agentsclimarketplace
Sign in

Marketing analytics

Skill m-binimran/marketing-pack/skills/marketing-analytics

Turn marketing metrics into insights and next actions - funnel, channel, campaign, and cohort analysis - using real data only. Use when reviewing performance or building a report.From its SKILL.md

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

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

1.4 KB, 283 tokens by cl100k_base, as published. Nobody here has run it

marketing-analytics

Numbers into decisions. Read the right metric for the goal; never invent a figure.

Read the right metric per goal

  • Acquisition: traffic by channel, CTR, CPC, CPL/CPA, ROAS.
  • Conversion: landing/page conversion rate, funnel drop-off, form completion.
  • Email: delivery, open, click, unsubscribe, conversion.
  • Retention/value: repeat rate, LTV, churn, cohort behaviour.

Process

  1. Use the real data (supplied or via a connector - GA4, ad platforms, ESP). Don't fabricate or guess benchmarks.
  2. Find the story: what's working (scale it), where the funnel leaks (fix it), what underperforms (cut it). Compare to the baseline/goal, not vibes.
  3. Attribute honestly - note attribution model limits; don't over-credit a channel.
  4. Recommend: 3 concrete next actions + one experiment (ab-test).

Output

  • A short report: top performers + why, the biggest leak, 3 actions, 1 experiment - every number real and sourced.

Guardrails

  • No fabricated metrics or benchmarks (truth-telling); mark missing data [verify].
  • Don't over-read small samples or short windows; state the limitation.

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 283 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

  • select metrics matching the goal
  • note attribution model limits
  • recommend three concrete actions
  • recommend one experiment
  • mark missing data with verify tag
  • state small sample limitations

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.