agentleFS
Sign inStart free
skyf0xxskyf0xx/gambit/.agents/skills/brand-voice/SKILL.md

brand-voice

Skill29 starsChanged 33 days agoMITView on GitHub

Define a brand's verbal identity — tone, voice, writing style, vocabulary, and messaging rules. Use when the user says "brand voice", "tone of voice", "how should we write", "writing guidelines", "copy style guide", "brand language", "verbal identity", "how should the brand sound", "tone guide", "our copy doesn't sound right", "copywriter guidelines", "voice and tone", or when onboarding a copywriter or content team. Also use when the user has a brand strategy and wants to define how the brand communicates.

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 52 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Load the brand package first: Look for brand.yaml (in ./, ./brand/, or brands/<slug>/).

    line 14
  2. Distinctive:

    If brand context isn't available:

    line 20
  3. Very specific:

    Punctuation: Use of em-dashes, ellipses, exclamation marks (encouraged/limited/banned)?

    line 91
  4. Distinctive:

    Numbers: When to spell out, when to use numerals?

    line 95
  5. Distinctive:

    Contractions: Use them or avoid them?

    line 97

“Common” is measured: kept by at least 6 in 10 of the 52 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brand Voice

You are a senior verbal identity strategist and copy director. Your job is to define how a brand speaks — its tone, vocabulary, style, and communication principles — in a way any writer can apply consistently.

Before You Start

Load the brand package first. Look for brand.yaml (in ./, ./brand/, or brands/<slug>/); read it and context.md from the same folder before asking anything. Use that context — don't re-ask for what's already captured. No package yet? Run brand-init first. Legacy fallback: .agents/brand-context.md.

Information to Gather

If brand context isn't available:

  1. Brand name and category
  2. Brand personality — how would you describe the brand as a person?
  3. Audience — who are they? How do they communicate?
  4. Positioning — premium, approachable, expert, playful?
  5. Tone spectrum — ask them to rate: Formal ↔ Casual, Serious ↔ Playful, Expert ↔ Accessible, Corporate ↔ Human
  6. Brands with voices they admire — which brands communicate in a way they want to emulate?
  7. What the brand should never sound like — what voice is clearly wrong for this brand?

Output: Brand Voice Guide

01 — VOICE OVERVIEW

One strong paragraph (4–5 sentences) that captures the brand's communication character. Read this and you should immediately know how to write for this brand. Reference the personality, audience relationship, and tone territory.

Include a one-sentence Voice Essence statement: "[Brand] sounds like [character description] — [quality], [quality], and [quality]."

02 — TONE DIMENSIONS

Define the brand's position on 4–5 tone axes. For each:

[Dimension] — e.g. Casual ←——→ Formal

  • Where the brand sits (e.g. "Casual side, but not sloppy")
  • What this means in practice
  • One example sentence that demonstrates this

Cover dimensions such as:

  • Formality (casual ↔ formal)
  • Energy (calm ↔ energetic)
  • Humor (serious ↔ witty)
  • Expertise (accessible ↔ authoritative)
  • Warmth (distant ↔ intimate)

03 — VOICE QUALITIES

List 5–6 core voice qualities. For each:

[Quality Name]

  • What it means for this brand specifically (2 sentences)
  • Do: Example of this quality in action
  • Don't: Common mistake that violates this quality

04 — VOCABULARY

Words we use: List 10–15 words and phrases that feel natural for this brand. Include brand-specific terms, verbs, and descriptors.

Words we avoid: List 10–15 words and phrases that feel off-brand. Include industry jargon, clichés, and words that contradict the brand's personality.

Brand-specific language: Any proprietary terms, product names, or ways the brand refers to its customers/users (e.g. "members" vs "users" vs "customers").

05 — WRITING STYLE RULES

Sentence length: Short, medium, or long? When to mix?

Punctuation: Use of em-dashes, ellipses, exclamation marks (encouraged/limited/banned)?

Capitalization: Standard sentence case, title case for headlines, any exceptions?

Numbers: When to spell out, when to use numerals?

Contractions: Use them or avoid them?

Active vs passive voice: Preference and exceptions?

Humor: Allowed, encouraged, or off-limits? If allowed, what type?

06 — CHANNEL ADAPTATIONS

Voice stays consistent. Tone adapts. For each channel, explain how the core voice flexes:

ChannelTone AdjustmentExample
Website homepage[adjustment][example phrase]
Social media[adjustment][example phrase]
Email marketing[adjustment][example phrase]
Customer support[adjustment][example phrase]
Error messages / UI copy[adjustment][example phrase]

07 — BEFORE AND AFTER EXAMPLES

Provide 4–5 rewrite examples showing off-brand copy transformed into on-brand copy:

Before (off-brand):

[example]

After (on-brand):

[example]

Why it works: [one sentence]

08 — THINGS WE NEVER SAY

List specific phrases, formats, or communication patterns this brand never uses. Be direct.

Examples of categories:

  • Hollow hype ("world-class", "revolutionary", "game-changing")
  • Over-apologetic language
  • Passive-aggressive humor
  • Overly corporate language
  • False urgency or pressure tactics

Related Skills

  • brand-strategy: Brand positioning the voice should express
  • brand-identity: Visual identity to pair with verbal identity
  • brand-messaging: Taglines and messaging hierarchy
  • brand-guidelines: Full standards doc incorporating voice
  • brand-context: Foundation context for all brand work

Download now (ZIP)

  • Other versions56 projects use a version of this.

    Word for word · 1

    1. xeroc/skills★ 1100% same

    Edited · 2

    1. cofoundy/brand-skills★ 6799% same
    2. productionx-in/Core-Skills★ 196% same

    Wrote their own version · 53

    1. affaan-m/ECC★ 246ksame name
    2. HybridAIOne/hybridclaw★ 159same name
    3. runxhq/runx★ 97same name
    4. mturac/everything-openai-codex★ 89same name
    5. mit-network/everything-claude-code★ 76same name
    6. jgerton/brand-toolkit★ 64same name
    7. Fmarzochi/EGC★ 61same name
    8. ysyecust/everything-claude-code★ 44same name
    9. MoizIbnYousaf/marketing-cli★ 33same name
    10. sanky369/vibe-building-skills★ 30same name

    43 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.

  • Used alongsideProjects with it also use brand-discovery, agent-sort and 7 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.
    • ysyecustSkill

      brand-discovery

      Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand tension across 8 modules using laddering, 5 Whys, and projective techniques. Produces a resumable session with disk-persisted state and a master brandbook (90_SYNTHESIS.md).

      Also in 6 projects that use this

    • niloykumarbarmanSkill

      agent-sort

      Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

      Also in 13 projects that use this

    • arsalllsSkill

      network-config-validation

      Pre-deployment validation of Cisco IOS/IOS-XE configuration — catching missing saves, mismatched ACLs, overlapping subnets, duplicate IPs, missing route-maps, and dangerous commands before they cause outages.

      Also in 5 projects that use this

    • renepfSkill

      motion-advanced

      Advanced motion patterns for React / Next.js — drag & drop, gestures, text animations, SVG path drawing, custom hooks, imperative sequences (useAnimate), loaders, and the full API decision tree. Requires motion-foundations.

      Also in 4 projects that use this

    • posteverywhereSkill

      agency-clients

      Work safely across several clients or brands in PostEverywhere. Use when the user manages social media for more than one client, brand or business, mentions a client by name, asks to switch clients, or when the connected accounts belong to different companies.

      Also in 3 projects that use this

    • posteverywhereSkill

      cross-post-video

      Post one video to several platforms with PostEverywhere, with the right title and caption for each. Use when the user wants to share a video, Reel, Short or TikTok across TikTok, Instagram Reels, YouTube Shorts, LinkedIn and Facebook Reels, or asks to "post this video everywhere".

      Also in 3 projects that use this

    • +3 more from posteverywhere
  • In this repository36 other files it gives its agents.

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free