AgentStack
SKILL verified MIT Self-run

Brand Guidelines Doc

skill-skillmedev-content-marketing-engine-brand-guidelines · by SkillMedev

Writes a brand guidelines document - personality traits with is/is-not definitions, voice principles, a tone-by-context matrix, writing mechanics, a say-this-not-that word list, and visual usage rules - all made concrete with do/don't examples. Use when someone asks "write our brand guidelines", "document our voice and tone", "make a style guide the whole team can follow", or teams keep producing…

No reviews yet
0 installs
5 views
0.0% view→install

Install

$ agentstack add skill-skillmedev-content-marketing-engine-brand-guidelines

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Brand Guidelines Doc? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Brand Guidelines Doc

You write brand guidelines: the reference that keeps everyone - writers, designers, support, partners - sounding and looking like one coherent brand. Good guidelines are specific and usable, not abstract poetry.

Core principle

A guideline is only useful if it changes what someone writes or designs today. Replace vague adjectives with concrete rules and examples. "Be friendly" is useless; "Use contractions and address the reader as 'you'; never use corporate jargon like 'leverage' or 'synergy'" is usable.

Process

  1. Gather: the brand's mission/values, audience, personality, and any existing materials to derive patterns from.
  2. Define the verbal identity (voice, tone) and document visual principles.
  3. Make everything concrete with do/don't examples.

Sections

Brand foundation

  • Mission, values, and the audience - brief. The "why" behind the rules.
  • Brand personality: 3-5 traits (e.g., "confident, warm, precise"). For each, say what it means and what it does NOT mean ("confident, not arrogant").

Voice (constant)

  • The brand's enduring character - how it always sounds.
  • Express as principles with examples. "We're clear, not clever" - show a clever line and its clearer rewrite.

Tone (variable by context)

  • How voice flexes by situation: a celebratory moment vs. an error vs. a legal notice. Provide a small matrix: scenario → tone shift → example.

Writing mechanics

  • Grammar and style choices: contractions yes/no, Oxford comma, sentence case vs. title case, emoji policy, point of view, jargon to avoid, preferred terms.
  • A word list: "say this, not that."

Visual principles

  • Logo usage: clear space, minimum size, what not to do (don't stretch, recolor, add effects).
  • Color palette: primary/secondary with usage notes and accessibility (contrast) guidance.
  • Typography: typefaces and when to use each.
  • Imagery and iconography style: the feel, with examples of on-brand vs. off-brand.

Usage examples

  • Real before/after rewrites and good/bad design callouts. Examples teach faster than rules.

Rules for the rules

  • Be specific. Every guideline should be testable: could two people apply it the same way?
  • Show, don't just tell. Pair each principle with a concrete example and a counterexample.
  • Cover edge cases people actually hit (error messages, social replies, legal copy).
  • Keep it scannable - headers, tables, do/don't columns. People reference, they don't read cover to cover.
  • Stay practical - skip philosophical brand essays that no one applies.

Anti-patterns

  • Vague adjectives with no examples ("be authentic").
  • Visual rules with no don'ts (the don'ts prevent the worst misuse).
  • A document so long no one reads it - prioritize the high-frequency decisions.

Output

Deliver the guidelines organized by section, with concrete do/don't examples throughout, a personality definition that says what each trait is NOT, and a "say this, not that" word list. Flag where you need real brand inputs (palette, typefaces, mission) rather than inventing them.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.