agentleFS
gomarble-aigomarble-ai/marketing-agent/skills/meta-creative-strategy/SKILL.md

meta-creative-strategy

Skill15 starsChanged 36 days agoMITView on GitHub

Full creative strategy pass for Meta Ads. Identifies winners + losers across the account, extracts the pattern behind each winner (hook, format, angle, audience pairing), produces a test plan + scaling plan + fatigue check, and outputs a concrete 12-creative production spec (6 static + 6 video) with hook lines, angles, and CTA recommendations. Read-only — no ads built. Use when a brief asks "what should we test next" or before a creative production sprint.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    If the user didn't name an account, list their connected accounts and ask which one to use.

    line 11

≈ “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

Meta Creative Strategy (Read-Only)

For the ad account the user names, produce a complete creative strategy pass. Default lookback: 30 days. Read-only — no ads built or modified.

If the user didn't name an account, list their connected accounts and ask which one to use.

Section 1 — Winners + losers

  • Top 10 ads by ROAS with sufficient spend (≥ $500 / 14d or 100+ purchases)
  • Bottom 10 ads by ROAS with sufficient spend
  • For each: spend, ROAS, CPA, hook rate (3s view %), hold rate (15s view %), thumbstop rate

Section 2 — Pattern extraction

For the winners, identify common patterns across these dimensions:

  • Hook style — pain point / curiosity / social proof / pattern interrupt / UGC opener
  • Format — talking-head / product demo / lifestyle / before-after / split-screen
  • Angle — value / urgency / aspiration / fear / convenience
  • Audience pairing — what audience type does each winner pair best with

Output a short table: Pattern | # of winners using it | Avg ROAS.

Section 3 — Fatigue check on winners

Flag any winner that's showing fatigue signals (frequency > 4, CTR declining > 25% from week 1, CPA creeping up > 25%). These are "still winning but on borrowed time" — first priority to remix.

Section 4 — Test plan

3–5 hypotheses to test next. Each:

  • Hypothesis (one sentence)
  • What to vary vs control
  • Success metric + threshold
  • Budget allocation suggestion

Section 5 — Scaling plan

For each healthy winner with strong ROAS:

  • Suggest budget headroom (% increase)
  • Audience expansion suggestion (broader lookalike, geo expansion, etc.)
  • Risk flag (fatigue ceiling, audience saturation)

Section 6 — 12-creative production spec

Concrete spec for 6 static + 6 video creatives. For each:

  • Format + dimensions (1:1 / 4:5 / 9:16)
  • Hook line (the first 1–3 words on screen)
  • Angle + audience pairing
  • Reference to which winner pattern it remixes

End with: _Strategy doc — no ads built. Hand this to your creative team or use the launch-campaigns skill to build any of the 12 specs._

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.