agentsclimarketplace
Sign in

Ad copy

Skill m-binimran/marketing-pack/skills/ad-copy

Write paid ad copy for Google, Meta, or LinkedIn - hooks, headlines, primary text, and CTAs - matched to platform specs and the offer. Use when creating ads for a campaign.From its SKILL.md

Install
npx -y skills add m-binimran/marketing-pack --skill ad-copy

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.

SKILL.md

1.3 KB, 282 tokens by cl100k_base, as published. Nobody here has run it

ad-copy

Stop the scroll / win the click, then keep the promise on the landing page.

Process

  1. Anchor: persona pain, the offer, the one message (value-prop), and the destination (message-match!).
  2. Hook on the outcome or pain - lead with what they get, not your brand name.
  3. Write to platform format:
    • Google Search: multiple headlines (<=30 chars) + descriptions (<=90); keyword-relevant, benefit-led, 1 CTA.
    • Meta: primary text (hook first line), headline, description; thumb-stopping, native tone.
    • LinkedIn: professional, outcome + credibility, B2B-aware.
  4. Variations to test: different angles (pain, outcome, social proof, urgency-but-honest) - hand to ab-test.
  5. One clear CTA.

Output

  • Ad variations per platform (with char counts), each with the angle it tests, plus the matching landing message.

Guardrails

  • Substantiate claims ("#1", "guaranteed") or cut them - claim-guard/truth-claims.
  • Honest urgency only (no fake countdowns). Message must match the landing page.
  • Follow each platform's ad policies (prohibited/restricted claims).

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 282 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

  • follow each platform's ad policy
  • match ad copy to platform format and offer
  • hook on outcome or pain
  • write platform-specific headline and text variations
  • include character counts for each ad variation

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.