is true). Test it: does it differentiate? Is it credible? Is it relevant to the audience?
3. **Define personality and voice.** Pick 3–4 personality traits. For each trait, write "this, not that" pairs (e.g., "Confident, not arrogant"). Draft voice in action: rewrite the same sentence (an error message, a promo, a help article) in the brand voice.
4. **Build the visual system.** Lock logo variants, a palette of 5–8 colors, two typefaces max, and imagery direction. Specify minimum sizes, clear space, and backgrounds.
5. **Write usage rules.** For every element, document correct use, incorrect use, and exceptions. Include co-branding and partner-use rules.
6. **Assemble the guide.** Structure: brand story → positioning → personality/voice → visual identity → applications (templates for common deliverables) → governance (who approves, how to request exceptions).
7. **Roll out and govern.** Share with all creators, run a workshop on the voice, and set a review cadence (quarterly is plenty). Guidelines that nobody reads are decoration.

**Quick audit checklist:** pick 10 random recent touchpoints (ads, emails, social posts, packaging). Score each 1–5 on voice match and visual match. Anything averaging under 3.5 gets fixed or removed.


**Voice example bank (build 10–15 of these):** the same message rewritten per channel — push notification, error message, invoice email, social reply, out-of-office. Creators copy the pattern instead of guessing the tone.

**Guidelines structure:** 1) brand story and positioning (one page), 2) logo system, 3) color, 4) typography, 5) imagery and iconography, 6) voice and tone with examples, 7) application examples (right and wrong), 8) templates and assets.
Publish as a living web page, not a PDF — PDFs go stale and nobody checks version numbers.
**Rollout:** present to all teams → run 30-min training per department → provide templates on day one → set up a lightweight review process for major external assets → audit quarterly.
Guidelines without rollout are shelfware.
## Common pitfalls

- **Guidelines without examples.** Abstract adjectives ("bold", "authentic") mean nothing without concrete before/after samples. Show, don't describe.
- **Too many fonts and colors.** Two typefaces and a tight palette beat a sprawling system. Complexity invites inconsistency.
- **Voice that only works for marketing.** The brand voice must work for error messages, invoices, and legal notices too — test it in the unglamorous places.
- **No governance.** Without an owner and an approval process, guidelines decay within a quarter. Assign one person as brand guardian.
- **Copying a competitor's personality.** Differentiation is the point. If your guidelines could be swapped with a rival's, start over at positioning.
- **Treating guidelines as finished.** Revisit annually. Brands evolve; the guide should evolve with documented version history.
- **Logo-first branding.** Starting with the logo instead of positioning. Visuals express strategy; they cannot substitute for it.
- **No examples of tone in failure states.** Brands reveal themselves in apologies and error messages — script those explicitly.
- **Guidelines nobody can find.** Buried in a shared drive. One canonical URL, linked from onboarding.
- **Rules without reasons.** "Don't do X" with no rationale gets ignored. Explain the why — it builds judgment, not just compliance.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →