agentleFS
aaronpdohertyaaronpdoherty/meta-ads-genius/skills/pulse/SKILL.md

pulse

Skill1 starsChanged 3 months agoMITView on GitHub

Quick Meta Ads account health check — last 7 days vs. prior 7, top-line deltas, learning status, fatigue and delivery flags, and the top 3 actions. Use when the user asks "how are we doing", wants a daily/weekly pulse, or before a standup. For deep diagnosis use ad-analysis; this is the fast scorecard.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ant, artistic and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • bergsideSkill

    ant

    Structured, enterprise-focused design system emphasizing clarity, consistency, and efficiency for data-dense web applications.

    Also in 3 projects that use this

  • bergsideSkill

    artistic

    High-contrast, expressive style with creative typography and bold color choices for visually striking interfaces.

    Also in 3 projects that use this

  • +10 more from bergside

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 3

    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:

    No API and no files → ask for an Ads Manager export (ad-set level, last 14 days, daily breakdown) and stop until it arrives.

    line 14
  2. Distinctive:

    No verdicts on in-learning entities.

    line 43
  3. Distinctive:

    Never recommend a live change here — actions are hand-offs to ad-optimization, with its approval flow.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 18 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

Account Pulse

A pulse is a 5-minute scorecard, not a report. Verdict first, numbers second, at most three recommended actions.

Data

  1. Freshest data wins: data/raw/ files covering the last 14 full days at ad-set level, else pull: python3 "${CLAUDE_PLUGIN_ROOT}/scripts/pull_insights.py" --level adset --last 14 --daily and python3 "${CLAUDE_PLUGIN_ROOT}/scripts/pull_structure.py" for statuses/learning info.
  2. No API and no files → ask for an Ads Manager export (ad-set level, last 14 days, daily breakdown) and stop until it arrives.

Compute (last 7 full days vs. prior 7)

  • Top line: spend · results (the account's primary event) · cost per result · vs. target from _config/account.md (no target set → say so, compare to trailing average).
  • Deltas: cost per result, CPM, link CTR, CVR — WoW %. Decompose the cost move: which of CPM/CTR/CVR drove it.
  • Flags (each with the entity named):
    • Learning: ad sets in learning or learning-limited (from structure pull / effective_status).
    • Fatigue: frequency >3.0 (prospecting) with CTR down ≥20% vs. prior week.
    • Delivery: active ads with ~zero spend; ad sets spending <50% of budget.
    • Pacing: 7-day spend vs. plan (monthly budget ÷ days) — over/under 15%+.
    • Change collisions: shifts that coincide with entries in optimization/CHANGELOG.md — attribute, don't alarm.

Output format

## Pulse — <date range>
**Verdict**: <one sentence: healthy / watch / act, and why>

| | last 7d | prior 7d | Δ |
|Spend|…|…|…|
|<Results>|…|…|…|
|Cost/<result> (target $X)|…|…|…|
|CPM / CTR / CVR|…|…|…|

**Flags**: <bulleted, entity-named, max 5 — or "none">
**Top actions**: 1) … 2) … 3) …   (each cites its number; anything execution-worthy routes to the ad-optimization skill)

Rules

  • 20–30% day-to-day cost variance is normal — flag only sustained (>3 days) or >50% moves as urgent.
  • No verdicts on in-learning entities; mark them "(learning)" in tables.
  • Sample honesty: under ~30 results/week account-wide, report weekly numbers only, skip the CVR decomposition.
  • Never recommend a live change here — actions are hand-offs to ad-optimization, with its approval flow.

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.