gooseworks-ai/goose-skills / skills/marketing/run-paid-campaigns
run-paid-campaigns
VerifiedRuns the paid leg of an approved plan: checks tracking, pages and stock before money moves, then stages one weekly proposal of kills, scales, pauses, swaps and launches, each with its reason and a check date. Nothing changes without your yes. Use when: launch these ads; it's Monday — kill, scale or pause?; swap this fatiguing ad; we sold out or the sale ended — pause the ads now; an ad got rejected or the account got restricted; we're in a brand crisis — hold the ads; give me the Google, TikTok or LinkedIn changes to make. Not for how the ads did or which ad won — use analyze-performance; not for rewriting a rejected image ad — use make-static-ads.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.9 KB |
| references/baseline-audit.md | markdown | 2.6 KB |
| references/launch-and-graduate.md | markdown | 7.7 KB |
| references/local-mode.md | markdown | 2.8 KB |
| references/meta-levers.md | markdown | 8.1 KB |
| references/moves.md | markdown | 8.1 KB |
| references/proposal-and-log.md | markdown | 19.6 KB |
| references/reading-results.md | markdown | 7.9 KB |
| references/run-memory.md | markdown | 18.7 KB |
| references/written-instructions.md | markdown | 4.5 KB |
| skill.meta.json | config | 6.8 KB |
| tests/test-by-hand.md | markdown | 10.5 KB |
references/baseline-audit.md
View on GitHub# First-run account baseline
Load at step 0, the first time this playbook runs on an account (and again when the structure changed a lot). A senior operator never moves money in a new account before knowing its shape. Use the marketer's exports (campaign / ad set / ad, last 30 days if they have it, else 14) plus, with GooseWorks, `meta_read` performance for the ads GooseWorks made (local mode: the connector's account-wide reads instead, `local-mode.md`). Do this first, because every later move depends on whether the account can learn at all.
## What to map
| Look at | How | What it usually seeds |
|---|---|---|
| **Ad sets vs the learning floor** | per ad set: optimisation event, conversions in the last 7 days vs ~50 (Meta's guideline), daily budget vs ~50 × allowable ÷ 7 | consolidation instructions (merge thin ad sets into one, broad targeting); a higher-funnel event if even one can't be fed |
| **Overlap and fragmentation** | several ad sets with similar audiences, interest stacks, one ad per ad set | consolidation; audience exclusions (purchasers out of prospecting) |
| **Spend concentration** | share of spend on the top concept and the top 3 ads | if one ad carries > ~50%: a rotation request before it fatigues; if spend is spread over 20+ ads with few conversions each: fewer, stronger concepts |
| **Creative age and mix** | days live per top ad; formats (static / video / carousel), angles (from the makers' tags where present) | rotation cadence; gaps in formats the placements need |
| **Click-rate trend on the top ads** | 3-day vs 14- or 28-day click rate at similar spend | early fatigue flags |
| **Retargeting and brand share** | spend on retargeting and brand-search vs prospecting | keep them out of the scale case (low incrementality); cap retargeting share |
| **Tracking and attribution** | conversion event firing, attribution setting, platform conversions vs store orders (from the weekly read) | fix moves; whether results can be trusted this week |
| **Account hygiene** | spending limit set, payment method, rejected ads, special ad category declared where needed | instructions |
## Output
A short "Account at a glance" block as the first section of the first proposal's story (`### Account at a glance`, before Checks and pacing; the main finding also goes in In short): 5–8 lines, each a finding with its number and the move it seeds ("4 of 6 ad sets get under 10 purchases a week — I propose merging them into one (move 3)"). Record the baseline date and the key counts in `state.md`'s header so later runs can see what changed. No moves are applied from the audit by itself — they go into the same proposal and the same approvals.
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 |