agentsclimarketplace

Brand voice

Skill propiter/landing-craft/skills/brand-voice

Trigger: write copy, marketing, landing page text, headline, CTA, value prop, email, social, ad, anti-slop, humanize content, brand voice, tono de marca. Write persuasive on-brand copy that does not read like AI.From its SKILL.md

Install
npx -y skills add propiter/landing-craft --skill brand-voice

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.4 KB, 557 tokens by cl100k_base, as published. Nobody here has run it

When to Use

Any user-facing words meant to persuade or sell: landing pages, headlines, CTAs, value props, onboarding, emails, ads, social. Pairs with frontend-design (the visuals); this skill owns the words.

Brand Brief (read FIRST)

Before writing, load the project brand brief if present: docs/brand-voice.md. If absent, ask for these 5 minimum and do not proceed without them: (1) what it is, (2) who it's for, (3) the pain it removes, (4) the feeling it should leave, (5) words/claims to avoid. NEVER invent brand facts, stats, testimonials, or features.

Anti-Slop Rules (mandatory ban list)

Cut on sight — these are AI tells:

  • Filler openers: "In today's fast-paced world", "In the realm of", "Unlock/Unleash the power of", "Elevate your".
  • Hype empties: "seamless", "robust", "cutting-edge", "game-changer", "revolutionary", "supercharge", "effortlessly", "next-level".
  • Hedge/bloat: "very", "really", "actually", "it's important to note", "delve", "leverage" (as a verb), "tapestry", "landscape", "journey".
  • Symmetry tics: "It's not just X, it's Y", triadic lists everywhere, em-dash overuse, every sentence the same length.
  • Emoji-as-punctuation and exclamation spam.

Voice Patterns

MoveDo
Lead with the benefitFirst line states the outcome the reader wants, in their words.
Concrete over abstractName the specific thing/number/moment, not the category.
One idea per lineShort. Vary rhythm — let a 3-word line land after a long one.
Speak to "you"Second person, active voice, present tense.
Earn every claimBack a superlative with a specific proof, or cut it.
CTA = verb + value"Start free", "See it live" — not "Submit", "Learn more".

Hard Rules

  • Read-it-aloud test: if a human wouldn't say it to a friend, rewrite it.
  • Match the brand brief's tone words; flag any line that drifts.
  • No claim without a proof the user supplied. Don't fabricate.

Output Contract

Return: the copy, plus a one-line note on the tone choices made and any brand facts still missing.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in 557 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • ask for brand brief details if absent
  • cut filler openers on sight
  • cut hype empty words on sight
  • cut hedge and bloat words on sight
  • cut symmetry tics on sight
  • lead with the benefit first

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.