agentleFS
Sign inStart free
ldaumeldaume/agentic-engineering-harness/skills/writing/writing-marketing/SKILL.md

writing-marketing

Skill3 starsChanged 3 months agoMITView on GitHub

Use whenever writing or revising a hero section, landing page, homepage, service or product page, website copy, CTA, or marketing email or newsletter, in German or English (Hero schreiben, Landingpage, Website-Texte, Marketing-Mail). Carries the value-first narrative (what you get, how it compounds, proof, next step), evidence discipline against invented proof, and golden examples. Prefer it over generic copywriting skills when the copy must be value-first, evidence-bound, or German. Page layout and visual design belong to design-web.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Remove unsupported claims and generic hype.

    line 28
  2. Distinctive:

    Check message-to-CTA continuity: the CTA names the next step the copy earned.

    line 30
  3. Distinctive:

    Never invent customer logos, testimonials, metrics, market leadership, urgency, scarcity, certifications, or case-study outcomes, because …

    line 36
  4. Distinctive:

    If the file is missing (this skill was installed alone), check the artifact's checklist in its reference by hand.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Marketing & UX Writing

Help one defined reader see a valuable change, believe it, and take the next useful step.

Public narrative

Lead with positive value: what the reader gets, how that value compounds, the mechanism or proof that makes it credible, then the next useful conversation or action. Do not default to grievance, competitor bashing, anti-framework positioning, or "not for you" hooks, because contrast-first copy defines you by what you oppose and loses readers who never had the problem. When writing in a specific person's or brand's voice, also load that voice guide or skill.

Workflow

  1. Define segment, situation or trigger, and one primary job for the page or message.
  2. Extract the valuable change; separate capability from consequence.
  3. Identify the mechanism and the evidence that exists.
  4. Shape the information architecture, then draft.
  5. Remove unsupported claims and generic hype; replace adjectives with specifics.
  6. Check message-to-CTA continuity: the CTA names the next step the copy earned.
  7. Native DE/EN edit.

Evidence discipline

Never invent customer logos, testimonials, metrics, market leadership, urgency, scarcity, certifications, or case-study outcomes, because public copy is checkable and one fake proof point discredits the page. When proof is missing, write more specifically and flag the gap to the user.

Route

  • marketing email: references/marketing-email.md
  • hero section: references/heroes.md
  • landing page: references/landing-pages.md
  • homepage, service page, website content: references/web-content.md

Gate

From this skill's directory, run python3 ../writing-core/scripts/quality_gate.py --artifact <type> --lang <de|en> FILE with type one of marketing_email|hero|landing_page|website_content. If the file is missing (this skill was installed alone), check the artifact's checklist in its reference by hand. Fix every error; judge each warning, because warnings are heuristics, not rules.

Done when

The reader can answer: is this for me, what changes for me, how does it work, why believe it, what do I do next.

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.

Check your setup, free