iamwaqargulzar/Marketing-Agent-OS / skills/ads
ads
VerifiedWhen the user wants to plan, run, or fix paid ads on Google, Meta, and LinkedIn, or asks a judgement call on them: are ads worth it, which channel or budget split, why CPA rose, kill or keep a campaign. End with facts, hypotheses, and missing data; label unavailable inputs MISSING instead of estimating. For ad copy, see ad-creative. For pixels and CAPI, see conversion-tracking. For landing pages, see cro.
references/operating-review.md
View on GitHub# Paid account operating review
Read the user's current targets, floors, budget/pacing, conversion definition, known tracking weaknesses, and approved changes. Check prior experiments/learnings when provided; an unavailable input is missing evidence, not a number to invent.
Use equivalent closed windows and appropriate conversion lag. Inspect spend/pacing, auction/traffic, conversions and downstream quality, creative, landing experience, and tracking, then compare change history. This is a diagnostic order, not proof that the first correlated movement caused the rest.
Return HOLD when evidence supports no action, FIX for a supported issue with a reversible proposal, TEST for a hypothesis with metric/sample/stopping rule, or INVESTIGATE when critical evidence is unreliable. Evidence uncertainty can veto scaling even if a dashboard appears healthy. These are recommendations, not permission to alter budget, bids, status, tags, or audiences.
Separate facts, hypotheses, missing data, and what would change the decision. Name tracking uncertainty and route conversion delivery to conversion-tracking. Tie each proposed action to the exact account/campaign, current state, payload, expected outcome, risk, owner, and rollback.
For behavioral retargeting, define evidenced audiences, recency, exclusions, consent, frequency, and message sequence; verify platform eligibility instead of inventing audience-size or delivery guarantees. For creator ads, evaluate distinct concepts, approved rights, brand safety, quality outcomes, and spend limits instead of using creative count or view rate as a universal scaling rule.
Keep the stakeholder summary short and decision-ready. Schedule only when requested, through the host's supported mechanism; the review itself creates no recurring task or account write.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |