agentleFS
narayan-metaflownarayan-metaflow/metaflow-marketing-skills/skills/meta-ads-playbook/SKILL.md

meta-ads-playbook

Skill14 starsChanged 7 months agoMITView on GitHub

Meta ads planning playbook: objectives, structure, audiences, creative, testing cadence, Pixel/CAPI measurement. Does not assume live Marketing API access.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Consolidate: when learning is fragmented.

    line 25
  2. Distinctive:

    Attribution: Call out that Meta reporting ≠ last-click GA.

    line 58
  3. Distinctive:

    If the user connects Meta via app integrations, Composio tools may apply—never guess tool slugs.

    line 68

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

When to Activate

Use this skill for Meta ads planning: objective selection, account structure, audiences, creative formats, copy, testing cadence, and measurement concepts (pixel, CAPI). Live Meta Marketing API access is not assumed unless the user has connected integrations—use llm_call (e.g. Perplexity) for policy and trend research and web_scrape for URLs the user provides.

First Questions

  1. Offer & conversion — Purchase, lead, app install, engagement? Value per conversion?
  2. Geo & placements — Countries; Feed, Stories, Reels, RHS; any placement exclusions?
  3. Budget & duration — Daily cap, flight dates, learning phase tolerance?
  4. Creative assets — Video UGC, static, catalog/DPAs, existing hooks?
  5. Data — Pixel/CAPI status, offline conversions, lists (customer file, engagement)?
  6. Brand constraints — Disclaimers, restricted categories, tone?

Objectives & Structure

  • Match campaign objective to true outcome (Sales / Leads / Traffic / Awareness)—avoid optimizing for clicks when you need purchases.
  • ASC / Advantage+ shopping vs manual: spell out tradeoffs (creative control vs automation).
  • Consolidate when learning is fragmented; separate when budgets or offers truly differ.

Audiences

  • Prospecting: Broad + creative feed, or interest/stacked signals when niche.
  • Remarketing: Site, engagers, customer lists—frequency caps and creative refresh.
  • Lookalikes (where available): Seed quality matters more than percentage size.
  • Exclusions: Purchasers, low-intent site sections, employees.

Creative

  • Formats: Single image, carousel, collection, Reels, short video—match platform norms (safe zones, thumb-stop in first 2s).
  • Angles: Pain, outcome, social proof, objection handling, urgency (honest)—rotate 3–5 concepts.
  • Copy: Primary text variants, headline, description; CTA button alignment with landing promise.
  • Fatigue: Plan refresh cadence and naming for tests.

Testing

  • Hypothesis: One clear variable (audience vs creative vs landing)—avoid multivariate soup.
  • Duration & spend: Enough conversions per cell; don’t call winners on noise.
  • Document: What was tested, result, next iteration.

Measurement & Privacy

  • Pixel + CAPI: Redundancy for web events; server-side helps iOS/signal loss—conceptual checklist only unless user provides integration status.
  • Attribution: Call out that Meta reporting ≠ last-click GA; compare definitions when user has both.
  • Consent: Mention when ads touch EU/UK and consent mode matters.

Tools and data sources

  • llm_call: Current policy questions, format specs, competitor public positioning research—do not fabricate metrics.
  • web_scrape: User-supplied landing pages, help articles, public policy pages.

If the user connects Meta via app integrations, Composio tools may apply—never guess tool slugs; follow integration search workflow when available.


Quality Gate (before final deliverable)

  • Objective matches business outcome and conversion definition
  • Campaign structure maps to prospecting vs retargeting (or catalog) clearly
  • Audience strategy stated with exclusions
  • Creative matrix: ≥3 angles × stated formats; hooks for video
  • Primary text / headline variants provided or templated
  • Test plan: hypothesis, budget split, minimum runtime guidance
  • Measurement checklist (pixel/CAPI/offline) with gaps flagged
  • Limitations stated: no live account data unless user provides exports or integrations

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.