agentleFS
sanky369sanky369/vibe-building-skills/skills/marketing/brand-voice/SKILL.md

brand-voice

Skill30 starsChanged 5 months agoMITView on GitHub

Define a brand's voice and produce a working voice guide: a personality archetype, settings on eight voice dimensions, do/don't rules, word choices, a tone matrix by context, and before/after rewrites of the user's real content. Use when the user says 'define my brand voice', 'what should our tone be', 'make this sound like us', 'our content sounds generic/inconsistent', 'write tone-of-voice or brand guidelines', or before producing copy at scale across channels. Also use in audit mode when existing content needs to be checked against a voice. Produces a Voice Guide document that other skills consume when writing any copy.

60 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use agent-sort, brand-discovery 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.
  • 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 14 projects that use this

  • 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

  • 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 4 projects that use this

  • akachandan1Skill

    brand-story

    Receipts-based marketing storytelling engine for LinkedIn and X personal-brand, founder, and brand accounts. Use when the user wants to plan social content, write a LinkedIn post or X thread, research what's being said on social platforms before writing, react to a trend, or build a content calendar. Triggers: "brand story", "plan my content", "write a post", "LinkedIn post", "X thread", "tweet", "content calendar", "what should I post", "social listening", "research this topic", "react to this", "post about", "founder content".

    Also in 4 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 4 projects that use this

  • TironFoxSkill

    agent-payment-x402

    Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents.

    Also in 5 projects that use this

  • +5 more from posteverywhere

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 57 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use before writing copy at scale, when content across channels sounds inconsistent, or when the user asks for tone/voice/brand guidelines.

    line 12
  2. Very specific:

    If the user's actual problem is *what to say* — differentiation, the core claim — use skills/marketing/positioning-angles first.

    line 13
  3. Very specific:

    If the user wants one specific page written, use skills/marketing/direct-response-copy (it consumes the voice guide.

    line 14
  4. Distinctive:

    Audit mode: if a voice guide already exists and the user says "our content drifted", skip to Step 6 and score existing content against the …

    line 15
  5. Distinctive:

    Ask in one batch, only for what's missing from context:

    line 19
  6. Distinctive:

    Don't stall: if samples or a site exist, infer answers 3–4 from them, state your inferences as assumptions, and proceed.

    line 26
  7. Distinctive:

    Before prescribing, describe.

    line 31
  8. Distinctive:

    Place the brand on each spectrum (1–5) with a one-line justification tied to the audience or positioning:

    line 52

“Common” is measured: kept by at least 6 in 10 of the 57 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

Produce a voice guide: a compact, enforceable document that makes every future piece of copy sound like the same brand, whoever (or whatever) writes it. Voice is how the brand sounds; positioning is what it claims — keep them separate. The governing principle: a voice guide is only real if it changes sentences. Every rule in it must be concrete enough that you can point at a line of copy and say pass or fail.

When to use / when not to

  • Use before writing copy at scale, when content across channels sounds inconsistent, or when the user asks for tone/voice/brand guidelines.
  • If the user's actual problem is what to say — differentiation, the core claim — use skills/marketing/positioning-angles first; voice without positioning is a costume on an empty claim.
  • If the user wants one specific page written, use skills/marketing/direct-response-copy (it consumes the voice guide; a lightweight voice sketch from its own intake is acceptable if no guide exists).
  • Audit mode: if a voice guide already exists and the user says "our content drifted", skip to Step 6 and score existing content against the guide.

Intake

Ask in one batch, only for what's missing from context:

  1. What do you sell and to whom? (If a positioning statement exists from skills/marketing/positioning-angles, use it — don't re-ask.)
  2. Paste 2–3 samples of your current writing (site copy, emails, posts) — or share a URL.
  3. Name 2–3 brands or writers whose voice you admire, and one you never want to sound like.
  4. Any words your brand insists on or bans?

Don't stall: if samples or a site exist, infer answers 3–4 from them, state your inferences as assumptions, and proceed.

Workflow

1. Extract the current voice (if any content exists)

Before prescribing, describe. Read the samples and write a 3-line diagnosis: what the voice currently is, where it's inconsistent, what's distinctive worth keeping. Skip only for pre-launch brands with no content.

2. Propose an archetype — user decides

Propose the top 2–3 archetype candidates with a one-line case for each; have the user pick one. Never present all ten as a menu.

ArchetypeCharacterExample brand
SageAnalytical, knowledgeable, truth-seekingTED
HeroCourageous, bold, inspiringNike
LoverPassionate, emotional, intimateTiffany & Co.
CreatorInnovative, imaginative, expressiveApple
InnocentOptimistic, cheerful, simpleCoca-Cola
EverymanRelatable, friendly, down-to-earthTarget
CaregiverCompassionate, supportive, helpfulDove
RulerAuthoritative, commanding, organizedIBM
MagicianTransformative, mysterious, powerfulTesla
OutlawRebellious, disruptive, provocativeRed Bull

Decision rules for shortlisting: trust-critical B2B or expertise-led → Sage or Ruler; challenger attacking an incumbent category → Outlaw or Magician; care/health/support products → Caregiver or Innocent; consumer brands built on relatability → Everyman; premium/design-led → Creator or Lover; performance and ambition → Hero. The archetype must match what the brand can sustain, not what sounds coolest.

3. Set the eight voice dimensions

Place the brand on each spectrum (1–5) with a one-line justification tied to the audience or positioning:

Dimension1 ←→ 5
FormalityFormal ↔ Casual
OptimismSober ↔ Optimistic
HumorSerious ↔ Humorous
ConfidenceHedged ↔ Confident
SophisticationSimple ↔ Complex
WarmthCold ↔ Warm
EnergyCalm ↔ Energetic
DirectnessIndirect ↔ Direct

Rule: push 2–3 dimensions to an extreme (1 or 5); leave the rest moderate. All-moderate settings produce a generic voice; all-extreme settings produce a caricature. The extremes are where distinctiveness lives — choose the ones the competition can't or won't match.

4. Write the enforcement rules

  • Do's / Don'ts — 5 each, all testable against a sentence ("Do open with the reader's problem, not our product"; not "Do be authentic").
  • Word choices — words/phrases the brand uses, and banned words (including the category's clichés).
  • Sentence structure — length tendency, active/passive, contractions, punctuation habits (em-dashes, exclamation marks), person (we/you/I).

5. Build the tone matrix

Voice is constant; tone flexes by context. For each context, state which dimensions shift and by how much — never the archetype:

Educational content · Sales/promotional · Customer support · Social media · Crisis communication

Example rule format: "Support: Warmth 4→5, Humor 3→1, everything else unchanged."

6. Prove it with rewrites

Take 3 real passages from the user's content (or draft realistic ones if pre-launch) and show before → after in the new voice, each with one line naming which rules drove the change. This is the acceptance test: if the rewrite isn't visibly different and better, the guide's rules are too vague — tighten them and redo.

Required output format

# Voice Guide — [Brand]

**Archetype:** [name] — [one-line why]
**Voice in one sentence:** [e.g., "A sharp, warm expert who talks like a person, not a deck."]

## Dimensions
| Dimension | Setting (1–5) | Why |
|---|---|---|
| Formality | ... | ... |
(all eight; mark the 2–3 extremes in bold)

## Rules
**Do:** 1–5 (testable)
**Don't:** 1–5 (testable)
**Say:** [preferred words/phrases] · **Never say:** [banned words]
**Sentences:** [structure rules]

## Tone matrix
| Context | Dimension shifts | Note |
|---|---|---|
| Educational | ... | ... |
| Sales | ... | ... |
| Support | ... | ... |
| Social | ... | ... |
| Crisis | ... | ... |

## Before / After
1. Before: "..." → After: "..." — [rule applied]
2. ...
3. ...

In audit mode, append: a scorecard of sampled content (pass/fail per rule) and the top 3 drift patterns to fix.

Quality bar (check before delivering)

  • 2–3 dimensions at an extreme, justified; not all-moderate, not all-extreme.
  • Every do/don't is checkable against a single sentence of copy — no "be authentic"-grade rules.
  • At least 3 before/after rewrites, using the user's real content when any exists.
  • Swap test: replace the brand name with its nearest competitor's — if the guide still fits them, it's too generic; sharpen the extremes and word choices.
  • Tone matrix changes dimensions only, never the archetype.
  • No claims about the brand's audience invented — inferences labeled as assumptions.

Integration

  • Upstream: skills/marketing/positioning-angles supplies the positioning statement — the claim the voice must carry. skills/marketing/orchestrator routes here as a foundation step.
  • Downstream: the voice guide is a required input to skills/marketing/direct-response-copy, skills/marketing/seo-content, skills/marketing/email-sequences, skills/marketing/newsletter, skills/marketing/content-atomizer, and skills/marketing/tweet-writer. What crosses the boundary is this document — paste or reference it whenever any of those skills write copy.

Download now (ZIP)

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.