agentleFS
Sign inStart free
sp-hk2ldnsp-hk2ldn/SKILLS/apple-ads-discovery-promotion/SKILL.md

apple-ads-discovery-promotion

Skill0 starsChanged 5 days agoMITView on GitHub

Discovery, promotion, and isolation operational skill for Apple Ads. Use when converting Search Match/broad search terms into exact-match keywords and maintaining negative-keyword isolation with auditable thresholds.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add promoted terms as exact-match negatives in Discovery ad groups.

    line 19
  2. Distinctive:

    No deletes or budget changes in the same run.

    line 28
  3. Distinctive:

    No destructive changes without explicit user confirmation.

    line 31
  4. Distinctive:

    Do not remove discovery coverage before replacement exact terms are active.

    line 32
  5. Distinctive:

    Keep Search Match isolation behavior explicit in output recommendations.

    line 33
  6. Distinctive:

    Treat pause, negate, delete, and bulk deactivation actions as recommendation-only until the user explicitly approves execution.

    line 34
  7. Distinctive:

    Before running CLI commands or interpreting Insights, read the Platform API agent guidance.

    line 35
  8. Very specific:

    Read references/discovery-promotion-sop.md for thresholds and automation spec fields.

    line 38

≈ “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

Discovery -> Promotion -> Isolation

Use when

  • A user asks for weekly keyword optimization workflow.
  • A user asks how to promote search terms from discovery campaigns.
  • A user wants an automation spec for safe keyword expansion and isolation.

Workflow

  1. Pull Discovery search term and keyword/ad-group performance data for the configured window.
  2. Normalize and dedupe terms; exclude terms already added as exact keywords or negatives.
  3. Score terms by promotion thresholds (taps, installs, CPA, TTR).
  4. Classify winners into Brand/Category/Competitor targets.
  5. Promote winners as exact-match keywords in target ad groups.
  6. Add promoted terms as exact-match negatives in Discovery ad groups.
  7. Emit audit logs and reasons per term (why promoted/skipped).

Default policy

  • Weekly cadence (or twice weekly).
  • 14-day lookback.
  • Exclude most recent 24-48 hours for lag.
  • Dry-run by default.
  • Cap number of new keywords per run.
  • No deletes or budget changes in the same run.

Guardrails

  • No destructive changes without explicit user confirmation.
  • Do not remove discovery coverage before replacement exact terms are active.
  • Keep Search Match isolation behavior explicit in output recommendations.
  • Treat pause, negate, delete, and bulk deactivation actions as recommendation-only until the user explicitly approves execution.
  • Before running CLI commands or interpreting Insights, read the Platform API agent guidance. It covers explicit account selection, SOV metric limits, unsupported operations, and write recovery.

References

  • Read references/discovery-promotion-sop.md for thresholds and automation spec fields.

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