agentleFS
Sign inStart free
F0rger123F0rger123/claude-meta-ads-god-mode/skills/ads-reporting/SKILL.md

ads-reporting

Skill1 starsChanged 23 days agoMITView on GitHub

Business-owner-friendly advertising reports for Meta and Google Ads - spend, results, cost per result, revenue/ROAS, what won, what lost, what changed, what to do next - followed by platform detail only where it matters. Use for "report", "how did ads do", "weekly/monthly update", "review <client> ads this week".

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:

    Never promise future results.

    line 34

≈ “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

Ads reporting

Workflow: workflows/reporting.md. Templates: templates/monthly-report.md, templates/optimization-report.md.

Owner summary first (always this order)

<CLIENT> - <platforms> - <date range> (vs <previous range>)

SPEND            $2,140  (+6%)
RESULTS          27 leads (+4)   · 9 qualified (CRM)
COST PER RESULT  $79 per lead (-3%) · $238 per qualified lead
REVENUE / ROAS   2 jobs sold, $71k (if known) - otherwise "not tracked yet"

WHAT WON         one or two lines, with the number
WHAT LOST        one or two lines, with the number
WHAT CHANGED     changes we made + outside changes (season, tracking, competitors)
WHAT WE DO NEXT  2-4 concrete actions, each marked needs-approval or not

Then platform detail (only metrics that explain the summary): Meta - campaign/ad set table, top ads, frequency/fatigue, learning status; Google - campaigns, search-term waste, impression share, QS issues.

Rules

  • Plain language. Define any metric you must use. No metric dumps.
  • Compare like with like: same length windows, same attribution settings; flag the Jan-2026 Meta attribution change if the comparison spans it.
  • Say how confident each statement is when data is thin ("only 6 leads - directional").
  • Business truth over platform numbers: show CRM-qualified leads when available.
  • Never promise future results; give ranges and the assumptions behind them.
  • One client per report.

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