Budget rebalance
Skill foxgeeek/adskills/.claude/skills/cross-platform/budget-rebalance
Claude Code Skills framework for multi-platform ad operations — Meta, Google, LinkedIn Ads from the terminal / Framework de Claude Code Skills pra gestão de tráfego multi-plataforma
npx -y skills add foxgeeek/adskills --skill budget-rebalanceAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Recommend budget reallocation across Meta, Google, and LinkedIn based on per-platform CPA efficiency. Computes efficiency score (bestCPA/platformCPA) and weights budget proportionally. Read-only — recommendations must be applied manually. Triggers on prompts about where to shift budget or which platform to scale.
SKILL.md
1.7 KB, 344 tokens by cl100k_base, as published. Nobody here has run it
Cross-Platform — Budget Rebalance
When to use
- "Onde devo colocar mais budget?"
- "Qual plataforma tá com melhor CPA agora?"
- "Realoca $10k entre as 3 plataformas"
Inputs
--account— account ref--budget— total budget to allocate (required)--lookback— days (default 30)
Logic
- Fetch aggregated spend + conversions per platform over
lookbackdays - Compute CPA per platform =
spend / conversions - Efficiency =
minCPA / platformCPA(best platform = 100%, worse = lower) - Recommended allocation =
(platformEfficiency / sumEfficiency) × totalBudget - Delta =
recommended - currentShare(where currentShare is today's spend distribution over the same budget)
Output
- Summary cards: total budget, best CPA, lookback window
- Table per platform: spend, conv, CPA, efficiency %, current share, recommended, Δ
- Green/red deltas (green = give more, red = take away)
Invocation
adskills cross rebalance --account acme --budget 10000 --lookback 30
Guardrails
- Read-only — never mutates budgets on any platform
- Platforms with zero conversions are excluded from efficiency scoring (treated as 0%)
- Requires at least one platform with conversions; aborts gracefully otherwise
- Assumes conversion value parity across platforms — if conversion quality differs (e.g., MQL vs SQL), weight manually before applying