agentleFS
alectivismalectivism/maven-template/.claude/skills/content-draft/SKILL.md

content-draft

Skill1 starsChanged 6 months agoMITView on GitHub

Marketing content in MMA voice — blog posts, newsletter articles, thought leadership, web copy, one-pagers.

5 other projects use 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. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    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:

    When relevant, weave in MMA research and programs as evidence:

    line 32
  2. Distinctive:

    Use Marketing + Media Alliance (MMA) on first reference

    line 42
  3. Distinctive:

    Never "the MMA" — just "MMA"

    line 43
  4. Distinctive:

    Create outline for approval

    line 51

“Common” is measured: kept by at least 6 in 10 of the 5 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

Content Creation — MMA Standards

Brand Voice

Hero archetype: energetic, sharp, smart, clear, confident, generous.

Writing Principles

  • Lead with insight, not introduction — skip "In today's rapidly evolving landscape..."
  • Data-first claims — back assertions with MMA research (CAP +160%, MMGF +50% ROAS, BaP 6x favorables, MOSTT 1% = +2.5% YoY revenue)
  • Active voice throughout
  • Specific over vague — "825+ members across 16 countries" not "a large global membership"
  • Short paragraphs — 2-3 sentences max for digital content
  • Subheads every 2-3 paragraphs for scannability

Tone by Content Type

TypeToneLength
Blog postAuthoritative, energetic800-1200 words
Newsletter articleConcise, action-oriented300-500 words
Thought leadershipAnalytical, provocative1000-2000 words
One-pagerDense, data-driven1 page
Web copyClear, benefit-focusedVaries
Social teaserSharp, curiosity-driving1-3 sentences
Press releaseWire-ready, journalistic, factual400-550 words (body)

MMA Programs to Reference

When relevant, weave in MMA research and programs as evidence:

  • CAP: +160% average lift vs BAU across 29 experiments, 18 brands
  • AURA: +24% average lift, 90% showed incremental conversion improvement
  • MMGF: +50% ROAS vs reach-based plans (Movable Middles)
  • BaP: Brand favorables activate ~6x vs non-favorables
  • MOSTT: 1% improvement in marketing capabilities fit = +2.5% YoY revenue growth
  • DAM: 9,300+ registrations, 5,000+ attendees, 2,100+ certified
  • State of M&A: Industry's longest-running measurement study (Wave 10 in 2026)

Formatting

  • Use Marketing + Media Alliance (MMA) on first reference
  • Never "the MMA" — just "MMA"
  • Spell out acronyms on first use: Consortium for AI Personalization (CAP)
  • For Word docs: Aptos 12pt
  • For presentations: Söhne Leicht body, Söhne Halbfett headers

Process

  1. Clarify content type, audience, key message, and distribution channel
  2. Research topic using web search if needed
  3. Create outline for approval
  4. Draft full content
  5. Self-audit against MMA brand checklist:
    • Leads with insight, not throat-clearing
    • Data points sourced from MMA research where applicable
    • Active voice throughout
    • MMA naming conventions followed
    • Appropriate length for content type
    • Clear CTA or next step

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.